From patchwork Tue May 28 14:07:12 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799490 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257757wrz; Tue, 28 May 2024 07:13:39 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWpgrlrX8zzmJfbOQrTBymcTK4zPxgkUnhxpYQm1sijeiiMxt5e858sGhGfjCy7W5vIlzKUaiWnKBLDoj3I1GFq X-Google-Smtp-Source: AGHT+IGJLqyNPhNbPLkpAhMU2TRnBJBIEY16qvW7ldf3nLlRk5DRJ9IRFWXpTZlC+6O7LBAmlxfo X-Received: by 2002:a9d:7649:0:b0:6eb:5b4a:867f with SMTP id 46e09a7af769-6f8d0a7b9demr15732202a34.22.1716905619323; Tue, 28 May 2024 07:13:39 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905619; cv=none; d=google.com; s=arc-20160816; b=Q7p9gKeVtg6jMgaGMtIXphyi8AMz6jES0t/K6NyQniNUIVY0n9k29fKsLS2DL4GfyG qfs3bGr4y3bRo34hX/vMVwRElIyEXy3u6xH8gackOxD/ehUpveRcSbh0HI3zq0Ef6N6y FxEos6nAaLZnUILgQfZn1EKJacuGCtrYAzbu7gBbq8EFuA4sEoZ+GbPq3NJSQalCYR7d WVd7UJRIbUyuCNkmfqm5ovdNIW/LU5dJEMTwrELEgdF+8ScT5RSvsA9psADBkdcrolTo kdCpsNDe34LNZ3ttxSH6geyhBIXBPwcV1D+eAhVVHXqkStyVXU4jYUqYCI/FpaJ0JTBZ FnWA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=AsQRQeKjgMaSSmYepAKdEFvTM+lwKQ9eFt3DVA5Soas=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=c+du6DUY/9I5PT9hJ/NAYUGyEfgtowmFP3d1fhV2Qk9drZvxoOjiWR2n833Tj6UIX5 mej3+9RxtVFnfCDIYtKpOjC7+hE3ihOiAYWKDPxAKxipznBcDz+Q9gwHymdVtgk4lVmG jaxLIkQzLgizJ/WkIv4F1LbXh0S1xeWEvbcTsfx5A+d3aBre9MrpoPPNR60lGcZ4wGLP 1m1wcOfNJScOA2+On95PTCOTlnXptWcq8KUL+iBAdI4TIoOJPg24WtjaRsRru4E4WiNp NLZ5F+hCgrR6hAv+VIqlLVoXtnjHjvA+I6jBwNavWjY8rIQss81jLWlzfYQLkJ5r7yok THXg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=kI5ggoQj; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a2f0de0si2227243137.287.2024.05.28.07.13.39 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:39 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=kI5ggoQj; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUh-0001VT-MX; Tue, 28 May 2024 10:08:03 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUf-0001Ts-7R for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:01 -0400 Received: from mail-wr1-x42b.google.com ([2a00:1450:4864:20::42b]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUc-00070A-FA for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:00 -0400 Received: by mail-wr1-x42b.google.com with SMTP id ffacd0b85a97d-351da5838fcso810467f8f.1 for ; Tue, 28 May 2024 07:07:58 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905277; x=1717510077; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=AsQRQeKjgMaSSmYepAKdEFvTM+lwKQ9eFt3DVA5Soas=; b=kI5ggoQj2nP6FxdUW0bGZ9XzdctSvs8aV1H1+IqyY1ElSwQnqwcr0lq1VHtrIdndOU TOydKExB68kFUL9mlZd+Sg1co1FOmj9doZtPw3CxCOpvgeHJqhgQs5TAdo7dS6ooJoF6 DNvLkoYHoEGgfs5+TkQ2SQ6G6BK+X8ZX7X3NC+kn9Eqg4MT/998CbKc68er+RRkE/pNc WR/gguHGyIr4atKpbIMVlxEBWfyeMFavOCO0ZSBWDmob25D/gBGpk4A8Gg8bzPOv50lZ PXcszROAgU8Q297b1R5jqVm/uwixpEZIvjK4qtN3UQ91HDd/G1joN5xag1Js9P+HhLow 3QFA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905277; x=1717510077; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=AsQRQeKjgMaSSmYepAKdEFvTM+lwKQ9eFt3DVA5Soas=; b=PQfYb++MzOtTQvHeVal//o62NEDV/sfrcxX0RU/gBU/BrlenzJDl+/hDTYkAIlOQyZ Ubt7nglr27U160JWgeRCh5DxvYdcU6/yFzKj2L4BOBGJnPdqMzr2XuIkDDWqSp4iv0CK 8gt/VE+trEd2RICKPQ7aEiTEqnrS5ZHpNkfG0Uz/DDioFQHXskm9PzA+wh/pHtjUUFit DAihZxPr5b3067hGGc5oCR53VYP/QPb9xKTu8icddGnY3t4PfqR13/pACOSASIQ5aO+D tALkD1JDE62rGHqfiQI0KVeyucWR1Fy3uBKPO5ZZazgUZr9QQ3eGpuEnO+kz6VbZijQn r8bQ== X-Gm-Message-State: AOJu0YzQiQ28uDaVNYGdruL6VgeVsKe/zJCsE3ImCWikI/1ay+teQyM8 9HMtuy3XS5oriHeXhaCuaa7XqmZ2TAPdRsVpkGRtZrjLNdAYqpZ2zip106HH/SBGC+ONI7kffGu i X-Received: by 2002:a5d:4f8b:0:b0:355:2c1:cbba with SMTP id ffacd0b85a97d-3552217f5c2mr8805791f8f.16.1716905276615; Tue, 28 May 2024 07:07:56 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.56 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:56 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 01/42] xlnx_dpdma: fix descriptor endianness bug Date: Tue, 28 May 2024 15:07:12 +0100 Message-Id: <20240528140753.3620597-2-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42b; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42b.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Alexandra Diupina Add xlnx_dpdma_read_descriptor() and xlnx_dpdma_write_descriptor() functions. xlnx_dpdma_read_descriptor() combines reading a descriptor from desc_addr by calling dma_memory_read() and swapping the desc fields from guest memory order to host memory order. xlnx_dpdma_write_descriptor() performs similar actions when writing a descriptor. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: d3c6369a96 ("introduce xlnx-dpdma") Signed-off-by: Alexandra Diupina [PMM: tweaked indent, dropped behaviour change for write-failure case] Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/dma/xlnx_dpdma.c | 68 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 64 insertions(+), 4 deletions(-) diff --git a/hw/dma/xlnx_dpdma.c b/hw/dma/xlnx_dpdma.c index 530717d1885..dde4aeca401 100644 --- a/hw/dma/xlnx_dpdma.c +++ b/hw/dma/xlnx_dpdma.c @@ -614,6 +614,65 @@ static void xlnx_dpdma_register_types(void) type_register_static(&xlnx_dpdma_info); } +static MemTxResult xlnx_dpdma_read_descriptor(XlnxDPDMAState *s, + uint64_t desc_addr, + DPDMADescriptor *desc) +{ + MemTxResult res = dma_memory_read(&address_space_memory, desc_addr, + &desc, sizeof(DPDMADescriptor), + MEMTXATTRS_UNSPECIFIED); + if (res) { + return res; + } + + /* Convert from LE into host endianness. */ + desc->control = le32_to_cpu(desc->control); + desc->descriptor_id = le32_to_cpu(desc->descriptor_id); + desc->xfer_size = le32_to_cpu(desc->xfer_size); + desc->line_size_stride = le32_to_cpu(desc->line_size_stride); + desc->timestamp_lsb = le32_to_cpu(desc->timestamp_lsb); + desc->timestamp_msb = le32_to_cpu(desc->timestamp_msb); + desc->address_extension = le32_to_cpu(desc->address_extension); + desc->next_descriptor = le32_to_cpu(desc->next_descriptor); + desc->source_address = le32_to_cpu(desc->source_address); + desc->address_extension_23 = le32_to_cpu(desc->address_extension_23); + desc->address_extension_45 = le32_to_cpu(desc->address_extension_45); + desc->source_address2 = le32_to_cpu(desc->source_address2); + desc->source_address3 = le32_to_cpu(desc->source_address3); + desc->source_address4 = le32_to_cpu(desc->source_address4); + desc->source_address5 = le32_to_cpu(desc->source_address5); + desc->crc = le32_to_cpu(desc->crc); + + return res; +} + +static MemTxResult xlnx_dpdma_write_descriptor(uint64_t desc_addr, + DPDMADescriptor *desc) +{ + DPDMADescriptor tmp_desc = *desc; + + /* Convert from host endianness into LE. */ + tmp_desc.control = cpu_to_le32(tmp_desc.control); + tmp_desc.descriptor_id = cpu_to_le32(tmp_desc.descriptor_id); + tmp_desc.xfer_size = cpu_to_le32(tmp_desc.xfer_size); + tmp_desc.line_size_stride = cpu_to_le32(tmp_desc.line_size_stride); + tmp_desc.timestamp_lsb = cpu_to_le32(tmp_desc.timestamp_lsb); + tmp_desc.timestamp_msb = cpu_to_le32(tmp_desc.timestamp_msb); + tmp_desc.address_extension = cpu_to_le32(tmp_desc.address_extension); + tmp_desc.next_descriptor = cpu_to_le32(tmp_desc.next_descriptor); + tmp_desc.source_address = cpu_to_le32(tmp_desc.source_address); + tmp_desc.address_extension_23 = cpu_to_le32(tmp_desc.address_extension_23); + tmp_desc.address_extension_45 = cpu_to_le32(tmp_desc.address_extension_45); + tmp_desc.source_address2 = cpu_to_le32(tmp_desc.source_address2); + tmp_desc.source_address3 = cpu_to_le32(tmp_desc.source_address3); + tmp_desc.source_address4 = cpu_to_le32(tmp_desc.source_address4); + tmp_desc.source_address5 = cpu_to_le32(tmp_desc.source_address5); + tmp_desc.crc = cpu_to_le32(tmp_desc.crc); + + return dma_memory_write(&address_space_memory, desc_addr, &tmp_desc, + sizeof(DPDMADescriptor), MEMTXATTRS_UNSPECIFIED); +} + size_t xlnx_dpdma_start_operation(XlnxDPDMAState *s, uint8_t channel, bool one_desc) { @@ -651,8 +710,7 @@ size_t xlnx_dpdma_start_operation(XlnxDPDMAState *s, uint8_t channel, desc_addr = xlnx_dpdma_descriptor_next_address(s, channel); } - if (dma_memory_read(&address_space_memory, desc_addr, &desc, - sizeof(DPDMADescriptor), MEMTXATTRS_UNSPECIFIED)) { + if (xlnx_dpdma_read_descriptor(s, desc_addr, &desc)) { s->registers[DPDMA_EISR] |= ((1 << 1) << channel); xlnx_dpdma_update_irq(s); s->operation_finished[channel] = true; @@ -755,8 +813,10 @@ size_t xlnx_dpdma_start_operation(XlnxDPDMAState *s, uint8_t channel, /* The descriptor need to be updated when it's completed. */ DPRINTF("update the descriptor with the done flag set.\n"); xlnx_dpdma_desc_set_done(&desc); - dma_memory_write(&address_space_memory, desc_addr, &desc, - sizeof(DPDMADescriptor), MEMTXATTRS_UNSPECIFIED); + if (xlnx_dpdma_write_descriptor(desc_addr, &desc)) { + DPRINTF("Can't write the descriptor.\n"); + /* TODO: check hardware behaviour for memory write failure */ + } } if (xlnx_dpdma_desc_completion_interrupt(&desc)) { From patchwork Tue May 28 14:07:13 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799494 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257858wrz; Tue, 28 May 2024 07:13:51 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWzZw6ZrHDlSgc/UR5V5Z+sdAN5riO2A/V5FKT7B15yQTIwqc2DSX+/abwy/FxXVQadjK/BOtpYqkt+wYPAS+b/ X-Google-Smtp-Source: AGHT+IEJvaLeCOGlQUlly8yAgyv1J0U8hB70L69XNUg2kvRawVutIU/KKWAMjDGTcMUN7XqvlV3x X-Received: by 2002:a05:6102:1499:b0:47c:2a61:ec9 with SMTP id ada2fe7eead31-48a386d2a5amr14859479137.25.1716905631487; Tue, 28 May 2024 07:13:51 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905631; cv=none; d=google.com; s=arc-20160816; b=ZkfPN2BkiCx9Djoi4QV/zl4AS/ymycpuE0lAzgk63aBzh+SC7M87fnHfGPXggsfmK7 +LF7GaWuBkpP7l3gMKsYizUxfNe7S7SW1r/Tw76ctJllvrmtl1zl9BpmPV+FGM+sFkBf aFKQoHZ2vTbYRQjhEmF5lsCfPgTzQ3TMP6aiY3KvMTE07qZQ0PRyNuT2ETIAP5eBU8Rv 1Oa7d3SxE/Hp5Ib2y+ayzss3hcQnzXHCvGf6nbE2JkZmYUMucmlkIR0M5bP67/75/nsW HsoZe9GCTUu4s88mXIYnhjvvklEweaZmjZGOaUjxhIF+2Sd65yQg+qU24IVlrMkI4IJi EW1w== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=8YxNpQoelVW24RPVvumPTEVnZuR0kkw8zkh8/F6BNsc=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=s2e6KruMmHjBxwEcUw7ETSwvQYP1YMH/6Y65888GbYrvojCazq86REs8PYgoA3lusd lIhzKzqkiUkQJDHn9K9br7d2ovnSLwAlKC7kpPgSDIB7mAXoe4K68/7ei1gqBlqP33A3 cExXt4bHGyxo8d/sB0ST5wnYC7Dutbo/peOCv2q4WWSuGfXJlP5qsr760dHJvPhXRh6g LmGwyZnOGzg6iR1KIqyH5jezWFzR47Oo8bFhth9A3EROmUCbiFtZ0ujDvIEZEloJ8/73 COvV7pKon4cNHiFXBxT2f9/JnV7KPIl2MMH25hGhn8i+K/nbZbmVk4a04WsIuSHd5S4u dsCw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=tW2kQxZ8; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a204ebesi2132255137.47.2024.05.28.07.13.51 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:51 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=tW2kQxZ8; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUh-0001VS-EZ; Tue, 28 May 2024 10:08:03 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUf-0001UC-Gz for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:01 -0400 Received: from mail-wr1-x429.google.com ([2a00:1450:4864:20::429]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUc-00070E-Oi for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:01 -0400 Received: by mail-wr1-x429.google.com with SMTP id ffacd0b85a97d-354de97586cso1058701f8f.0 for ; Tue, 28 May 2024 07:07:58 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905277; x=1717510077; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=8YxNpQoelVW24RPVvumPTEVnZuR0kkw8zkh8/F6BNsc=; b=tW2kQxZ8FlbaRJMHd7aUCVmAeK/yH128bPt5Ry5fHIeivEUFCoKwO1AgWqU92IBaSM u7akjZdFVKXpml8a3ID2xEFsyK7i3BHMjPirIz40xqLZc2G5l+QHIaofLyOa5/nol3Pp ssupgT484k43JC0/5aQIcRdsVde0Vlc6iLMIJtIORhPfEsToAX6ww3fbNefea+a/TqNe Cft/VBIjgdIp1YwYk6bUmhgQjqIgNSyLDLRwU3VmiHnMYjMEpKSN2WzjS4Dq7V2rAFXr j1E8mPuyF/WKpYpgLYDHb7e+hbHZY/uvuIuuEkM+VFK3X+mRueTwQEwFCneZB5FcgzKL 8Taw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905277; x=1717510077; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=8YxNpQoelVW24RPVvumPTEVnZuR0kkw8zkh8/F6BNsc=; b=qAs2Nr9gA4J8qF0/E2Nca3MA8IV+sPWMDWB59r0eTMkt1tZhzVna5+NTFH4bXw1ZtH AgmIT8ZhTvoScoY7FilpyNI2/dY/3j2ZZ7zdZTzLZh/4i5F7Y/uKsBk2Yt78JqjiwxxE my+inbWp7oBgy2UamTByHB52H+c+2K+3sPt58dnEiji6jNE05XF+/+f/J1SYIOwU/BqB vq5SRBXSVknCtwv+tgqAgKR12ain1hN2IqokC8L3ZqegeRD/wMOEPVk9GLr+Aocw1seE wiqgpxAOrOLrtaSQWOlm8ba8XeYCD0Nu478K6K5ndC1GSzQEChr0Zx4f+p4xhIe0PU3v +t+Q== X-Gm-Message-State: AOJu0Ywn9gxLExVSoHzX5if+kVKwYoUwR8ptVW7j594gLprqjw+GZros 2tViGA3bxszlH2cuf4F8wYG4+O8ayPxCzVeDPrn2Y4DXVO0JXJHBkJ1WjFFVOJie3b/5WwmR41m H X-Received: by 2002:a05:6000:1449:b0:358:4af8:b76e with SMTP id ffacd0b85a97d-3584af8b799mr5259166f8f.62.1716905277154; Tue, 28 May 2024 07:07:57 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.56 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:56 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 02/42] hvf: arm: Fix encodings for ID_AA64PFR1_EL1 and debug System registers Date: Tue, 28 May 2024 15:07:13 +0100 Message-Id: <20240528140753.3620597-3-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::429; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x429.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01, UPPERCASE_50_75=0.008 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Zenghui Yu We wrongly encoded ID_AA64PFR1_EL1 using {3,0,0,4,2} in hvf_sreg_match[] so we fail to get the expected ARMCPRegInfo from cp_regs hash table with the wrong key. Fix it with the correct encoding {3,0,0,4,1}. With that fixed, the Linux guest can properly detect FEAT_SSBS2 on my M1 HW. All DBG{B,W}{V,C}R_EL1 registers are also wrongly encoded with op0 == 14. It happens to work because HVF_SYSREG(CRn, CRm, 14, op1, op2) equals to HVF_SYSREG(CRn, CRm, 2, op1, op2), by definition. But we shouldn't rely on it. Cc: qemu-stable@nongnu.org Fixes: a1477da3ddeb ("hvf: Add Apple Silicon support") Signed-off-by: Zenghui Yu Reviewed-by: Alexander Graf Message-id: 20240503153453.54389-1-zenghui.yu@linux.dev Signed-off-by: Peter Maydell --- target/arm/hvf/hvf.c | 130 +++++++++++++++++++++---------------------- 1 file changed, 65 insertions(+), 65 deletions(-) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index 08d0757438c..45e2218be58 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -396,85 +396,85 @@ struct hvf_sreg_match { }; static struct hvf_sreg_match hvf_sreg_match[] = { - { HV_SYS_REG_DBGBVR0_EL1, HVF_SYSREG(0, 0, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR0_EL1, HVF_SYSREG(0, 0, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR0_EL1, HVF_SYSREG(0, 0, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR0_EL1, HVF_SYSREG(0, 0, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR0_EL1, HVF_SYSREG(0, 0, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR0_EL1, HVF_SYSREG(0, 0, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR0_EL1, HVF_SYSREG(0, 0, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR0_EL1, HVF_SYSREG(0, 0, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR1_EL1, HVF_SYSREG(0, 1, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR1_EL1, HVF_SYSREG(0, 1, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR1_EL1, HVF_SYSREG(0, 1, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR1_EL1, HVF_SYSREG(0, 1, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR1_EL1, HVF_SYSREG(0, 1, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR1_EL1, HVF_SYSREG(0, 1, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR1_EL1, HVF_SYSREG(0, 1, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR1_EL1, HVF_SYSREG(0, 1, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR2_EL1, HVF_SYSREG(0, 2, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR2_EL1, HVF_SYSREG(0, 2, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR2_EL1, HVF_SYSREG(0, 2, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR2_EL1, HVF_SYSREG(0, 2, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR2_EL1, HVF_SYSREG(0, 2, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR2_EL1, HVF_SYSREG(0, 2, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR2_EL1, HVF_SYSREG(0, 2, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR2_EL1, HVF_SYSREG(0, 2, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR3_EL1, HVF_SYSREG(0, 3, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR3_EL1, HVF_SYSREG(0, 3, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR3_EL1, HVF_SYSREG(0, 3, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR3_EL1, HVF_SYSREG(0, 3, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR3_EL1, HVF_SYSREG(0, 3, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR3_EL1, HVF_SYSREG(0, 3, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR3_EL1, HVF_SYSREG(0, 3, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR3_EL1, HVF_SYSREG(0, 3, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR4_EL1, HVF_SYSREG(0, 4, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR4_EL1, HVF_SYSREG(0, 4, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR4_EL1, HVF_SYSREG(0, 4, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR4_EL1, HVF_SYSREG(0, 4, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR4_EL1, HVF_SYSREG(0, 4, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR4_EL1, HVF_SYSREG(0, 4, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR4_EL1, HVF_SYSREG(0, 4, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR4_EL1, HVF_SYSREG(0, 4, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR5_EL1, HVF_SYSREG(0, 5, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR5_EL1, HVF_SYSREG(0, 5, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR5_EL1, HVF_SYSREG(0, 5, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR5_EL1, HVF_SYSREG(0, 5, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR5_EL1, HVF_SYSREG(0, 5, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR5_EL1, HVF_SYSREG(0, 5, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR5_EL1, HVF_SYSREG(0, 5, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR5_EL1, HVF_SYSREG(0, 5, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR6_EL1, HVF_SYSREG(0, 6, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR6_EL1, HVF_SYSREG(0, 6, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR6_EL1, HVF_SYSREG(0, 6, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR6_EL1, HVF_SYSREG(0, 6, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR6_EL1, HVF_SYSREG(0, 6, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR6_EL1, HVF_SYSREG(0, 6, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR6_EL1, HVF_SYSREG(0, 6, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR6_EL1, HVF_SYSREG(0, 6, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR7_EL1, HVF_SYSREG(0, 7, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR7_EL1, HVF_SYSREG(0, 7, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR7_EL1, HVF_SYSREG(0, 7, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR7_EL1, HVF_SYSREG(0, 7, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR7_EL1, HVF_SYSREG(0, 7, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR7_EL1, HVF_SYSREG(0, 7, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR7_EL1, HVF_SYSREG(0, 7, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR7_EL1, HVF_SYSREG(0, 7, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR8_EL1, HVF_SYSREG(0, 8, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR8_EL1, HVF_SYSREG(0, 8, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR8_EL1, HVF_SYSREG(0, 8, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR8_EL1, HVF_SYSREG(0, 8, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR8_EL1, HVF_SYSREG(0, 8, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR8_EL1, HVF_SYSREG(0, 8, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR8_EL1, HVF_SYSREG(0, 8, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR8_EL1, HVF_SYSREG(0, 8, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR9_EL1, HVF_SYSREG(0, 9, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR9_EL1, HVF_SYSREG(0, 9, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR9_EL1, HVF_SYSREG(0, 9, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR9_EL1, HVF_SYSREG(0, 9, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR9_EL1, HVF_SYSREG(0, 9, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR9_EL1, HVF_SYSREG(0, 9, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR9_EL1, HVF_SYSREG(0, 9, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR9_EL1, HVF_SYSREG(0, 9, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR10_EL1, HVF_SYSREG(0, 10, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR10_EL1, HVF_SYSREG(0, 10, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR10_EL1, HVF_SYSREG(0, 10, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR10_EL1, HVF_SYSREG(0, 10, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR10_EL1, HVF_SYSREG(0, 10, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR10_EL1, HVF_SYSREG(0, 10, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR10_EL1, HVF_SYSREG(0, 10, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR10_EL1, HVF_SYSREG(0, 10, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR11_EL1, HVF_SYSREG(0, 11, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR11_EL1, HVF_SYSREG(0, 11, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR11_EL1, HVF_SYSREG(0, 11, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR11_EL1, HVF_SYSREG(0, 11, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR11_EL1, HVF_SYSREG(0, 11, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR11_EL1, HVF_SYSREG(0, 11, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR11_EL1, HVF_SYSREG(0, 11, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR11_EL1, HVF_SYSREG(0, 11, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR12_EL1, HVF_SYSREG(0, 12, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR12_EL1, HVF_SYSREG(0, 12, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR12_EL1, HVF_SYSREG(0, 12, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR12_EL1, HVF_SYSREG(0, 12, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR12_EL1, HVF_SYSREG(0, 12, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR12_EL1, HVF_SYSREG(0, 12, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR12_EL1, HVF_SYSREG(0, 12, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR12_EL1, HVF_SYSREG(0, 12, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR13_EL1, HVF_SYSREG(0, 13, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR13_EL1, HVF_SYSREG(0, 13, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR13_EL1, HVF_SYSREG(0, 13, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR13_EL1, HVF_SYSREG(0, 13, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR13_EL1, HVF_SYSREG(0, 13, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR13_EL1, HVF_SYSREG(0, 13, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR13_EL1, HVF_SYSREG(0, 13, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR13_EL1, HVF_SYSREG(0, 13, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR14_EL1, HVF_SYSREG(0, 14, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR14_EL1, HVF_SYSREG(0, 14, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR14_EL1, HVF_SYSREG(0, 14, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR14_EL1, HVF_SYSREG(0, 14, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR14_EL1, HVF_SYSREG(0, 14, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR14_EL1, HVF_SYSREG(0, 14, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR14_EL1, HVF_SYSREG(0, 14, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR14_EL1, HVF_SYSREG(0, 14, 2, 0, 7) }, - { HV_SYS_REG_DBGBVR15_EL1, HVF_SYSREG(0, 15, 14, 0, 4) }, - { HV_SYS_REG_DBGBCR15_EL1, HVF_SYSREG(0, 15, 14, 0, 5) }, - { HV_SYS_REG_DBGWVR15_EL1, HVF_SYSREG(0, 15, 14, 0, 6) }, - { HV_SYS_REG_DBGWCR15_EL1, HVF_SYSREG(0, 15, 14, 0, 7) }, + { HV_SYS_REG_DBGBVR15_EL1, HVF_SYSREG(0, 15, 2, 0, 4) }, + { HV_SYS_REG_DBGBCR15_EL1, HVF_SYSREG(0, 15, 2, 0, 5) }, + { HV_SYS_REG_DBGWVR15_EL1, HVF_SYSREG(0, 15, 2, 0, 6) }, + { HV_SYS_REG_DBGWCR15_EL1, HVF_SYSREG(0, 15, 2, 0, 7) }, #ifdef SYNC_NO_RAW_REGS /* @@ -486,7 +486,7 @@ static struct hvf_sreg_match hvf_sreg_match[] = { { HV_SYS_REG_MPIDR_EL1, HVF_SYSREG(0, 0, 3, 0, 5) }, { HV_SYS_REG_ID_AA64PFR0_EL1, HVF_SYSREG(0, 4, 3, 0, 0) }, #endif - { HV_SYS_REG_ID_AA64PFR1_EL1, HVF_SYSREG(0, 4, 3, 0, 2) }, + { HV_SYS_REG_ID_AA64PFR1_EL1, HVF_SYSREG(0, 4, 3, 0, 1) }, { HV_SYS_REG_ID_AA64DFR0_EL1, HVF_SYSREG(0, 5, 3, 0, 0) }, { HV_SYS_REG_ID_AA64DFR1_EL1, HVF_SYSREG(0, 5, 3, 0, 1) }, { HV_SYS_REG_ID_AA64ISAR0_EL1, HVF_SYSREG(0, 6, 3, 0, 0) }, From patchwork Tue May 28 14:07:14 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799454 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp254636wrz; Tue, 28 May 2024 07:08:32 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXE6JwQu0abfo4wPNqY+l0z0SLdgIX4NdaGNw9C/yb3gWrRuRPeO/DAaW4XGghC0j8DzpE3LDFUVCiVKpT0F12o X-Google-Smtp-Source: AGHT+IHHwA5/yxsWGhSx4APM9nqoCcxS9HCGokeEjCJM8OL0m4kLsQT72VttYqvwGSk33CIF9L6S X-Received: by 2002:a05:6870:46ac:b0:24c:b4b0:8839 with SMTP id 586e51a60fabf-24cb4b0a789mr11902577fac.37.1716905312589; Tue, 28 May 2024 07:08:32 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905312; cv=none; d=google.com; s=arc-20160816; b=BZsYqpBuRAXjNZcyA3MNe+fVKEgRK3wLSlvzhH+4K5vELG3Rwu0RBGioVZmi25xPeI IEDHW+3QgqqgWgk3oi4jh34y2OJ5cAXzCKFBvuNgrK2msO4l3HVapfIValWoyOoNmFTX BTqhRyN6f34dLNrB2YM3NO4COSkB6FtojbzdPb08ORxfuIqOOmxZtQQ0PCGGaJCTiFFZ aN6JymtFS/6y4o6kCZ1+NbCJMujVfQMAy4nRDSuqk3EQzZ8zhAq4xP1VSmdYVKrQ/+CH Hhstu8PEZ/If4WSCyefJzxEpBamLvzcMv0bE771sBfHpwF1qOjP/WBs2/nIjzowvYLm4 Q6kg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=EAAlRYMlBTnMK71N/Zu05HtnM34HblCxoLd1v+E1rkk=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=yKam/GXJ/kAfJg8AGnzOiP2WF+4+anfW9KvyuHJKfnr3fAqrUsnUZrlCw/61vhbb/6 NOpOy9f8yruqsrW6gRwSBndZmT8F7eXy4lXQQLdld5k9AXGqPf9Z3bSWMF1F0Y4ue2Ar EJPR+A1JsCAY444/SvoCk6MnRr2sb/ZdlU4djz4aG+YohlvkwYjH2ye2+nK9bz2eiF0h gR9egr0qksvfulkrWso1pEye1Wwhx/hGHSqSOqtut218B1/X+FeApnnDZIhAX/OV3C5o XjnTj16Fhkkad98B8lgICfras3wJ1sQeMqX3Nr6oyDIqPaAgMOGRDT+OoazNpM5sA1bN 52bQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=EkGF+zQG; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id a1e0cc1a2514c-804cbeb75e3si1750419241.66.2024.05.28.07.08.32 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:08:32 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=EkGF+zQG; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUf-0001UM-Tk; Tue, 28 May 2024 10:08:01 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUf-0001Tn-3b for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:01 -0400 Received: from mail-wr1-x432.google.com ([2a00:1450:4864:20::432]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUd-00070M-45 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:00 -0400 Received: by mail-wr1-x432.google.com with SMTP id ffacd0b85a97d-354e0cc9c5cso756125f8f.0 for ; Tue, 28 May 2024 07:07:58 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905277; x=1717510077; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=EAAlRYMlBTnMK71N/Zu05HtnM34HblCxoLd1v+E1rkk=; b=EkGF+zQGRmrzicrr4ZUfs+Fx/hiQnBUEQd0IGzOdvK0Pf3VtPvBIFkaDpkKImKS9uX WJc0G2Keh/fRhvl9pemS1XVBQk9uuy4grRbm6dH3dd2FD2isJ3iVJteuloU+EyHq0Bvs yBM1KzTDJiTVbjtQUgOzfzGEJDyS+AADxqfQvj2b+C6VPgCSoORByEF940H6wafpgs0h ZdCeV5Cvmujlbt5Bqvt53Btm15NIPGaEdar/AblFNK8X2ObxMoJnnHRmKvw3DIQCQKlZ eM+NBMx21/m+XWudsMDFaTwzuUFPxuWLj+Hl9DVatAVKpc6av/A/0HRs7H1rWSQN/b2h zCAg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905277; x=1717510077; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=EAAlRYMlBTnMK71N/Zu05HtnM34HblCxoLd1v+E1rkk=; b=qNHijZaUhdHc8ljweMHDA7/i9/9G1ud2qdet/md9cT/o3W578VhwZ5BJnFYkaS2iEg 82l7Zr6fn4M/Mi+BxcPNybF6o6Rt/hGK49U00ZwB2wnopB7B0zRjHGFdCXZqGixUhxkx TwjpkZL9mSircbUpasT5sfr1YHZKx7CxtRvT6ZEj3SmH5lUcu0r0w8jbktqsBrorTg4w rdbCdm+NsYnBfec/5A+JMMmJ3JJzV8wsnqpAbn8OuEcVYPIqapxpe1WOU0LuQAzp1zG6 7omDWK5o4qkVPYvllNPEXYUiqc3q6NHMlFgNyW7h87U7ykWVxQcgIfN8KpeeZMS88ra/ j6BQ== X-Gm-Message-State: AOJu0YwFuqQTYECDYLJwwiaAegsSIklyYKouEcRGtx8PvgA1t2p8I6c5 c+g9LM4WPNgdmoZ5VqOteSSgj3RWayHLaBg6QdEh4I2+qIv5TemW0rDBXO1FI+qZnqyJiK5QcAx q X-Received: by 2002:a05:6000:1541:b0:359:733c:c8d6 with SMTP id ffacd0b85a97d-359733cc9fbmr4982633f8f.67.1716905277685; Tue, 28 May 2024 07:07:57 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.57 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:57 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 03/42] hw/arm/npcm7xx: remove setting of mp-affinity Date: Tue, 28 May 2024 15:07:14 +0100 Message-Id: <20240528140753.3620597-4-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::432; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x432.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Dorjoy Chowdhury The value of the mp-affinity property being set in npcm7xx_realize is always the same as the default value it would have when arm_cpu_realizefn is called if the property is not set here. So there is no need to set the property value in npcm7xx_realize function. Signed-off-by: Dorjoy Chowdhury Reviewed-by: Richard Henderson Reviewed-by: Philippe Mathieu-Daudé Message-id: 20240504141733.14813-1-dorjoychy111@gmail.com Signed-off-by: Peter Maydell --- hw/arm/npcm7xx.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index 9f2d96c733a..cb7791301b4 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -487,9 +487,6 @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) /* CPUs */ for (i = 0; i < nc->num_cpus; i++) { - object_property_set_int(OBJECT(&s->cpu[i]), "mp-affinity", - arm_build_mp_affinity(i, NPCM7XX_MAX_NUM_CPUS), - &error_abort); object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar", NPCM7XX_GIC_CPU_IF_ADDR, &error_abort); object_property_set_bool(OBJECT(&s->cpu[i]), "reset-hivecs", true, From patchwork Tue May 28 14:07:15 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799477 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257082wrz; Tue, 28 May 2024 07:12:31 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWtxApchDc9WEJ8KhOcIjnHeHNV2AlVFSic7zaHsuBY2Lhgb32yZtjQFsb6nho37QxVbDgk9U4Bt/TjjZ3Ibw8f X-Google-Smtp-Source: AGHT+IHa/kgAYVEXnnM07ZfaXw5eqOrGai8EIdonPfRZJmai3FQDIhpr4GOBACUkBojKdRT9Zp4A X-Received: by 2002:a54:4884:0:b0:3c9:93f1:c7b0 with SMTP id 5614622812f47-3d1a5b3ce8fmr11578394b6e.20.1716905550946; Tue, 28 May 2024 07:12:30 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905550; cv=none; d=google.com; s=arc-20160816; b=uIWPeMgOZ0gA4cA9yOPl0xvjTVuLV3g73BcNxP6HHdTc6hWFTuMtK7fGGDKZgLSUhO Kl+FKKW/iEqUoGeK98BpMmH0Gc4qZi9yshGdCY/c7TrrLYWjaT1Bb74cEm1eIyJkpVQS 4nEULfpkwg80shjZAHE5Ejh9s5v7HA0LPlg5JHjrpHg3C79ju1x3S1JEr550tjKVbgKi rBV1+AC6gETaUWEKrdCaaYWIfTS9KcOBCjwEHKczjYHIdkDtPTbcykobngLbgLTF31b5 f4sF5MkfTv5R8ErnVU89oxRX2MUggiPKK9mPX8XlOhauceE55Cige+852n8qEG30He1U yDpw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=js5qncWkemZbFOUTBcvGMDqOGolfrcRJMq2DK5PGxrw=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=w+rMPMdcmeIXQMTyzyAB46UbgKvC/F8ru9kjwTKJsnEjz7Mm1LNeh9K7RLp1sQjahr CnEnqafquCG6qHGun4FWKEl+k8jTGH8vl7YpjhFxZ+POUBQ/I7uMwH5mI4NH/VaOo5pV vRKJuYL4tPOFyxpHwxg74zRUj17Ey1MjqL4LcLx0PXCgCFMwokg05fKxfbmEV9jJVeU/ QGu6Oz0t6HonHXD/QNsOkqT0qBa25/aIEn/0bi4cd8/Ft7Mam6RupN7KjVCAM1BDyjfS 5gWRoMm1rw2xwzMvXOfncUw1zFfxRilLAANXb1Px5RhSruswHHeAqj7SMnUpSQTkKnq1 l4LQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="sXX4gy/2"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48b8b8cdf0bsi713148137.752.2024.05.28.07.12.30 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:30 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="sXX4gy/2"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUg-0001Uv-Il; Tue, 28 May 2024 10:08:02 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUf-0001Tq-7R for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:01 -0400 Received: from mail-wr1-x430.google.com ([2a00:1450:4864:20::430]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUd-00070S-Ha for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:00 -0400 Received: by mail-wr1-x430.google.com with SMTP id ffacd0b85a97d-35bf77ba951so210008f8f.3 for ; Tue, 28 May 2024 07:07:59 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905278; x=1717510078; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=js5qncWkemZbFOUTBcvGMDqOGolfrcRJMq2DK5PGxrw=; b=sXX4gy/28aC7T3VCBj8KFmLrXZinqkKJTsHpRbPtz7R+FJ229SZNdptGVtYfW++yV8 92Zco127RY4BcdqBiMVrO067VXrGHdTBIqlRmqBqE0lM2QKIvqBGG5U+U77fHWqsHDYp MO0ai/5GKw36e+kxA4kf5L6Kguf54BOEzJzEd3Pkdfap6dz2tIaOFmkZi/I5S0OCAqV/ aKtyIfG67Z5dacmapW+m9Uhwn4EVFQ5mm3di8o6kTQqxbUDmyfgzFkSKJ18UjvdgcKIe vg2VxFFPudGws5/+d98wjPC+3Dfohvozidlm0DEdB5sCLF8gJIFIFp01Ii6/RLj+kGW4 WKEw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905278; x=1717510078; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=js5qncWkemZbFOUTBcvGMDqOGolfrcRJMq2DK5PGxrw=; b=dSxJMO0QZ2tHN7C6AyXFAvAFbEqA1zfcrPH0lHvhasAIRzHtIRBSFNgo6LdZXIUbdN GLu0vGbNJvJZZIWGdFj2M7U6z5a0A5fFhuxfpk2+Doaa6v/EXukxTI0oHF1rvHVgFaYb qIEEhBI9rF3W1FDrYQC5GhDCQs9oie9TOhMk+XvvI4bDaeE2X2/fvGBQ5x7k+aPQRDkF 9Wmu5z7bdNaRL44OE33UYbaoL4+LJpiKln0Iz2Ov1SJ4M70+F1APo0YgUO9oURh4qdiP mnczmCHXOP+d5VKyFSrG+bSlMdBLNADH81R0TMycjhArnCdy/1Pi2N7sg+CN+OM4SbJO 3EdA== X-Gm-Message-State: AOJu0YyMYAEI9xs287x5KaHAZoNlUFvqDrQhL3Z3+Q6QVoC167foZnLQ dywPVQKnOxL5+YP28mAUqz/ZkO8IbGyGJxu8Wgz3hUv2uvsVy9n/RN4Nu4yNh2o9UwDmsxpKA/g u X-Received: by 2002:a5d:4988:0:b0:354:f489:fb8 with SMTP id ffacd0b85a97d-35526c3e2admr8015667f8f.14.1716905278262; Tue, 28 May 2024 07:07:58 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.57 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:57 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 04/42] hw/char: Correct STM32L4x5 usart register CR2 field ADD_0 size Date: Tue, 28 May 2024 15:07:15 +0100 Message-Id: <20240528140753.3620597-5-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::430; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x430.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Inès Varhol Signed-off-by: Arnaud Minier Signed-off-by: Inès Varhol Message-id: 20240505141613.387508-1-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/char/stm32l4x5_usart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c index 02f666308c0..fc5dcac0c45 100644 --- a/hw/char/stm32l4x5_usart.c +++ b/hw/char/stm32l4x5_usart.c @@ -56,7 +56,7 @@ REG32(CR1, 0x00) FIELD(CR1, UE, 0, 1) /* USART enable */ REG32(CR2, 0x04) FIELD(CR2, ADD_1, 28, 4) /* ADD[7:4] */ - FIELD(CR2, ADD_0, 24, 1) /* ADD[3:0] */ + FIELD(CR2, ADD_0, 24, 4) /* ADD[3:0] */ FIELD(CR2, RTOEN, 23, 1) /* Receiver timeout enable */ FIELD(CR2, ABRMOD, 21, 2) /* Auto baud rate mode */ FIELD(CR2, ABREN, 20, 1) /* Auto baud rate enable */ From patchwork Tue May 28 14:07:16 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799483 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257241wrz; Tue, 28 May 2024 07:12:47 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX7VzbHAtDaOndMEGXC7+HR3WqNx0ye7o908vMnk62AVYKD9S8GfdOVqX5mytRoF5OdWhvetSLKkF4MdMgyTSD8 X-Google-Smtp-Source: AGHT+IHXyYRCL6QirakpizBPuMq0u0uCgBBp5AqJm3wsleeY57BXFGdwzKRX8h4CzW2BIdaa79o4 X-Received: by 2002:a05:6122:2512:b0:4e4:e9dc:5dc5 with SMTP id 71dfb90a1353d-4e4f0120562mr13234005e0c.0.1716905566979; Tue, 28 May 2024 07:12:46 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905566; cv=none; d=google.com; s=arc-20160816; b=C0vwW3ZBCQs/RmZ3+MC+X8JS/1lFfk9w0qG82aW5aeiNTCnGMdVhBFn7CW7ftqPMyf 08vgL5rxUKi7xP9FTs1RgxQNKRmEQQwELXElckoVYnMgesmo2fLflU5GqDAGkXIf69F2 O54ePsNWyBKHxsAeotyBVJyGlzGL91oSAd/ndmuNOWNASnHg5Dam111wmRrNllmZoeH6 0//reEyAQigbJfDtcv4C7xdZbg9lCQ9AGrcoYi6SnE/LLu30IyA9aqs4M7kvcNU/DEJr wKDzcCeIWhsovAn4oCRM9R6sN04Uz6EV5VtCTRCitrhNPKzbKau2HTP2fFryP+TUtIFx cCNQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=cix61aPqu8KvNLcJRTXQi8LmaQzXhkWR11FG/+cNvi0=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=KcGEHAblaR3aHfDPJiFkMw24bIjWaBqUTm4PlIlVe/ro0o1ldSOegbAhQnqj2vJmRm pe2eB39iLpjrZOhX76VQhuAZ9Q0F+9dCFcnoFONegTMM/V7D4wT74XK+ZhthiegeMeOQ pWDofxC8keFYs4/auoQU3uZD0mZzNCdN0U5l0zCTEzJ/1jcSDr7hzqoEgB3TmaKgwoCu rHMbYJKZ888WwAqD4fS8DCbXdt5XlA5FfKzCAcZ6967my7OGyX5DFlQ44Z33zJD4O+hL k8Bc2neIdtVjwoIXZooXJfMynrTNT8CgaIM+O683fxT9mRdgPzgdgBcfLAClIBJlnnxB sdbg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=LMDnWw8J; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a44fbe5si1580708137.813.2024.05.28.07.12.46 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:46 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=LMDnWw8J; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUi-0001W9-Dj; Tue, 28 May 2024 10:08:04 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUg-0001Um-FK for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:02 -0400 Received: from mail-wr1-x435.google.com ([2a00:1450:4864:20::435]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUe-00070Z-Cc for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:02 -0400 Received: by mail-wr1-x435.google.com with SMTP id ffacd0b85a97d-357d533b744so813748f8f.2 for ; Tue, 28 May 2024 07:08:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905279; x=1717510079; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=cix61aPqu8KvNLcJRTXQi8LmaQzXhkWR11FG/+cNvi0=; b=LMDnWw8JnxOoRF2pqsijhJnw717kJke9xP83Z1Vn0AE2pVdNuZ+/tn5/+6PxfTvPMY LTxIf1LGWjBUgYUXwNpCe2THaG9Ewxco3sDLhv0TqAGvoVFRMSYtchV2rbd29+o1LEFf 9ynpQharuWnIa9qXHOFvF+bZdPDWoZ5sTPQ2N8OrdMFhW9O6CNl0xhBtDGYaNXzo4zOc ur43O1Z05eEbad2zank4QbUn3/pxBpfgeXc9VWQOENwovp+AxiqqBwjY6giW5JbL4tXW mLNkI82AjA5ps1b6gKrcKhCQOB/3mrcyxCJWdU3Wvhwk+ey/a5gsoJNnlrRiBjCuQ4+P dD4g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905279; x=1717510079; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=cix61aPqu8KvNLcJRTXQi8LmaQzXhkWR11FG/+cNvi0=; b=jdBh8wZ2blerELxIdwqdpNQ8MW4WqOpSFDgyFh1Z1y+BRAY1C3VRuOXCjIasr2XY5X gGi7TZX1Bf4aZ44PIwlcwXzuZg3BwUQrZgeJU/IgvbercOFlzyDKxj0+hdFdkxXgo32D DcwacZBIzhSmur62liCOKTOHE7zgt8htu5Db9f172V0q9EndibOPO5Nrwr48xB+xoVNR mVtA9Axn+dAL7P7mMOlJMxLIJWcr+9I29Yz2YKfRmojOBMAuqTPKp7PSQvfIc3qSm8wP 3Rly5dsd/T/6hdPmoNoeWMZ8kjmugXyfwhRIVYemBItcQu7HjMtOi7NbD3oqXUuwDgJ4 Kq6w== X-Gm-Message-State: AOJu0Yww/UQImn+m955+cl3cm/Z6mogwL15cWJI8W3tVRzrV+/1twEcF S4/RhAFgmh9cFfB7FLxrCNjO1LzuylHxQ222AWb20VB3X103BK/3ukgtqhJhTLyOF/tr+Qev7iL y X-Received: by 2002:a5d:6911:0:b0:354:fb2a:7daf with SMTP id ffacd0b85a97d-3552fdef9cbmr9002016f8f.57.1716905279101; Tue, 28 May 2024 07:07:59 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.58 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:58 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 05/42] hw/intc/arm_gic: Fix handling of NS view of GICC_APR Date: Tue, 28 May 2024 15:07:16 +0100 Message-Id: <20240528140753.3620597-6-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::435; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x435.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Andrey Shumilin In gic_cpu_read() and gic_cpu_write(), we delegate the handling of reading and writing the Non-Secure view of the GICC_APR registers to functions gic_apr_ns_view() and gic_apr_write_ns_view(). Unfortunately we got the order of the arguments wrong, swapping the CPU number and the register number (which the compiler doesn't catch because they're both integers). Most guests probably didn't notice this bug because directly accessing the APR registers is typically something only done by firmware when it is doing state save for going into a sleep mode. Correct the mismatched call arguments. Found by Linux Verification Center (linuxtesting.org) with SVACE. Cc: qemu-stable@nongnu.org Fixes: 51fd06e0ee ("hw/intc/arm_gic: Fix handling of GICC_APR, GICC_NSAPR registers") Signed-off-by: Andrey Shumilin [PMM: Rewrote commit message] Signed-off-by: Peter Maydell Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Alex Bennée --- hw/intc/arm_gic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c index 074cf50af25..e4b8437f8b8 100644 --- a/hw/intc/arm_gic.c +++ b/hw/intc/arm_gic.c @@ -1658,7 +1658,7 @@ static MemTxResult gic_cpu_read(GICState *s, int cpu, int offset, *data = s->h_apr[gic_get_vcpu_real_id(cpu)]; } else if (gic_cpu_ns_access(s, cpu, attrs)) { /* NS view of GICC_APR is the top half of GIC_NSAPR */ - *data = gic_apr_ns_view(s, regno, cpu); + *data = gic_apr_ns_view(s, cpu, regno); } else { *data = s->apr[regno][cpu]; } @@ -1746,7 +1746,7 @@ static MemTxResult gic_cpu_write(GICState *s, int cpu, int offset, s->h_apr[gic_get_vcpu_real_id(cpu)] = value; } else if (gic_cpu_ns_access(s, cpu, attrs)) { /* NS view of GICC_APR is the top half of GIC_NSAPR */ - gic_apr_write_ns_view(s, regno, cpu, value); + gic_apr_write_ns_view(s, cpu, regno, value); } else { s->apr[regno][cpu] = value; } From patchwork Tue May 28 14:07:17 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799476 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257049wrz; Tue, 28 May 2024 07:12:28 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXfNT3jrTdBhYFnioR3gtyM5ZQ9stW3TCbpN6r202In4UZaZZ+e6PqY+mPO2ooBOn+GcLyinosBknsaLJDV1fR7 X-Google-Smtp-Source: AGHT+IE+83U/nxXCUjm18SSGYCQV4wAaIGhJnDsY+p5Gjmi3LpzbrG1Z2ewSZtlgI/zf9//1gM6+ X-Received: by 2002:a05:620a:1654:b0:792:b921:5a55 with SMTP id af79cd13be357-794ab0822demr1215364185a.26.1716905548412; Tue, 28 May 2024 07:12:28 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905548; cv=none; d=google.com; s=arc-20160816; b=QLmozcLR5P7v1TYN3Gnb2n8dxcMttD0hHqEQLq1NB2JFXbvYh3njm1l/ZQfY2CLHr/ 1mG+JeBK21QOStVhHhYxTGxqH4udF0biG/3fro6xE9OgqGl6JpTsXAcO5hf+ytiPzu3C RhQWtZYA3+ak+6Z4D006zirwNjTKnvVA8ZPJ1ppobm7evSYbkW00VYDmmJdlmjE0vGGk xCuX8NjpTFskkNwDvDcqREZrwaE7MGAu/4+ftkQnAj7p2e6eYfk/pg+NsBkPBfLpeD5b nz0MNnnMwMyOBDYJ0K4fV7OJLjc3xSn55X1W/SU4MZ+QezUczKJNVlyc5Rap/DDWqcOB bhvQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=Z8e50owdFjq3l9wuKAY7n7wmjEPbhSYGUt29AzUeGso=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=NT01NHIRL9bKnj3l+JGHYCrZbp2FfmjI5vxeqo92nQ/UVLz8WGfW+aRKsTSiofMogP 01bY567xYS0juxNtIWqDnpbpQ62fRCXbhQWzU70a5Dio2CjAtSQ5hKrWFhU6m48bKZUf lxMMqqlOrotksEX61YygxtPOcW0nGKbg898WtZva/+qHeBxL44D36M/VLs2krDGxluum CpAJ00SqHe8ytmQmt1Tlu7+AumaIUKiloXUT+8DwWV0hy7srAb6zx8KlXw+5k0rk/BGV u1YLB4KWSsqXQJ6OJYzE7noN0UqCA6PlDlPjdmcdJpH6J5uIs2R0NY6PQ3cOd1PbCHsL Rx6g==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=SDr0s0Qn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fbf8056cfsi83173631cf.45.2024.05.28.07.12.28 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:28 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=SDr0s0Qn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUi-0001Vq-3K; Tue, 28 May 2024 10:08:04 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUg-0001Uk-F4 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:02 -0400 Received: from mail-wr1-x432.google.com ([2a00:1450:4864:20::432]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUe-000727-Tu for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:02 -0400 Received: by mail-wr1-x432.google.com with SMTP id ffacd0b85a97d-354f8a0cd08so769589f8f.2 for ; Tue, 28 May 2024 07:08:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905279; x=1717510079; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=Z8e50owdFjq3l9wuKAY7n7wmjEPbhSYGUt29AzUeGso=; b=SDr0s0QnY0bSwnJNzkvQlmeDvmanbs4nXXCX3Li2TTWoQyZgkPfnDf3Usituz52rHt ZTi5ooziShMQ1DLUmBLDIIpPqlYyV7Vx+Oqeb5dcZYe6+sefO+62uoj+RHedGCR6978+ 9dElUfQ7cIomDMw0mATMHrRWyLj6Efpp/YLSm1Jp5JlEJcu1OWH/gpNgqR4ZhW8cu21i mVWGMDLb4pLwfyUrBTRRciuFsAyP+n+x720jThuNNR3OC8/2wE+jKMRMyFlafWkfc2dd 5t45/G5H0PNpgRl5j07eUlCPnYlHNQiZ2ScO+3NrmzPA4pAa4DHGHc+V9GPl/hdE0pzc 0GoQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905279; x=1717510079; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Z8e50owdFjq3l9wuKAY7n7wmjEPbhSYGUt29AzUeGso=; b=gCLgz++kgQDwvBcXZBOOJEN7dZiBZQ8mROb04Rvy1tbZgdvR2Dqtzrn6fZ6avDhTph dST9xagznzC2BC9ypFb9BLFVl3c/5MGpic5kvB6WfaxfMSNjG5YhZtwFHvQrfaL2ufwQ jFbNzZ/noM+vPZ5zBA4jhZwBodeudNMDQ3CDEjZaVgWU4NIgfIswaKg1pdv3NtveJxqU iZKa1H9WedRYTn6zM8runeB/n2c19HPAA9Y8KOHfNluozpJe5t0jak9q5nK85I3hLGil frksF475v8VhY0UVPOsWsKzQML0NNTrrQfTrNVXuapoYsoAnylaJ9TKt9i8ztQPbtsIR lHcA== X-Gm-Message-State: AOJu0YzcvDXWPPvfh48ej6ewR+33Mih/ZNxgTp1JHvcVsZEnQcmwKv3K hC9KB8ZLLEp7mugHUv/oeJ8ctxb5BkPB0NLr4ZxfTt13k+b5z91m4qWgTQ0hU0FkJwUrjWgm2/2 N X-Received: by 2002:a5d:598b:0:b0:356:4bb7:b205 with SMTP id ffacd0b85a97d-3564bb7b370mr10008772f8f.1.1716905279499; Tue, 28 May 2024 07:07:59 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.59 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:59 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 06/42] hw/input/tsc2005: Fix -Wchar-subscripts warning in tsc2005_txrx() Date: Tue, 28 May 2024 15:07:17 +0100 Message-Id: <20240528140753.3620597-7-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::432; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x432.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Philippe Mathieu-Daudé Check the function index is in range and use an unsigned variable to avoid the following warning with GCC 13.2.0: [666/5358] Compiling C object libcommon.fa.p/hw_input_tsc2005.c.o hw/input/tsc2005.c: In function 'tsc2005_timer_tick': hw/input/tsc2005.c:416:26: warning: array subscript has type 'char' [-Wchar-subscripts] 416 | s->dav |= mode_regs[s->function]; | ~^~~~~~~~~~ Signed-off-by: Philippe Mathieu-Daudé Message-id: 20240508143513.44996-1-philmd@linaro.org Reviewed-by: Peter Maydell [PMM: fixed missing ')'] Signed-off-by: Peter Maydell --- hw/input/tsc2005.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/input/tsc2005.c b/hw/input/tsc2005.c index 941f163d364..ac7f54eeafb 100644 --- a/hw/input/tsc2005.c +++ b/hw/input/tsc2005.c @@ -406,6 +406,9 @@ uint32_t tsc2005_txrx(void *opaque, uint32_t value, int len) static void tsc2005_timer_tick(void *opaque) { TSC2005State *s = opaque; + unsigned int function = s->function; + + assert(function < ARRAY_SIZE(mode_regs)); /* Timer ticked -- a set of conversions has been finished. */ @@ -413,7 +416,7 @@ static void tsc2005_timer_tick(void *opaque) return; s->busy = false; - s->dav |= mode_regs[s->function]; + s->dav |= mode_regs[function]; s->function = -1; tsc2005_pin_update(s); } From patchwork Tue May 28 14:07:18 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799455 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp254702wrz; Tue, 28 May 2024 07:08:40 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWAsQjJKiGKiBIcPvFYcbugg1z54x+KRsUMDTYEiTzitYT7XETDec82xbe2tH6TmJruN+4Nikr/2xRKMgbdLRul X-Google-Smtp-Source: AGHT+IF3oigFK60ViYZWmuHV63xDQBHZRh1Gcdu2qFf+rVz8TZbJxe9PrTtbEy78xl0w9m5V+x7v X-Received: by 2002:a05:6359:2e82:b0:183:f7cb:af75 with SMTP id e5c5f4694b2df-197e566bd09mr1082555855d.32.1716905319702; Tue, 28 May 2024 07:08:39 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905319; cv=none; d=google.com; s=arc-20160816; b=lH5m1II2NwrtGHRFsNylDjkwXkZH0oEN6qaFkEFQPNM0o+hodu3kbFXdjiGYM3yA7v lFKnwg2KCJja2KlAr+IzoWIolt4K7T1EPHUyKRU4C3S5CtwrWw8XgxR86DiOZ3vLSpNN 74a1T7uT2uGl5PDuMFMu+Rq9RSJj07ewFxhH06WEODnylxlS/F54EG6933VOMsdBlQWx T0FjztnIeiKEG6N+zhKEFUcXou41kMqd191kYql3+Kav+VGBoqhzbN7cWEIhRxJWjZk5 KTU33KEAtMgNXCYQkdU0FLTWINwww2yWhTm1y27zby+b2h0ka7305vj0/68U7sZo6ely nY/g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=LrmhrKaXF0DEYxLjGzXZ63cc61xp2WM9kMJXk0bodfg=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=nXnjsEy0BqxsGRMFNqQHt1m7qfUJ0VvQ9xnLbiIqSrMSWW/P89Mxie7KXcUkL8ri1J qY6gIoRurETC++4GurTf0VRo0ldn8z+qEiRCCJgUYWZafTLSKQQ0TdyThdwY1MbO282i 52DDvUT9eLMRgrKgR6HyP9/vBcU7L2Y3KBd9ngKGx+dF1Ue10NnuTr2/tIIjgd6ioAr5 NjNHob1keU6+isG5AWAl58Bz3e2baK6yC9IcwZ1k4l5+8N1AnOmrUCobrHjqdHg+iI/s 6apCm0VWenG5XZqkRLzrCaLPV/qFbA3MYf2YVbEgNk/NaB/dm0iG9mmv42HTglQgdwGa PyrQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=YWszOw9a; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id af79cd13be357-794abd170bbsi999859185a.236.2024.05.28.07.08.39 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:08:39 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=YWszOw9a; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUj-0001X3-Oc; Tue, 28 May 2024 10:08:05 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUi-0001WJ-Hb for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:04 -0400 Received: from mail-wr1-x433.google.com ([2a00:1450:4864:20::433]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUf-00072B-Jk for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:04 -0400 Received: by mail-wr1-x433.google.com with SMTP id ffacd0b85a97d-354f8a0cd08so769602f8f.2 for ; Tue, 28 May 2024 07:08:01 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905280; x=1717510080; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=LrmhrKaXF0DEYxLjGzXZ63cc61xp2WM9kMJXk0bodfg=; b=YWszOw9aFmfte7SAqYuqpVQChYDVJFF/mh3L8dlE1R3+gQmQZ1mJ4K7h2fjdVX7pAb TI/KqDylk7DsE53ERVaL3stg1lJDRSj0fsb2ylZtcRo6PVNjzN7gwajUQxOg2yhne17k 0Kue2fhUP10vbhNC8gOXL1VbZfDsb3sNylg38gc6UE6NwZSPWze39haBN4EPtRX1fMas qni2vBntF/6+SWhVxIxte98FUxpz/86KeNuykwNjCcc4EWgYpvMjAjRQ6zxcRzeai6f8 mRk2vg1tHuEbb32fooKdEaXEfWMshU5jQp2sPAGpJbBtoKk9B9V+XB42mZjVJNNJs5nR ZfUg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905280; x=1717510080; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=LrmhrKaXF0DEYxLjGzXZ63cc61xp2WM9kMJXk0bodfg=; b=rsFgM6STJ6lDByjDZTQVBi7iDA4JDlnrtt+W4Uz2RWYWRSYmGRAb7gV12D5V8GwG6W f62J3RA7mIirC693yXvv918TKmfbN4OUEs6+l9Ecdis6DEhwIvnNG/xNywSUi4kQWC82 nywP/f5fJ1FH64UVqabzktqbrbTSQ8z5CdJ0Tdji98NvMOqqLuyuE9eCZ+dOWLzwWJNN 6kITQDRWqg9lefCYPB0D+QaTe6uPu536iIR1USWDVnxAXc1w73T6H8fNP5cGf7sPpVaM lYfP0rVETuwRjZhSiDoV0j2kFOmwq1VQRpLCxKpRonVlQF9cCKExc7Wc/U8EI5ijbqqp rdzA== X-Gm-Message-State: AOJu0YxbwzK6zlyXjtIGW6U8fgQ4SpUHIAKdvE3QnAACkah0Y6uwcIuX J5QhL25pmdlIxMnnaK4xTeDtfk7Yuhhyi87H7kbwWU4OXyx05crlAgxBm46BMznV1ewlCWpb5c1 N X-Received: by 2002:a05:6000:7:b0:355:49a:3721 with SMTP id ffacd0b85a97d-3552216657cmr8501757f8f.3.1716905279986; Tue, 28 May 2024 07:07:59 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.07.59 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:07:59 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 07/42] hw: arm: Remove use of tabs in some source files Date: Tue, 28 May 2024 15:07:18 +0100 Message-Id: <20240528140753.3620597-8-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::433; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x433.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Tanmay Patil Some of the source files for older devices use hardcoded tabs instead of our current coding standard's required spaces. Fix these in the following files: - hw/arm/boot.c - hw/char/omap_uart.c - hw/gpio/zaurus.c - hw/input/tsc2005.c This commit is mostly whitespace-only changes; it also adds curly-braces to some 'if' statements. This addresses part of https://gitlab.com/qemu-project/qemu/-/issues/373 but some other files remain to be handled. Signed-off-by: Tanmay Patil Message-id: 20240508081502.88375-1-tanmaynpatil105@gmail.com Reviewed-by: Peter Maydell [PMM: tweaked commit message] Signed-off-by: Peter Maydell --- hw/arm/boot.c | 8 +-- hw/char/omap_uart.c | 49 +++++++++-------- hw/gpio/zaurus.c | 59 ++++++++++---------- hw/input/tsc2005.c | 130 ++++++++++++++++++++++++-------------------- 4 files changed, 130 insertions(+), 116 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index 84ea6a807a4..d480a7da02c 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -347,13 +347,13 @@ static void set_kernel_args_old(const struct arm_boot_info *info, WRITE_WORD(p, info->ram_size / 4096); /* ramdisk_size */ WRITE_WORD(p, 0); -#define FLAG_READONLY 1 -#define FLAG_RDLOAD 4 -#define FLAG_RDPROMPT 8 +#define FLAG_READONLY 1 +#define FLAG_RDLOAD 4 +#define FLAG_RDPROMPT 8 /* flags */ WRITE_WORD(p, FLAG_READONLY | FLAG_RDLOAD | FLAG_RDPROMPT); /* rootdev */ - WRITE_WORD(p, (31 << 8) | 0); /* /dev/mtdblock0 */ + WRITE_WORD(p, (31 << 8) | 0); /* /dev/mtdblock0 */ /* video_num_cols */ WRITE_WORD(p, 0); /* video_num_rows */ diff --git a/hw/char/omap_uart.c b/hw/char/omap_uart.c index 6848bddb4e2..c2ef4c137e1 100644 --- a/hw/char/omap_uart.c +++ b/hw/char/omap_uart.c @@ -61,7 +61,7 @@ struct omap_uart_s *omap_uart_init(hwaddr base, s->fclk = fclk; s->irq = irq; s->serial = serial_mm_init(get_system_memory(), base, 2, irq, - omap_clk_getrate(fclk)/16, + omap_clk_getrate(fclk) / 16, chr ?: qemu_chr_new(label, "null", NULL), DEVICE_NATIVE_ENDIAN); return s; @@ -76,27 +76,27 @@ static uint64_t omap_uart_read(void *opaque, hwaddr addr, unsigned size) } switch (addr) { - case 0x20: /* MDR1 */ + case 0x20: /* MDR1 */ return s->mdr[0]; - case 0x24: /* MDR2 */ + case 0x24: /* MDR2 */ return s->mdr[1]; - case 0x40: /* SCR */ + case 0x40: /* SCR */ return s->scr; - case 0x44: /* SSR */ + case 0x44: /* SSR */ return 0x0; - case 0x48: /* EBLR (OMAP2) */ + case 0x48: /* EBLR (OMAP2) */ return s->eblr; - case 0x4C: /* OSC_12M_SEL (OMAP1) */ + case 0x4C: /* OSC_12M_SEL (OMAP1) */ return s->clksel; - case 0x50: /* MVR */ + case 0x50: /* MVR */ return 0x30; - case 0x54: /* SYSC (OMAP2) */ + case 0x54: /* SYSC (OMAP2) */ return s->syscontrol; - case 0x58: /* SYSS (OMAP2) */ + case 0x58: /* SYSS (OMAP2) */ return 1; - case 0x5c: /* WER (OMAP2) */ + case 0x5c: /* WER (OMAP2) */ return s->wkup; - case 0x60: /* CFPS (OMAP2) */ + case 0x60: /* CFPS (OMAP2) */ return s->cfps; } @@ -115,35 +115,36 @@ static void omap_uart_write(void *opaque, hwaddr addr, } switch (addr) { - case 0x20: /* MDR1 */ + case 0x20: /* MDR1 */ s->mdr[0] = value & 0x7f; break; - case 0x24: /* MDR2 */ + case 0x24: /* MDR2 */ s->mdr[1] = value & 0xff; break; - case 0x40: /* SCR */ + case 0x40: /* SCR */ s->scr = value & 0xff; break; - case 0x48: /* EBLR (OMAP2) */ + case 0x48: /* EBLR (OMAP2) */ s->eblr = value & 0xff; break; - case 0x4C: /* OSC_12M_SEL (OMAP1) */ + case 0x4C: /* OSC_12M_SEL (OMAP1) */ s->clksel = value & 1; break; - case 0x44: /* SSR */ - case 0x50: /* MVR */ - case 0x58: /* SYSS (OMAP2) */ + case 0x44: /* SSR */ + case 0x50: /* MVR */ + case 0x58: /* SYSS (OMAP2) */ OMAP_RO_REG(addr); break; - case 0x54: /* SYSC (OMAP2) */ + case 0x54: /* SYSC (OMAP2) */ s->syscontrol = value & 0x1d; - if (value & 2) + if (value & 2) { omap_uart_reset(s); + } break; - case 0x5c: /* WER (OMAP2) */ + case 0x5c: /* WER (OMAP2) */ s->wkup = value & 0x7f; break; - case 0x60: /* CFPS (OMAP2) */ + case 0x60: /* CFPS (OMAP2) */ s->cfps = value & 0xff; break; default: diff --git a/hw/gpio/zaurus.c b/hw/gpio/zaurus.c index 5884804c589..7342440b958 100644 --- a/hw/gpio/zaurus.c +++ b/hw/gpio/zaurus.c @@ -49,19 +49,20 @@ struct ScoopInfo { uint16_t isr; }; -#define SCOOP_MCR 0x00 -#define SCOOP_CDR 0x04 -#define SCOOP_CSR 0x08 -#define SCOOP_CPR 0x0c -#define SCOOP_CCR 0x10 -#define SCOOP_IRR_IRM 0x14 -#define SCOOP_IMR 0x18 -#define SCOOP_ISR 0x1c -#define SCOOP_GPCR 0x20 -#define SCOOP_GPWR 0x24 -#define SCOOP_GPRR 0x28 +#define SCOOP_MCR 0x00 +#define SCOOP_CDR 0x04 +#define SCOOP_CSR 0x08 +#define SCOOP_CPR 0x0c +#define SCOOP_CCR 0x10 +#define SCOOP_IRR_IRM 0x14 +#define SCOOP_IMR 0x18 +#define SCOOP_ISR 0x1c +#define SCOOP_GPCR 0x20 +#define SCOOP_GPWR 0x24 +#define SCOOP_GPRR 0x28 -static inline void scoop_gpio_handler_update(ScoopInfo *s) { +static inline void scoop_gpio_handler_update(ScoopInfo *s) +{ uint32_t level, diff; int bit; level = s->gpio_level & s->gpio_dir; @@ -125,8 +126,9 @@ static void scoop_write(void *opaque, hwaddr addr, break; case SCOOP_CPR: s->power = value; - if (value & 0x80) + if (value & 0x80) { s->power |= 0x8040; + } break; case SCOOP_CCR: s->ccr = value; @@ -145,7 +147,7 @@ static void scoop_write(void *opaque, hwaddr addr, scoop_gpio_handler_update(s); break; case SCOOP_GPWR: - case SCOOP_GPRR: /* GPRR is probably R/O in real HW */ + case SCOOP_GPRR: /* GPRR is probably R/O in real HW */ s->gpio_level = value & s->gpio_dir; scoop_gpio_handler_update(s); break; @@ -166,10 +168,11 @@ static void scoop_gpio_set(void *opaque, int line, int level) { ScoopInfo *s = (ScoopInfo *) opaque; - if (level) + if (level) { s->gpio_level |= (1 << line); - else + } else { s->gpio_level &= ~(1 << line); + } } static void scoop_init(Object *obj) @@ -203,7 +206,7 @@ static int scoop_post_load(void *opaque, int version_id) return 0; } -static bool is_version_0 (void *opaque, int version_id) +static bool is_version_0(void *opaque, int version_id) { return version_id == 0; } @@ -265,7 +268,7 @@ type_init(scoop_register_types) /* Write the bootloader parameters memory area. */ -#define MAGIC_CHG(a, b, c, d) ((d << 24) | (c << 16) | (b << 8) | a) +#define MAGIC_CHG(a, b, c, d) ((d << 24) | (c << 16) | (b << 8) | a) static struct QEMU_PACKED sl_param_info { uint32_t comadj_keyword; @@ -286,16 +289,16 @@ static struct QEMU_PACKED sl_param_info { uint32_t phad_keyword; int32_t phadadj; } zaurus_bootparam = { - .comadj_keyword = MAGIC_CHG('C', 'M', 'A', 'D'), - .comadj = 125, - .uuid_keyword = MAGIC_CHG('U', 'U', 'I', 'D'), - .uuid = { -1 }, - .touch_keyword = MAGIC_CHG('T', 'U', 'C', 'H'), - .touch_xp = -1, - .adadj_keyword = MAGIC_CHG('B', 'V', 'A', 'D'), - .adadj = -1, - .phad_keyword = MAGIC_CHG('P', 'H', 'A', 'D'), - .phadadj = 0x01, + .comadj_keyword = MAGIC_CHG('C', 'M', 'A', 'D'), + .comadj = 125, + .uuid_keyword = MAGIC_CHG('U', 'U', 'I', 'D'), + .uuid = { -1 }, + .touch_keyword = MAGIC_CHG('T', 'U', 'C', 'H'), + .touch_xp = -1, + .adadj_keyword = MAGIC_CHG('B', 'V', 'A', 'D'), + .adadj = -1, + .phad_keyword = MAGIC_CHG('P', 'H', 'A', 'D'), + .phadadj = 0x01, }; void sl_bootparam_write(hwaddr ptr) diff --git a/hw/input/tsc2005.c b/hw/input/tsc2005.c index ac7f54eeafb..54a15d24410 100644 --- a/hw/input/tsc2005.c +++ b/hw/input/tsc2005.c @@ -28,10 +28,10 @@ #include "migration/vmstate.h" #include "trace.h" -#define TSC_CUT_RESOLUTION(value, p) ((value) >> (16 - (p ? 12 : 10))) +#define TSC_CUT_RESOLUTION(value, p) ((value) >> (16 - (p ? 12 : 10))) typedef struct { - qemu_irq pint; /* Combination of the nPENIRQ and DAV signals */ + qemu_irq pint; /* Combination of the nPENIRQ and DAV signals */ QEMUTimer *timer; uint16_t model; @@ -63,7 +63,7 @@ typedef struct { } TSC2005State; enum { - TSC_MODE_XYZ_SCAN = 0x0, + TSC_MODE_XYZ_SCAN = 0x0, TSC_MODE_XY_SCAN, TSC_MODE_X, TSC_MODE_Y, @@ -82,100 +82,100 @@ enum { }; static const uint16_t mode_regs[16] = { - 0xf000, /* X, Y, Z scan */ - 0xc000, /* X, Y scan */ - 0x8000, /* X */ - 0x4000, /* Y */ - 0x3000, /* Z */ - 0x0800, /* AUX */ - 0x0400, /* TEMP1 */ - 0x0200, /* TEMP2 */ - 0x0800, /* AUX scan */ - 0x0040, /* X test */ - 0x0020, /* Y test */ - 0x0080, /* Short-circuit test */ - 0x0000, /* Reserved */ - 0x0000, /* X+, X- drivers */ - 0x0000, /* Y+, Y- drivers */ - 0x0000, /* Y+, X- drivers */ + 0xf000, /* X, Y, Z scan */ + 0xc000, /* X, Y scan */ + 0x8000, /* X */ + 0x4000, /* Y */ + 0x3000, /* Z */ + 0x0800, /* AUX */ + 0x0400, /* TEMP1 */ + 0x0200, /* TEMP2 */ + 0x0800, /* AUX scan */ + 0x0040, /* X test */ + 0x0020, /* Y test */ + 0x0080, /* Short-circuit test */ + 0x0000, /* Reserved */ + 0x0000, /* X+, X- drivers */ + 0x0000, /* Y+, Y- drivers */ + 0x0000, /* Y+, X- drivers */ }; -#define X_TRANSFORM(s) \ +#define X_TRANSFORM(s) \ ((s->y * s->tr[0] - s->x * s->tr[1]) / s->tr[2] + s->tr[3]) -#define Y_TRANSFORM(s) \ +#define Y_TRANSFORM(s) \ ((s->y * s->tr[4] - s->x * s->tr[5]) / s->tr[6] + s->tr[7]) -#define Z1_TRANSFORM(s) \ +#define Z1_TRANSFORM(s) \ ((400 - ((s)->x >> 7) + ((s)->pressure << 10)) << 4) -#define Z2_TRANSFORM(s) \ +#define Z2_TRANSFORM(s) \ ((4000 + ((s)->y >> 7) - ((s)->pressure << 10)) << 4) -#define AUX_VAL (700 << 4) /* +/- 3 at 12-bit */ -#define TEMP1_VAL (1264 << 4) /* +/- 5 at 12-bit */ -#define TEMP2_VAL (1531 << 4) /* +/- 5 at 12-bit */ +#define AUX_VAL (700 << 4) /* +/- 3 at 12-bit */ +#define TEMP1_VAL (1264 << 4) /* +/- 5 at 12-bit */ +#define TEMP2_VAL (1531 << 4) /* +/- 5 at 12-bit */ static uint16_t tsc2005_read(TSC2005State *s, int reg) { uint16_t ret; switch (reg) { - case 0x0: /* X */ + case 0x0: /* X */ s->dav &= ~mode_regs[TSC_MODE_X]; return TSC_CUT_RESOLUTION(X_TRANSFORM(s), s->precision) + (s->noise & 3); - case 0x1: /* Y */ + case 0x1: /* Y */ s->dav &= ~mode_regs[TSC_MODE_Y]; - s->noise ++; + s->noise++; return TSC_CUT_RESOLUTION(Y_TRANSFORM(s), s->precision) ^ (s->noise & 3); - case 0x2: /* Z1 */ + case 0x2: /* Z1 */ s->dav &= 0xdfff; return TSC_CUT_RESOLUTION(Z1_TRANSFORM(s), s->precision) - (s->noise & 3); - case 0x3: /* Z2 */ + case 0x3: /* Z2 */ s->dav &= 0xefff; return TSC_CUT_RESOLUTION(Z2_TRANSFORM(s), s->precision) | (s->noise & 3); - case 0x4: /* AUX */ + case 0x4: /* AUX */ s->dav &= ~mode_regs[TSC_MODE_AUX]; return TSC_CUT_RESOLUTION(AUX_VAL, s->precision); - case 0x5: /* TEMP1 */ + case 0x5: /* TEMP1 */ s->dav &= ~mode_regs[TSC_MODE_TEMP1]; return TSC_CUT_RESOLUTION(TEMP1_VAL, s->precision) - (s->noise & 5); - case 0x6: /* TEMP2 */ + case 0x6: /* TEMP2 */ s->dav &= 0xdfff; s->dav &= ~mode_regs[TSC_MODE_TEMP2]; return TSC_CUT_RESOLUTION(TEMP2_VAL, s->precision) ^ (s->noise & 3); - case 0x7: /* Status */ + case 0x7: /* Status */ ret = s->dav | (s->reset << 7) | (s->pdst << 2) | 0x0; s->dav &= ~(mode_regs[TSC_MODE_X_TEST] | mode_regs[TSC_MODE_Y_TEST] | mode_regs[TSC_MODE_TS_TEST]); s->reset = true; return ret; - case 0x8: /* AUX high threshold */ + case 0x8: /* AUX high threshold */ return s->aux_thr[1]; - case 0x9: /* AUX low threshold */ + case 0x9: /* AUX low threshold */ return s->aux_thr[0]; - case 0xa: /* TEMP high threshold */ + case 0xa: /* TEMP high threshold */ return s->temp_thr[1]; - case 0xb: /* TEMP low threshold */ + case 0xb: /* TEMP low threshold */ return s->temp_thr[0]; - case 0xc: /* CFR0 */ + case 0xc: /* CFR0 */ return (s->pressure << 15) | ((!s->busy) << 14) | - (s->nextprecision << 13) | s->timing[0]; - case 0xd: /* CFR1 */ + (s->nextprecision << 13) | s->timing[0]; + case 0xd: /* CFR1 */ return s->timing[1]; - case 0xe: /* CFR2 */ + case 0xe: /* CFR2 */ return (s->pin_func << 14) | s->filter; - case 0xf: /* Function select status */ + case 0xf: /* Function select status */ return s->function >= 0 ? 1 << s->function : 0; } @@ -200,13 +200,14 @@ static void tsc2005_write(TSC2005State *s, int reg, uint16_t data) s->temp_thr[0] = data; break; - case 0xc: /* CFR0 */ + case 0xc: /* CFR0 */ s->host_mode = (data >> 15) != 0; if (s->enabled != !(data & 0x4000)) { s->enabled = !(data & 0x4000); trace_tsc2005_sense(s->enabled ? "enabled" : "disabled"); - if (s->busy && !s->enabled) + if (s->busy && !s->enabled) { timer_del(s->timer); + } s->busy = s->busy && s->enabled; } s->nextprecision = (data >> 13) & 1; @@ -216,10 +217,10 @@ static void tsc2005_write(TSC2005State *s, int reg, uint16_t data) "tsc2005_write: illegal conversion clock setting\n"); } break; - case 0xd: /* CFR1 */ + case 0xd: /* CFR1 */ s->timing[1] = data & 0xf07; break; - case 0xe: /* CFR2 */ + case 0xe: /* CFR2 */ s->pin_func = (data >> 14) & 3; s->filter = data & 0x3fff; break; @@ -258,10 +259,12 @@ static void tsc2005_pin_update(TSC2005State *s) switch (s->nextfunction) { case TSC_MODE_XYZ_SCAN: case TSC_MODE_XY_SCAN: - if (!s->host_mode && s->dav) + if (!s->host_mode && s->dav) { s->enabled = false; - if (!s->pressure) + } + if (!s->pressure) { return; + } /* Fall through */ case TSC_MODE_AUX_SCAN: break; @@ -269,8 +272,9 @@ static void tsc2005_pin_update(TSC2005State *s) case TSC_MODE_X: case TSC_MODE_Y: case TSC_MODE_Z: - if (!s->pressure) + if (!s->pressure) { return; + } /* Fall through */ case TSC_MODE_AUX: case TSC_MODE_TEMP1: @@ -278,8 +282,9 @@ static void tsc2005_pin_update(TSC2005State *s) case TSC_MODE_X_TEST: case TSC_MODE_Y_TEST: case TSC_MODE_TS_TEST: - if (s->dav) + if (s->dav) { s->enabled = false; + } break; case TSC_MODE_RESERVED: @@ -290,13 +295,14 @@ static void tsc2005_pin_update(TSC2005State *s) return; } - if (!s->enabled || s->busy) + if (!s->enabled || s->busy) { return; + } s->busy = true; s->precision = s->nextprecision; s->function = s->nextfunction; - s->pdst = !s->pnd0; /* Synchronised on internal clock */ + s->pdst = !s->pnd0; /* Synchronised on internal clock */ expires = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + (NANOSECONDS_PER_SECOND >> 7); timer_mod(s->timer, expires); @@ -331,7 +337,7 @@ static uint8_t tsc2005_txrx_word(void *opaque, uint8_t value) TSC2005State *s = opaque; uint32_t ret = 0; - switch (s->state ++) { + switch (s->state++) { case 0: if (value & 0x80) { /* Command */ @@ -343,8 +349,9 @@ static uint8_t tsc2005_txrx_word(void *opaque, uint8_t value) if (s->enabled != !(value & 1)) { s->enabled = !(value & 1); trace_tsc2005_sense(s->enabled ? "enabled" : "disabled"); - if (s->busy && !s->enabled) + if (s->busy && !s->enabled) { timer_del(s->timer); + } s->busy = s->busy && s->enabled; } tsc2005_pin_update(s); @@ -368,10 +375,11 @@ static uint8_t tsc2005_txrx_word(void *opaque, uint8_t value) break; case 1: - if (s->command) + if (s->command) { ret = (s->data >> 8) & 0xff; - else + } else { s->data |= value << 8; + } break; case 2: @@ -412,8 +420,9 @@ static void tsc2005_timer_tick(void *opaque) /* Timer ticked -- a set of conversions has been finished. */ - if (!s->busy) + if (!s->busy) { return; + } s->busy = false; s->dav |= mode_regs[function]; @@ -438,8 +447,9 @@ static void tsc2005_touchscreen_event(void *opaque, * signaling TS events immediately, but for now we simulate * the first conversion delay for sake of correctness. */ - if (p != s->pressure) + if (p != s->pressure) { tsc2005_pin_update(s); + } } static int tsc2005_post_load(void *opaque, int version_id) From patchwork Tue May 28 14:07:19 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799466 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255977wrz; Tue, 28 May 2024 07:10:45 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX85W1Mlvx0Q8YQ8NV3DjrDB70AbJ4TjNxDJiyR8Tn+Ulmhgg0G7ICbTyP6J1tLeZ7SgCgQvdz8MeWflL4TJHfg X-Google-Smtp-Source: AGHT+IHW4kaboZ5VoWBDpc5+tWPb+rjTjubvKlN+WS5XKDlDq8ZpxXwbMNCJPX/miYMlAhZYT2ZG X-Received: by 2002:a05:620a:1a95:b0:794:8429:23be with SMTP id af79cd13be357-794ab054fdbmr1704810085a.6.1716905444680; Tue, 28 May 2024 07:10:44 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905444; cv=none; d=google.com; s=arc-20160816; b=yoSAxnEHJNcWMsCYo/WZcTFmngt2uFXZ6Yok/WeWTNtX+gA6ia/1vDKmJH2XS6u0ew p7mss8mTBm0Aq05ORZOBa+z/sbv0PQr2b39p7mZPsRCohB9nWtCG9+q3rghKvZR8JiuE k5VXIftBUbcecAnyLwt5EN1SqfAAGiSX7IOkzK0P2pVds8VnBeF0cVLdnvF4MDqViydj cX/JmWooiNG8sgjRdjh+wFjZe6o3qXgCxYu+1MetsPQthb5c2zyRIrnYVjBMulnSYBxW VjJlyVaakxmnqRrIZTXDAXLOxwgNk+hG9WyOUiDbi05Gu6lXgmrZ6aFZ/x5Jg6lo7E6y PM0g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=yISSHG5pyQA29zkBCoQV4o7C+tL/0qrYSueTe3e1ZIE=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=rzUQbljRfPSH2HIcFdL7bJi4Df5AUw+oGGAyPAkG8OJAzwy7RJR5ciSx0GypSiPk7j CT310KkpENFhkzmzdOsSB2CHn0XaolQAQ6lbYplYDrARccHJeKaPZulcw+/kxW8gXOKo 0SiF7Pu+To2Jqppda45JTXBbKpsrBefZ99Sckb13zqQrSGqDJCh2tU+jRwUeA2aenuf/ iyZ/Dz/Phdk0/cTpxTho1BNJF1515nQ7Sl0se9J/H+ylvCDN4hQD6fA1uLUvDo2MxOki gBqO6Gwlyrn4m+v3SyCBkg+LucIi4RigX7GD1M/NHAZtAFNXHg/BNkYa8V1E965NnzA3 zUFQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MSuPn4vM; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id af79cd13be357-794abd50ecesi1016586785a.612.2024.05.28.07.10.44 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:44 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MSuPn4vM; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUj-0001Wl-4E; Tue, 28 May 2024 10:08:05 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUh-0001VX-Si for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:03 -0400 Received: from mail-wr1-x42e.google.com ([2a00:1450:4864:20::42e]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUg-00072U-9c for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:03 -0400 Received: by mail-wr1-x42e.google.com with SMTP id ffacd0b85a97d-354fb2d9026so761319f8f.1 for ; Tue, 28 May 2024 07:08:01 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905280; x=1717510080; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=yISSHG5pyQA29zkBCoQV4o7C+tL/0qrYSueTe3e1ZIE=; b=MSuPn4vMNdreeioxo0Xi8JzhsQZozxn9C18cDiQcdEd1FcJuYLhY9oqclq6tcMPnj+ o4101bo0rXaj96U3X9yJ3wv3cwEURrAJRCFiCICd98nv6YGPFKymerM+YEmaJ3/Zu6oo nir9C/0aoR8+5KFAPO1tcl6C7ofoWWT7PqF62peFb0FFnrJzP8IzX+PIq+mG+HFienJu +YElKhqr9neevEY4rckaC/x6txxOs5lvfwB/6AoG5nRPfikh3Xl4uvP/JNTGqFRZj+T6 TnwnNlMLigO/qVx7I/gPgdd8V+nDS1GGVh1svPlsxG4bAvMzYAzwHwaNFGLNYFbOyLZ2 jKyQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905280; x=1717510080; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=yISSHG5pyQA29zkBCoQV4o7C+tL/0qrYSueTe3e1ZIE=; b=II0VDff2atUH59EkrCHbf70SdpRFJ/PyrK7NDqVLHFr8wcgEG/aZywNZx2nyU19KoI bSLaZ+I/gb/GXFjY9fxBn5I+9WzcKmiEecXzWwdCjKIIxDgY4HDVOEL0uNN9bEng8psr qUClqgtE+2s1q4RC+C3UWGdhK4SdClvGdEX0iMcN5qQ/7OGhALxNCRUzV51ZVp+F7K6I uLEEE9OfzBrgN/C4sLdSa7B3fB/lx5JPHgwU29UYdf25wzAx+8COZF0+CuQHencSseXd 6fs/oYU0aw5qs8aSnsUipHBPtCswwGLpWS/OxXxDa2iblJ5w/7j9JNMkg+92i28Xq1sz y91Q== X-Gm-Message-State: AOJu0YygE+7uhws+06RsMSlytYY482Rn/y5UFvxikxk0+NulU93KLxUb if5bYsrOmdKVeiv6BtDxrWYLnCYQtKlS5q/vH6vr7FFgTF+69v1zQUOA4AabAW0A7iTGOjqEt1c X X-Received: by 2002:adf:a34d:0:b0:354:dfd4:4f4d with SMTP id ffacd0b85a97d-35526c2b6bcmr7451490f8f.16.1716905280603; Tue, 28 May 2024 07:08:00 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.00 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:00 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 08/42] docs/system: Remove ADC from raspi documentation Date: Tue, 28 May 2024 15:07:19 +0100 Message-Id: <20240528140753.3620597-9-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42e; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42e.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Rayhan Faizel None of the RPi boards have ADC on-board. In real life, an external ADC chip is required to operate on analog signals. Signed-off-by: Rayhan Faizel Reviewed-by: Philippe Mathieu-Daudé Message-id: 20240512085716.222326-1-rayhan.faizel@gmail.com Signed-off-by: Peter Maydell --- docs/system/arm/raspi.rst | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/system/arm/raspi.rst b/docs/system/arm/raspi.rst index fbec1da6a1e..44eec3f1c33 100644 --- a/docs/system/arm/raspi.rst +++ b/docs/system/arm/raspi.rst @@ -40,7 +40,6 @@ Implemented devices Missing devices --------------- - * Analog to Digital Converter (ADC) * Pulse Width Modulation (PWM) * PCIE Root Port (raspi4b) * GENET Ethernet Controller (raspi4b) From patchwork Tue May 28 14:07:20 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799465 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255906wrz; Tue, 28 May 2024 07:10:39 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXKaaD/+iLdQyeRPx2xz7zC0jvmaUwvtAxsv+iKroOWPyD+KFr5FOJ14m2RnC0kJhJgJf65OZmpxmqvvDgpIj8v X-Google-Smtp-Source: AGHT+IFbcB4eedIkMmFOQavLlXXg9BnBHUUXfi8xdDlrD3tZq3oQJn3efnNpH3yuXql96ltn3qTY X-Received: by 2002:a05:6214:4981:b0:6ab:76a2:593d with SMTP id 6a1803df08f44-6abccfa64e1mr120982136d6.45.1716905438693; Tue, 28 May 2024 07:10:38 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905438; cv=none; d=google.com; s=arc-20160816; b=wwzEauWsPBnpEau+T52aaU8t4+M38wBtxAs1qaLWjxQpugk0jnbrGcSPVPEpXmAeJB 2SFwjgmv8pEKQv9XSfromZMGxMBeJr+OXX4xpbWV083GharMWvrQotbOgC3w8MtU/dcY 91p+9DPw5gEqCKBtSyR7aw45D2GvPgRVMfmF2rEtgX8ndONQj8eJM7P2kwTWWXdgLGZ6 50WhDo0hK4vdsJKa2QwGJdrk710KnaCt5b0Zz4suAw5CYi9uNKRHw3m1fESuMgTyip2m C17J2M1KK8M5hIDC0AB2kVBAcvSKfU5dbhOPLTNvqRIK1M8K6z8W9/1YMVJpdjmvqC5p I+LA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=7mmWhNodKbmTLVdPuiuTCYlFcWsuhcev1rLaRhnWvpU=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=vFo/RmUr5DWYOs8nJ0QEUSA9G4b+h5Y+VKljRc6rNgVxbIzzbzIgSfdMlrtOEnxBSA LWj2Jv2JnklLVc5ty1zUhA/XokbXaOiAsylFwYDWi/KBIVz0tlGvOW4Io+Jo2ARCOXAY 4C6W9ISW7ImVYsFs6obhn7xR/i2ZIIjnvm9oLZexWKBQLmAm3rP02i5TIa8t39UtEB/f RRmSFie+KfLA31wrPEt5vVlZtuwXbzD9KFuUPmi5hsnNT53PBsOB9FRGsSpYnMwL2NMh 19xpCbxANT3Ibx9WGPvebjVKvOB7yNumwXheT9H/KRJXYiyJ+HLOoEeb6ELYOKJksj8H d88g==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=PtUL9w1j; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ad76dbe991si66673136d6.153.2024.05.28.07.10.38 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:38 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=PtUL9w1j; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUk-0001Yw-MR; Tue, 28 May 2024 10:08:06 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUi-0001WK-It for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:04 -0400 Received: from mail-wm1-x334.google.com ([2a00:1450:4864:20::334]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUg-00072i-Ld for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:04 -0400 Received: by mail-wm1-x334.google.com with SMTP id 5b1f17b1804b1-42101a2ac2cso6923375e9.0 for ; Tue, 28 May 2024 07:08:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905281; x=1717510081; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=7mmWhNodKbmTLVdPuiuTCYlFcWsuhcev1rLaRhnWvpU=; b=PtUL9w1jIYyYZoccIPB2P6ENWUhQKBcYY+hOc+awKoF+Pi1MgtnAploO2f5FtzDYJb 7L+KhJyGQC1b88nyX7e3kj4yhbTQK3ltCYX2Jc1vlVDg2vL8+bYcUXD/h01cg6pv/uaU jHGIUvwoCQtS/HlZ7oZsJFGFc1OCuZgXTOcww3YFa+L180RO+HatXdwNhzV4EHDj0SUF pwfDTXRkw1lWV4VnS2o1RzUNuD6ToqIXksbrNnwr/s1HIeHrlmBelRsMJ6xBRs/3sGVS sZOSwYrghEt7Y0Grbis3IcNhl3TyP25vI7DkXAb+0pWX4OdJ1rRwi0ub4r/SGCr+TmGt qbKQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905281; x=1717510081; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=7mmWhNodKbmTLVdPuiuTCYlFcWsuhcev1rLaRhnWvpU=; b=iPOnxzUv/KTKa06NvA278Ycu3XjAaGiBqOeNQXeQb2iudxTZ9YPlHnDapQDwhbxDVV Z+r1hy8/1WpWGY6ZZCvIPnu59EXvXbcchjpb9cmkjwfxQs9r+yGWIMGo1yhsMe0UTMNA IIUKtt/dC7BUhZ8QRjNYCHWvy9LAbtOFfU+r/PNe8h0ZHDW4wYpZdiCr2iwh9Tz2vgqm wS8lmPYoW0Tk7Dt40okjgtXXEIJ7OCc42NgJ2NPSB+ekwviQw91IegobRGAjAnQETuJH QukNcMkfd4wBDrHGSNhJSMXY/risXGzJIuAW09uts5oDHI9RU83mrE20vI3zPS7m7MBb cDtw== X-Gm-Message-State: AOJu0YxZvLErENYs7cRmv55v2LnXZ7PTWotSNEVEAT7lJUcAxza4z7Mv FriXHUvJqbsChclEhKrZ/fij+etDsVdaBm9meCRq6NheAToD+qKP8XX6Jr5vlGmLN0zlNvBx0VE w X-Received: by 2002:a5d:54cf:0:b0:357:73ca:9c00 with SMTP id ffacd0b85a97d-35773ca9de0mr5997579f8f.32.1716905281275; Tue, 28 May 2024 07:08:01 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.00 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:00 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 09/42] target/arm: Use PLD, PLDW, PLI not NOP for t32 Date: Tue, 28 May 2024 15:07:20 +0100 Message-Id: <20240528140753.3620597-10-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::334; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x334.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson This fixes a bug in that neither PLI nor PLDW are present in ARMv6T2, but are introduced with ARMv7 and ARMv7MP respectively. For clarity, do not use NOP for PLD. Note that there is no PLDW (literal). Architecturally in the T1 encoding of "PLD (literal)" bit 5 is "(0)", which means that it should be zero and if it is not then the behaviour is CONSTRAINED UNPREDICTABLE (might UNDEF, NOP, or ignore the value of the bit). In our implementation we have patterns for both: + PLD 1111 1000 -001 1111 1111 ------------ # (literal) + PLD 1111 1000 -011 1111 1111 ------------ # (literal) and so we effectively ignore the value of bit 5. (This is a permitted option for this CONSTRAINED UNPREDICTABLE.) This isn't a behaviour change in this commit, since we previously had NOP lines for both those patterns. Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20240524232121.284515-3-richard.henderson@linaro.org [PMM: adjusted commit message to note that PLD (lit) T1 bit 5 being 1 is an UNPREDICTABLE case.] Signed-off-by: Peter Maydell --- target/arm/tcg/t32.decode | 25 ++++++++++++------------- target/arm/tcg/translate.c | 4 ++-- 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/t32.decode b/target/arm/tcg/t32.decode index f21ad0167ab..d327178829d 100644 --- a/target/arm/tcg/t32.decode +++ b/target/arm/tcg/t32.decode @@ -458,41 +458,41 @@ STR_ri 1111 1000 1100 .... .... ............ @ldst_ri_pos # Note that Load, unsigned (literal) overlaps all other load encodings. { { - NOP 1111 1000 -001 1111 1111 ------------ # PLD + PLD 1111 1000 -001 1111 1111 ------------ # (literal) LDRB_ri 1111 1000 .001 1111 .... ............ @ldst_ri_lit } { - NOP 1111 1000 1001 ---- 1111 ------------ # PLD + PLD 1111 1000 1001 ---- 1111 ------------ # (immediate T1) LDRB_ri 1111 1000 1001 .... .... ............ @ldst_ri_pos } LDRB_ri 1111 1000 0001 .... .... 1..1 ........ @ldst_ri_idx { - NOP 1111 1000 0001 ---- 1111 1100 -------- # PLD + PLD 1111 1000 0001 ---- 1111 1100 -------- # (immediate T2) LDRB_ri 1111 1000 0001 .... .... 1100 ........ @ldst_ri_neg } LDRBT_ri 1111 1000 0001 .... .... 1110 ........ @ldst_ri_unp { - NOP 1111 1000 0001 ---- 1111 000000 -- ---- # PLD + PLD 1111 1000 0001 ---- 1111 000000 -- ---- # (register) LDRB_rr 1111 1000 0001 .... .... 000000 .. .... @ldst_rr } } { { - NOP 1111 1000 -011 1111 1111 ------------ # PLD + PLD 1111 1000 -011 1111 1111 ------------ # (literal) LDRH_ri 1111 1000 .011 1111 .... ............ @ldst_ri_lit } { - NOP 1111 1000 1011 ---- 1111 ------------ # PLDW + PLDW 1111 1000 1011 ---- 1111 ------------ # (immediate T1) LDRH_ri 1111 1000 1011 .... .... ............ @ldst_ri_pos } LDRH_ri 1111 1000 0011 .... .... 1..1 ........ @ldst_ri_idx { - NOP 1111 1000 0011 ---- 1111 1100 -------- # PLDW + PLDW 1111 1000 0011 ---- 1111 1100 -------- # (immediate T2) LDRH_ri 1111 1000 0011 .... .... 1100 ........ @ldst_ri_neg } LDRHT_ri 1111 1000 0011 .... .... 1110 ........ @ldst_ri_unp { - NOP 1111 1000 0011 ---- 1111 000000 -- ---- # PLDW + PLDW 1111 1000 0011 ---- 1111 000000 -- ---- # (register) LDRH_rr 1111 1000 0011 .... .... 000000 .. .... @ldst_rr } } @@ -504,24 +504,23 @@ STR_ri 1111 1000 1100 .... .... ............ @ldst_ri_pos LDRT_ri 1111 1000 0101 .... .... 1110 ........ @ldst_ri_unp LDR_rr 1111 1000 0101 .... .... 000000 .. .... @ldst_rr } -# NOPs here are PLI. { { - NOP 1111 1001 -001 1111 1111 ------------ + PLI 1111 1001 -001 1111 1111 ------------ # (literal T3) LDRSB_ri 1111 1001 .001 1111 .... ............ @ldst_ri_lit } { - NOP 1111 1001 1001 ---- 1111 ------------ + PLI 1111 1001 1001 ---- 1111 ------------ # (immediate T1) LDRSB_ri 1111 1001 1001 .... .... ............ @ldst_ri_pos } LDRSB_ri 1111 1001 0001 .... .... 1..1 ........ @ldst_ri_idx { - NOP 1111 1001 0001 ---- 1111 1100 -------- + PLI 1111 1001 0001 ---- 1111 1100 -------- # (immediate T2) LDRSB_ri 1111 1001 0001 .... .... 1100 ........ @ldst_ri_neg } LDRSBT_ri 1111 1001 0001 .... .... 1110 ........ @ldst_ri_unp { - NOP 1111 1001 0001 ---- 1111 000000 -- ---- + PLI 1111 1001 0001 ---- 1111 000000 -- ---- # (register) LDRSB_rr 1111 1001 0001 .... .... 000000 .. .... @ldst_rr } } diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index d605e10f110..187eacffd96 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -8765,12 +8765,12 @@ static bool trans_PLD(DisasContext *s, arg_PLD *a) return ENABLE_ARCH_5TE; } -static bool trans_PLDW(DisasContext *s, arg_PLD *a) +static bool trans_PLDW(DisasContext *s, arg_PLDW *a) { return arm_dc_feature(s, ARM_FEATURE_V7MP); } -static bool trans_PLI(DisasContext *s, arg_PLD *a) +static bool trans_PLI(DisasContext *s, arg_PLI *a) { return ENABLE_ARCH_7; } From patchwork Tue May 28 14:07:21 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799478 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257097wrz; Tue, 28 May 2024 07:12:32 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCV959liI4F9iPEv8wW+XVnrL0zGX6Aryd4sPdcbvySKmrUrZYpMnyQWUza8dorvenmkvdUWMqcIwrtoQ7CZWJcd X-Google-Smtp-Source: AGHT+IHUKFhknnkY+8cwIyx4hVOn2Aay3xON4utn6npTSRFq7V7AHvh5FC3HY4G3hErjoMwxxcZ8 X-Received: by 2002:a05:6214:d87:b0:6ad:84aa:2956 with SMTP id 6a1803df08f44-6ad84aa7f2amr82700506d6.13.1716905551905; Tue, 28 May 2024 07:12:31 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905551; cv=none; d=google.com; s=arc-20160816; b=g8eu7/ehg2V4iIj3brUoJUitsPNOOGNp0Ghf8zLoQA3tpAsEhtvKVvqb7/BsDH4h6f k99BZ5TKwHW0LFBwaVKuQlJeKjKSuGBDZz3577b8Hds9tIJK3mxwbmy6Npl6yCPMk/DB SWK0ZRkYC6LSuXXN484kzMp10X9Vgpxr//fU9/MkuJ/1+mf8M/xbsys0KSt9koex+DQY HCLPKSJHjKVV+Bf9Oi4FLE33QjV3Elwhy0wB3ZVSi6xQ4Dt/dnP60mCKNQ0eU4v0Qk4R seylJAH8Pfc3BBtSvBMLv14UyUmVVRJCqTbs+C5iUKl4yhaQrVog0WqIKJJLDMD+WSjH 3Lpg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=MMlq9Auj6l45MaC9OkLzg6YYNbQpSqIPdMIwL/zQx0E=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=ihPCzQNEsQIkjnFIJqOmsSECoPcJcK+d9PofVA63dn4HBrqqvAbBrBK9X/5T09X5RC Tdu/BZqM3YMnHNzhaahypMgqdngFlpLfL4twvj800QenIzRWPbOdq/G3qINv2lr9fIiQ EW1h/7iBLAh+v3rKB07EG6PGhDTtPkaxFWtxI6de04OW3sjlcxfMasNS3zlOuUyWjovx MfJa5XfOVP9wHiO9IFySBJCiPZ2x1MyPkfqINL8kHNj7wG4/WofMJi8WyXw9feeDMNTy FOfJM6fVcAhGhouxeNCTMrAts/a+C6H0YtOdnHDKTcTwnphHW6J6+tHLnyGftGdyWMh3 NMMQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=IA6bRw0J; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ac070f110esi76132716d6.218.2024.05.28.07.12.31 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:31 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=IA6bRw0J; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUv-0001fL-Iy; Tue, 28 May 2024 10:08:17 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUt-0001dt-E5 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:15 -0400 Received: from mail-wr1-x435.google.com ([2a00:1450:4864:20::435]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUh-00072s-4j for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:15 -0400 Received: by mail-wr1-x435.google.com with SMTP id ffacd0b85a97d-357f1c0b86fso644926f8f.0 for ; Tue, 28 May 2024 07:08:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905282; x=1717510082; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=MMlq9Auj6l45MaC9OkLzg6YYNbQpSqIPdMIwL/zQx0E=; b=IA6bRw0JA6ZrsWCaq7MPgvgmYEjgj5OAg8obfE9DzpzXm7HHkyOFBuo0YEL5b3r3/R y5wi7AEs53OeNGB2udEtdsN+w6i0w2lJqU2ZXY+s1v0ugYDeHxYpXsAx74LIozIpmnR4 UuIAjIoOrxjhhguCdXWSz1GfzSWqC9T47i67bhAvxnxfc4bjrRWaDkr8BT9GUKaTrkJR WbnmDzN+AWPX++OXOQAnsSEJ0DV7Ryr624f627bCkW2UUngGtgbMbbRwgg7Q9tlL7PXw vHMPN1Kpsngyxmu1IqEM7SpRJjtaaTAs8pO9S+On8R8YtPIGtxfkRPXFqCpCbLMYJ08s wD7w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905282; x=1717510082; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=MMlq9Auj6l45MaC9OkLzg6YYNbQpSqIPdMIwL/zQx0E=; b=mQXEgZFwgdWHhmUTgQkFqcpOK05fdZcI/hUv0TxPoeAISE22HmyMcqkQ4cD825qdB5 UF9QLVv2zbmKOlMzUj2K9yxxT9F1MHrK0IUP6tVYWQLAzFv8f9qwxJYK4hXCd1BnALzQ 7suJG8GJe3NSArTEP9aT95TDv1gNGTc+poyG7GhITdfykc6zLlZIP+uZI515UKqIjTe9 B3cHtXQZ5KjasdGvSkvsMIQZzgpEdQl3WyNm5B40QUg6xGYFL4ioVCAvK30Vb5zp6+zM +YZ9YhDwQTvQmYMGN9rV/y0s0t7WMlqAwUvu9D8XuL5q3OmTDYOdTobx25V+RFYNLdMD ts1w== X-Gm-Message-State: AOJu0YyFsq7NSeTlhF9qngO8MbkK9UGkLYRUE3iOihru/DbBrBM0wyBK lw7/IYdJtVkmh07e8E/uhL+ViaQ98QMDete2oCfi+A+22e/tXOsDjIlxVvYzmpUT9eqNq3c8VMu 7 X-Received: by 2002:adf:f605:0:b0:351:d78e:875e with SMTP id ffacd0b85a97d-35526c271e2mr8205750f8f.14.1716905281814; Tue, 28 May 2024 07:08:01 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.01 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:01 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 10/42] target/arm: Zero-extend writeback for fp16 FCVTZS (scalar, integer) Date: Tue, 28 May 2024 15:07:21 +0100 Message-Id: <20240528140753.3620597-11-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::435; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x435.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Fixes RISU mismatch for "fcvtzs h31, h0, #14". Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20240524232121.284515-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 4126aaa27e6..d97acdbaf9a 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8707,6 +8707,9 @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, read_vec_element_i32(s, tcg_op, rn, pass, size); fn(tcg_op, tcg_op, tcg_shift, tcg_fpstatus); if (is_scalar) { + if (size == MO_16 && !is_u) { + tcg_gen_ext16u_i32(tcg_op, tcg_op); + } write_fp_sreg(s, rd, tcg_op); } else { write_vec_element_i32(s, tcg_op, rd, pass, size); From patchwork Tue May 28 14:07:22 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799480 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257118wrz; Tue, 28 May 2024 07:12:33 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXINLIu2iJY2O1pLtBtff/YP6wT7gGyvxhK4nHi4Mqom/ADfhZ0zOA3FMD8QrE+nSxS9xy7PWkQWe60dHGn4s5/ X-Google-Smtp-Source: AGHT+IEX1RP6bUHoa7sPZ62gWWPz3lNiaCMDgkEef4klhNN9tz52QHCOGOoFSf8cEZpFkY4a697Y X-Received: by 2002:a54:441a:0:b0:3c9:6e80:8ea2 with SMTP id 5614622812f47-3d1a6019290mr12414507b6e.32.1716905553557; Tue, 28 May 2024 07:12:33 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905553; cv=none; d=google.com; s=arc-20160816; b=JyIxw54Gmsxbuw9MfVO1g9rhF7ulOMowFAzcwEa6cUrlvYvNTagukEViA39FTBdwft zjHVO9eBjyXXR9E9MvLokYciL9UUmlpNTs+p2pixoys3VwRY337o79C2j8C1Rv2n+60l bU67ZTad3EdmbuXE8bnip0XzKw/IrCl0MqyGQw+7R3+ZeyMDSQaQVq4VmJW+g9SjqLyJ UKIZRAoYhaeb4TYodeEqKQBh2VCwReyv6gb3eSwQDnrfKmKDEjNWVK9eYhVp9K8V3FXY SL9Z34s1XlLrCBAptPLFdhsmGEJmfC+/+Y4MM/viBRiQD+D/CFgkjtQVpom5hrMNCDvz bScA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=dZiOjDpaTDBfQcZ9XO1B8DxujP/epjSMsXMLUfhPG4s=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=O79bDRSp8E6T/UPUnJVBSiwY/s6h0ghNIosf0KN1uilqhrLvtNdcKII7lf2rhtm6jK j8RVZIwpTj+FnR5GxEOn1jfqFRFg9pisYc/cQWDecaBqrEBKUPtyCndOHu5RfwsWYe4Y 9CA4dKpiyXav3VcNHyfzyrUiIaRoGnTlJVsjz7Z4XeVIR0ZULCstBotj72j1vOv5w8Us PaHLMhnbN9s01qqIqR0Jpp7UdxcaIMW+dHEriRy0pGqBv9sWz6ach8aRNY4Bzsh5ruDH WBF2ZDSoboeEgRinCetvExKaxR8TJo6xSigMoRzV+LmoR7R6v+ighthvzeAS3mrdKbM4 Y1PA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=EGqjzigM; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18ca3b4si117031281cf.659.2024.05.28.07.12.33 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:33 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=EGqjzigM; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUm-0001Zo-Ab; Tue, 28 May 2024 10:08:08 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUl-0001ZV-9P for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:07 -0400 Received: from mail-wr1-x432.google.com ([2a00:1450:4864:20::432]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUi-000737-Nh for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:06 -0400 Received: by mail-wr1-x432.google.com with SMTP id ffacd0b85a97d-354df3ee1a9so762448f8f.1 for ; Tue, 28 May 2024 07:08:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905282; x=1717510082; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=dZiOjDpaTDBfQcZ9XO1B8DxujP/epjSMsXMLUfhPG4s=; b=EGqjzigM3hczXyA1ep8QwUHRljJ94Ftf7Sn1vjI/A7ts5km95xdXUFiNdpaBb2+ETn xa8qqjUbr6EqJR54dMaKRU7SXRFH0FVU9FGhPpjfgFB34/XJjxHpPHFfG4k5P8jIVGea kH/qZaEuHAaLKLV6auKbMlqTyES6ML+rIhP82r4V7lWnZrWvD/zpPQZrJZElBQblCpDH 2IFmYno36/rohVyG5JlZE/X0qrj4Io7gLumkeY+IpRYvBj9c320+5UZFNJ4jx7/Ykg2K otr4QFQ2ir/FRvzok7gPUxmlnSQISXGQxAsX+ZaIF+6QhESKZnxUdRaLbXAdBzExIgFD 3P3A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905282; x=1717510082; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=dZiOjDpaTDBfQcZ9XO1B8DxujP/epjSMsXMLUfhPG4s=; b=r7YQSdZrDPUrnpr5a2ChlYFnPumcTLQqjxvS0mLukM3fgb+UIsarsYG3J5hiDWvp3X HX9AMJHFyWqFYH2YTgISMuNqvoUtH/dtvkrFdiH9l1hFA2f+iCsKKoK71WEhIuBIKEx5 0rPVM0/DsifOIjUK+IJ6xnmLCL86EAIiBQjVu+PYt25lWGh+fmYZtuv0ppkgji5fg+rf Daqvw8nbJsZ64kpcRQWr3OqSzXCUDTNJZNIhjmPSmuF5gEa7rEDQyrIY2ABT/oTcZPno P0gNSdn7vwwTIl7eTAcTLFAcUQRdh+GqWtst6T7jI7tzVfdmLKpSOa7COjzbxmy3wHfg PNMQ== X-Gm-Message-State: AOJu0Yy/oEH3QvvW3t0AlpCLDK5G9uEGUMwElfqzwOuiaC29pIBiEbeO BBw1+rxSEo2480fldVzSpoDD8d/FnEleJBrQ+FKSzUqvKD3NfbeUQFTksKedO7hi/lYHzxhJ4q3 i X-Received: by 2002:a05:6000:1001:b0:354:f52b:db65 with SMTP id ffacd0b85a97d-355245e3d1dmr9303927f8f.3.1716905282324; Tue, 28 May 2024 07:08:02 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.01 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:02 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 11/42] target/arm: Fix decode of FMOV (hp) vs MOVI Date: Tue, 28 May 2024 15:07:22 +0100 Message-Id: <20240528140753.3620597-12-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::432; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x432.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson The decode of FMOV (vector, immediate, half-precision) vs invalid cases of MOVI are incorrect. Fixes RISU mismatch for invalid insn 0x2f01fd31. Fixes: 70b4e6a4457 ("arm/translate-a64: add FP16 FMOV to simd_mod_imm") Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20240524232121.284515-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d97acdbaf9a..5455ae36850 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7904,27 +7904,31 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) bool is_q = extract32(insn, 30, 1); uint64_t imm = 0; - if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) { - /* Check for FMOV (vector, immediate) - half-precision */ - if (!(dc_isar_feature(aa64_fp16, s) && o2 && cmode == 0xf)) { + if (o2) { + if (cmode != 0xf || is_neg) { unallocated_encoding(s); return; } - } - - if (!fp_access_check(s)) { - return; - } - - if (cmode == 15 && o2 && !is_neg) { /* FMOV (vector, immediate) - half-precision */ + if (!dc_isar_feature(aa64_fp16, s)) { + unallocated_encoding(s); + return; + } imm = vfp_expand_imm(MO_16, abcdefgh); /* now duplicate across the lanes */ imm = dup_const(MO_16, imm); } else { + if (cmode == 0xf && is_neg && !is_q) { + unallocated_encoding(s); + return; + } imm = asimd_imm_const(abcdefgh, cmode, is_neg); } + if (!fp_access_check(s)) { + return; + } + if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) { /* MOVI or MVNI, with MVNI negation handled above. */ tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), is_q ? 16 : 8, From patchwork Tue May 28 14:07:23 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799493 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257849wrz; Tue, 28 May 2024 07:13:51 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWKOewh6Jy62brE8knJ8txmiqtB3qI7+bgR9ftnVtDlLyYxore+u8GQ/CAPi5hqM0SXTorGY09zCkbnH2v25WOO X-Google-Smtp-Source: AGHT+IFREx2LKP0mWHGPFLtsUZu2RXYGqoraia1Q8Ar15ElWWyi6YnG0w9ZKBBmmd681M+qUjowp X-Received: by 2002:a05:6870:c1cb:b0:250:171d:5c74 with SMTP id 586e51a60fabf-250171d6f82mr3606301fac.26.1716905630760; Tue, 28 May 2024 07:13:50 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905630; cv=none; d=google.com; s=arc-20160816; b=G9QmzCVpMpbx6XBqRvkPc4IDffVS9mX1Nyv5+50gAzTvmw5Mg8VW+XJSSFQzG2WZGt syhRdsqgzwaA7/4E3PkEQM0xTzMwp92Ii83x3lBnSxlvqvZkbPT7k1v/sqLLjcYOvBKC 0zfnLHHffzBaSOSBu8E5LFn1mr3ojDFBLW7fNechVRjwYFPf30PQrwNPLfbHWS5rTtDP 4J1uqEV1JwwTF5A6V/vwBgLuRpqDC522ZPfGgx+I4xrbv2OVRLMrUVD5ZOoErRCgJqL7 W+emaReUXPNAUV6+tO3bDN4nSr+CjE5xRUu1PjRkYE/q61YyxSmS6MJ0DfkCnXBzP48m e9Gw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=0NfFGA91GjMAl+N5OiSeWRtiynvfnz6dd2uWVlnAF1w=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=JscD0PMPLU+APwkdk+Wy6llWbiOgzUrSY2jOqmtlP+pIVd6OJac2XeR3ikWAHam4LG kqMV4qi46b6C13KCNPmXl1jyHAmIu2DW4pAWhg7RzdVsJbEI7NSrUYtCfF0MoBMLobZd jz+VSl9kX0tWNWC3/+Q89YGCopTFszYYdPSThq8IXXl5fEy2vr7A6kp8dq6Adh/8OFYj yByfKBs8nRhVBS0kYB/TvxCtwWSHvAHWyPWEdLdVwF+dZHD6VkYTCVp93bOREmVa3tnE adx35xG8LqHCP6rf+yyIw6L55Givd72GEKU+Ad9cc0ZRdKtoxfgnXHGKC7GUOxhkOkvS IkfQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=BETzmEY0; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id a1e0cc1a2514c-804cbe7ba2asi2243961241.33.2024.05.28.07.13.50 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:50 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=BETzmEY0; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUn-0001aT-3P; Tue, 28 May 2024 10:08:09 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUk-0001Xi-UH for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:06 -0400 Received: from mail-wr1-x430.google.com ([2a00:1450:4864:20::430]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUi-00073C-Am for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:05 -0400 Received: by mail-wr1-x430.google.com with SMTP id ffacd0b85a97d-357ec504fcdso579070f8f.3 for ; Tue, 28 May 2024 07:08:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905283; x=1717510083; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=0NfFGA91GjMAl+N5OiSeWRtiynvfnz6dd2uWVlnAF1w=; b=BETzmEY0PNafl3znuUlD4c/Y0lmPXdi3hNHxdvHauEuL2AzjShnudTeos8PEPtNcIK Xp0tLzWkISgLc+dPfGLwV+e9AbA3f5idkzzPaTtWCVKet8+3kgoqEZCn4OtokELIdYve CZSSEnBag9MPlJoQXX6qf052j9vfVZ8t7qTxnoCznrqRGiiReySFlp4U7hQC6bjPB2PN 07F0DYK71e9Gv0aNweK7z4LIOsAe00Qbe3NSRPDy0H4wuPXBBUIBR1AYlpY3WlV2oPnp 1h5nOdxRgPTDJCfrlvra+6GAiP8eOdtuogQ3rqhhtUKGC99S6ENNa5SEKgCfnCxTkacP a9aQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905283; x=1717510083; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=0NfFGA91GjMAl+N5OiSeWRtiynvfnz6dd2uWVlnAF1w=; b=DRX7Pej58QtdzMKz+byUHKWmCnkgm6Z+IljfvVssRxZGu2S1e82Nm6xzGXspoc+q9d qT/a95ahkx5Ihjru9PSFojMkRNN+O6xxOP6HNhEmudv6QXfmrsF3TS2q2+1xZmSU9Yda OXmiJu9Zg83xfTabkF/qlXPfGnwta0waZBEchyDWefkPijpf6IztMiMKfMYUKepUll9b JfLkCeJC9bod78YvKIDOWki1JTX1KkjfMFaE57qwTUcB+vj4G9Vc68TeXUbcnnQKcgeL LmUFM87UT/AGEh4RRnni8+ElrlQUIGe6C4uDf7WgVkRTuF+3ZmY7aZc3DGHvbo7iyg3i TZhA== X-Gm-Message-State: AOJu0YwB56mIVq3ri0uxTYBPLMH6cy2LESYOKAR1cani7peHr3PSd5H/ dRhrG3bxgoMVBkmkaUB541uEdVxveb1SMIH/24fx1byUe8xY7bWepqhyRXsXmovWTWGZVzeGNWD q X-Received: by 2002:a5d:4950:0:b0:354:fc03:b44 with SMTP id ffacd0b85a97d-35526c27760mr7848927f8f.4.1716905282884; Tue, 28 May 2024 07:08:02 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.02 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:02 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 12/42] target/arm: Verify sz=0 for Advanced SIMD scalar pairwise (fp16) Date: Tue, 28 May 2024 15:07:23 +0100 Message-Id: <20240528140753.3620597-13-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::430; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x430.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson All of these insns have "if sz == '1' then UNDEFINED" in their pseudocode. Fixes a RISU miscompare for invalid insn 0x5ef0c87a. Fixes: 5c36d89567c ("arm/translate-a64: add all FP16 ops in simd_scalar_pairwise") Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20240524232121.284515-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 5455ae36850..0bdddb8517a 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8006,7 +8006,7 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0x2f: /* FMINP */ /* FP op, size[0] is 32 or 64 bit*/ if (!u) { - if (!dc_isar_feature(aa64_fp16, s)) { + if ((size & 1) || !dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } else { From patchwork Tue May 28 14:07:24 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799473 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256773wrz; Tue, 28 May 2024 07:12:00 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCUYJsZ0pGqfOUTEMIh2Y+542IQdiZjENx7lcsDL4HTGtTL/GiUL1MYb13iOIgHJ2lMpeUgz2KxEsFBTcBkAEZyC X-Google-Smtp-Source: AGHT+IFMPf+QqzejPEJpa+ZN1yeTZnnyNCUgHlzKbKiXzm6ioeEaGvp5IRRwlIyUiWF4uMbO9tjC X-Received: by 2002:a67:c785:0:b0:47b:9a99:1095 with SMTP id ada2fe7eead31-48a386578a9mr11642192137.22.1716905518110; Tue, 28 May 2024 07:11:58 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905518; cv=none; d=google.com; s=arc-20160816; b=as4YUxeouQ2/ht2j03AWFML/axPMlysUmdyIGjberWPdDN0wyu8zIcl9ZkK/DMAw0t yxU1y2BDbctl9iUp/vdGLvwnFQrBBXmC5HkPDjn22KKESkrb1luTM+yr3ZFye7Kcx34m IyUjudmsx/GamYNvkGuf1mKW2MSn7O1T9dLZMMlAJAyLiStPpqWezksjPiXlo84hvF0x 3e5oc/MBXSD0Lc1wab4KoM0FI4hON8JtB4m6sj981QEnY9L5mhrdhmogM9ZtO/bmptbq wrTpwS5eh036mcFlFai7PKGWmaxVegF7HSKqt3j/nWyReiHEH/XCW8kYciFj4BcyQ9ii O1uA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=WciRlzoMhhKEhX7CaIY9skfKWlBWC9Qtn9Zc1hUFaT8=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=UPh1JQx61FA/E8qg5popBk+lt47RhxfREb3Up+fFz4dE9axda4w4rDexFsM1dfmPRr a/2Nx4EOXhAOxrVbKepWuH5aAuM4ME6SpKBiAd8ZIaXbns2Zta9py+jZK+y6e+uaLIY7 v9BoOqBN8M7Ivmc8buy+6109rUNLGHkA8Q1Y83Hj+zilSSkEOMRtJgNsZN7C8VYjMAXD rjl08Bd4Wuf60aJZT2xwNrLGo7NJj4uM8HisUgHrpZo99DTUEsGEZtBvEsAZObEsBj2R cfmxVDcQ7Wo8XZhfOFfB4iqutX0IF+49eB8dYaK1BBSrvpCSJoQ51m8re4kGF1RkdpFb gCJw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MqZOfIur; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a4dab81b4si1302738137.168.2024.05.28.07.11.56 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:11:57 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MqZOfIur; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUr-0001br-4o; Tue, 28 May 2024 10:08:13 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUo-0001b5-N2 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: from mail-wr1-x434.google.com ([2a00:1450:4864:20::434]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUj-00073Z-RI for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: by mail-wr1-x434.google.com with SMTP id ffacd0b85a97d-35bf77ba951so210163f8f.3 for ; Tue, 28 May 2024 07:08:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905284; x=1717510084; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=WciRlzoMhhKEhX7CaIY9skfKWlBWC9Qtn9Zc1hUFaT8=; b=MqZOfIur8UdOn79BUa2OPC4kG5LYI9ADrXMYg2Xjbr3dx8h94043KEO1GgvjiIVBSL N7OKbMrI2CEYXfA6f5OzRvxyy/ItmW7WAQidNQKm3HhBvDKTwNkeov0FmNWfd8Le+8or i0hoYWCNYoGgxaMDD45wcaAqCnlJ/gK7lCvmnNvconElhrt81wqReunnjCFbW08BMEWx Yu/7GfmXA+YhoNfzxAkAIYJGHA7oweO09nq3HmeVl6Lj8KykfolD+9szkCJl4D11VaGX MmuzjaCsXMJv6gNqdaLk8xjy2vGZzTnfB7zvXH6ocv9kWBYJvAYBZg/wUImGsNO79VZP TFeg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905284; x=1717510084; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=WciRlzoMhhKEhX7CaIY9skfKWlBWC9Qtn9Zc1hUFaT8=; b=MPUfjST3NC12L+Pry9ux9CrEtHHFt9Z1wLVE6Bx8khPPnIxlMUmYKmdVQTsZ5t8Lno zVbYAsjvXHyHpolS+57nMWfdKgav/vGOFHyzrS54ZwhCQJTeIX29Ruf0DmWr8UWbIkkg uOXEeouBBqEbGrfthZkNZkxsvQeCjFkT0aZKBy8pAtj9loWbyOMsist8Fkv0VPOk27rb aqYC+ozvYtcaYGFtyvUaJ1t2T9FY4xUdUu1IgLLeSdQhLCMaAxWD5msvR3wYf7E4elM1 i4x07yPf/uRc68Y5D+vpEEyOoeRX0Mt7oGke/xYO8GkYkZZJHW3GrQsgRSJUJHQUPmcY fjXQ== X-Gm-Message-State: AOJu0YwL/PMTeBHsYtn2bMcjgS+B7xcdpNbROECFAdAhZeXO9X54fQmV jSca6jqn3DhlzLl/kqWqAPiXBLYc8Q8iRrExiawnf6JJOptorUC4EFYeuJxbGn6Fw4JFQkgOmQO 9 X-Received: by 2002:adf:e547:0:b0:354:fd11:2fa4 with SMTP id ffacd0b85a97d-35526c39f65mr9176614f8f.10.1716905283528; Tue, 28 May 2024 07:08:03 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.03 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:03 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 13/42] target/arm: Split out gengvec.c Date: Tue, 28 May 2024 15:07:24 +0100 Message-Id: <20240528140753.3620597-14-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::434; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x434.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate.h | 5 + target/arm/tcg/gengvec.c | 1612 ++++++++++++++++++++++++++++++++++++ target/arm/tcg/translate.c | 1588 ----------------------------------- target/arm/tcg/meson.build | 1 + 4 files changed, 1618 insertions(+), 1588 deletions(-) create mode 100644 target/arm/tcg/gengvec.c diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index dc66ff21908..80e85096a83 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -445,6 +445,11 @@ void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh); +void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh); +void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh); +void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh); + void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c new file mode 100644 index 00000000000..7a1856253ff --- /dev/null +++ b/target/arm/tcg/gengvec.c @@ -0,0 +1,1612 @@ +/* + * ARM generic vector expansion + * + * Copyright (c) 2003 Fabrice Bellard + * Copyright (c) 2005-2007 CodeSourcery + * Copyright (c) 2007 OpenedHand, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + */ + +#include "qemu/osdep.h" +#include "translate.h" + + +static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz, + gen_helper_gvec_3_ptr *fn) +{ + TCGv_ptr qc_ptr = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc)); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr, + opr_sz, max_sz, 0, fn); +} + +void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32 + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); +} + +void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32 + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); +} + +#define GEN_CMP0(NAME, COND) \ + void NAME(unsigned vece, uint32_t d, uint32_t m, \ + uint32_t opr_sz, uint32_t max_sz) \ + { tcg_gen_gvec_cmpi(COND, vece, d, m, 0, opr_sz, max_sz); } + +GEN_CMP0(gen_gvec_ceq0, TCG_COND_EQ) +GEN_CMP0(gen_gvec_cle0, TCG_COND_LE) +GEN_CMP0(gen_gvec_cge0, TCG_COND_GE) +GEN_CMP0(gen_gvec_clt0, TCG_COND_LT) +GEN_CMP0(gen_gvec_cgt0, TCG_COND_GT) + +#undef GEN_CMP0 + +static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_sari_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_sari_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_sari_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_ssra8_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_ssra16_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_ssra32_i32, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_ssra64_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. + */ + shift = MIN(shift, (8 << vece) - 1); + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); +} + +static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_shri_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_usra8_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8, }, + { .fni8 = gen_usra16_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16, }, + { .fni4 = gen_usra32_i32, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32, }, + { .fni8 = gen_usra64_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64, }, + }; + + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Unsigned results in all zeros as input to accumulate: nop. + */ + if (shift < (8 << vece)) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } else { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } +} + +/* + * Shift one less than the requested amount, and the low bit is + * the rounding bit. For the 8 and 16-bit operations, because we + * mask the low bit, we can perform a normal integer shift instead + * of a vector shift. + */ +static void gen_srshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_sar8i_i64(d, a, sh); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_sar16i_i64(d, a, sh); + tcg_gen_vec_add16_i64(d, d, t); +} + +void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t; + + /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ + if (sh == 32) { + tcg_gen_movi_i32(d, 0); + return; + } + t = tcg_temp_new_i32(); + tcg_gen_extract_i32(t, a, sh - 1, 1); + tcg_gen_sari_i32(d, a, sh); + tcg_gen_add_i32(d, d, t); +} + + void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_extract_i64(t, a, sh - 1, 1); + tcg_gen_sari_i64(d, a, sh); + tcg_gen_add_i64(d, d, t); +} + +static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec ones = tcg_temp_new_vec_matching(d); + + tcg_gen_shri_vec(vece, t, a, sh - 1); + tcg_gen_dupi_vec(vece, ones, 1); + tcg_gen_and_vec(vece, t, t, ones); + tcg_gen_sari_vec(vece, d, a, sh); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_srshr8_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_srshr16_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_srshr32_i32, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_srshr64_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + if (shift == (8 << vece)) { + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. With rounding, this produces + * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. + * I.e. always zero. + */ + tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_srsra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr8_i64(t, a, sh); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_srsra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr16_i64(t, a, sh); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_srsra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + gen_srshr32_i32(t, a, sh); + tcg_gen_add_i32(d, d, t); +} + +static void gen_srsra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr64_i64(t, a, sh); + tcg_gen_add_i64(d, d, t); +} + +static void gen_srsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + gen_srshr_vec(vece, t, a, sh); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_srsra8_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fni8 = gen_srsra16_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_srsra32_i32, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_srsra64_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. With rounding, this produces + * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. + * I.e. always zero. With accumulation, this leaves D unchanged. + */ + if (shift == (8 << vece)) { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_urshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_shr8i_i64(d, a, sh); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_shr16i_i64(d, a, sh); + tcg_gen_vec_add16_i64(d, d, t); +} + +void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t; + + /* Handle shift by the input size for the benefit of trans_URSHR_ri */ + if (sh == 32) { + tcg_gen_extract_i32(d, a, sh - 1, 1); + return; + } + t = tcg_temp_new_i32(); + tcg_gen_extract_i32(t, a, sh - 1, 1); + tcg_gen_shri_i32(d, a, sh); + tcg_gen_add_i32(d, d, t); +} + +void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_extract_i64(t, a, sh - 1, 1); + tcg_gen_shri_i64(d, a, sh); + tcg_gen_add_i64(d, d, t); +} + +static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec ones = tcg_temp_new_vec_matching(d); + + tcg_gen_shri_vec(vece, t, a, shift - 1); + tcg_gen_dupi_vec(vece, ones, 1); + tcg_gen_and_vec(vece, t, t, ones); + tcg_gen_shri_vec(vece, d, a, shift); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_urshr8_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_urshr16_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_urshr32_i32, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_urshr64_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + if (shift == (8 << vece)) { + /* + * Shifts larger than the element size are architecturally valid. + * Unsigned results in zero. With rounding, this produces a + * copy of the most significant bit. + */ + tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift - 1, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_ursra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 8) { + tcg_gen_vec_shr8i_i64(t, a, 7); + } else { + gen_urshr8_i64(t, a, sh); + } + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_ursra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 16) { + tcg_gen_vec_shr16i_i64(t, a, 15); + } else { + gen_urshr16_i64(t, a, sh); + } + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_ursra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + if (sh == 32) { + tcg_gen_shri_i32(t, a, 31); + } else { + gen_urshr32_i32(t, a, sh); + } + tcg_gen_add_i32(d, d, t); +} + +static void gen_ursra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 64) { + tcg_gen_shri_i64(t, a, 63); + } else { + gen_urshr64_i64(t, a, sh); + } + tcg_gen_add_i64(d, d, t); +} + +static void gen_ursra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + if (sh == (8 << vece)) { + tcg_gen_shri_vec(vece, t, a, sh - 1); + } else { + gen_urshr_vec(vece, t, a, sh); + } + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_ursra8_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fni8 = gen_ursra16_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_ursra32_i32, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_ursra64_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); +} + +static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); +} + +static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); +} + +static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); + tcg_gen_shri_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); +} + +void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 }; + const GVecGen2i ops[4] = { + { .fni8 = gen_shr8_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shr16_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shr32_ins_i32, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_shr64_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* Shift of esize leaves destination unchanged. */ + if (shift < (8 << vece)) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } else { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } +} + +static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); +} + +static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); +} + +static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_shli_vec(vece, t, a, sh); + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); +} + +void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 }; + const GVecGen2i ops[4] = { + { .fni8 = gen_shl8_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shl16_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shl32_ins_i32, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_shl64_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [0..esize-1]. */ + tcg_debug_assert(shift >= 0); + tcg_debug_assert(shift < (8 << vece)); + + if (shift == 0) { + tcg_gen_gvec_mov(vece, rd_ofs, rm_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_add_u8(d, d, a); +} + +static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_sub_u8(d, d, a); +} + +static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_add_u16(d, d, a); +} + +static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_sub_u16(d, d, a); +} + +static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_add_i32(d, d, a); +} + +static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_sub_i32(d, d, a); +} + +static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_add_i64(d, d, a); +} + +static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_sub_i64(d, d, a); +} + +static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_add_vec(vece, d, d, a); +} + +static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_sub_vec(vece, d, d, a); +} + +/* Note that while NEON does not support VMLA and VMLS as 64-bit ops, + * these tables are shared with AArch64 which does support them. + */ +void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_mul_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_mla8_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_mla16_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_mla32_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_mla64_i64, + .fniv = gen_mla_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_mul_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_mls8_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_mls16_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_mls32_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_mls64_i64, + .fniv = gen_mls_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +/* CMTST : test is "if (X & Y != 0)". */ +static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_and_i32(d, a, b); + tcg_gen_negsetcond_i32(TCG_COND_NE, d, d, tcg_constant_i32(0)); +} + +void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_and_i64(d, a, b); + tcg_gen_negsetcond_i64(TCG_COND_NE, d, d, tcg_constant_i64(0)); +} + +static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_and_vec(vece, d, a, b); + tcg_gen_dupi_vec(vece, a, 0); + tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); +} + +void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_cmp_vec, 0 }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_helper_neon_tst_u8, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_tst_u16, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_cmtst_i32, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_cmtst_i64, + .fniv = gen_cmtst_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) +{ + TCGv_i32 lval = tcg_temp_new_i32(); + TCGv_i32 rval = tcg_temp_new_i32(); + TCGv_i32 lsh = tcg_temp_new_i32(); + TCGv_i32 rsh = tcg_temp_new_i32(); + TCGv_i32 zero = tcg_constant_i32(0); + TCGv_i32 max = tcg_constant_i32(32); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i32(lsh, shift); + tcg_gen_neg_i32(rsh, lsh); + tcg_gen_shl_i32(lval, src, lsh); + tcg_gen_shr_i32(rval, src, rsh); + tcg_gen_movcond_i32(TCG_COND_LTU, dst, lsh, max, lval, zero); + tcg_gen_movcond_i32(TCG_COND_LTU, dst, rsh, max, rval, dst); +} + +void gen_ushl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) +{ + TCGv_i64 lval = tcg_temp_new_i64(); + TCGv_i64 rval = tcg_temp_new_i64(); + TCGv_i64 lsh = tcg_temp_new_i64(); + TCGv_i64 rsh = tcg_temp_new_i64(); + TCGv_i64 zero = tcg_constant_i64(0); + TCGv_i64 max = tcg_constant_i64(64); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i64(lsh, shift); + tcg_gen_neg_i64(rsh, lsh); + tcg_gen_shl_i64(lval, src, lsh); + tcg_gen_shr_i64(rval, src, rsh); + tcg_gen_movcond_i64(TCG_COND_LTU, dst, lsh, max, lval, zero); + tcg_gen_movcond_i64(TCG_COND_LTU, dst, rsh, max, rval, dst); +} + +static void gen_ushl_vec(unsigned vece, TCGv_vec dst, + TCGv_vec src, TCGv_vec shift) +{ + TCGv_vec lval = tcg_temp_new_vec_matching(dst); + TCGv_vec rval = tcg_temp_new_vec_matching(dst); + TCGv_vec lsh = tcg_temp_new_vec_matching(dst); + TCGv_vec rsh = tcg_temp_new_vec_matching(dst); + TCGv_vec msk, max; + + tcg_gen_neg_vec(vece, rsh, shift); + if (vece == MO_8) { + tcg_gen_mov_vec(lsh, shift); + } else { + msk = tcg_temp_new_vec_matching(dst); + tcg_gen_dupi_vec(vece, msk, 0xff); + tcg_gen_and_vec(vece, lsh, shift, msk); + tcg_gen_and_vec(vece, rsh, rsh, msk); + } + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_shlv_vec(vece, lval, src, lsh); + tcg_gen_shrv_vec(vece, rval, src, rsh); + + max = tcg_temp_new_vec_matching(dst); + tcg_gen_dupi_vec(vece, max, 8 << vece); + + /* + * The choice of LT (signed) and GEU (unsigned) are biased toward + * the instructions of the x86_64 host. For MO_8, the whole byte + * is significant so we must use an unsigned compare; otherwise we + * have already masked to a byte and so a signed compare works. + * Other tcg hosts have a full set of comparisons and do not care. + */ + if (vece == MO_8) { + tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max); + tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max); + tcg_gen_andc_vec(vece, lval, lval, lsh); + tcg_gen_andc_vec(vece, rval, rval, rsh); + } else { + tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max); + tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max); + tcg_gen_and_vec(vece, lval, lval, lsh); + tcg_gen_and_vec(vece, rval, rval, rsh); + } + tcg_gen_or_vec(vece, dst, lval, rval); +} + +void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_neg_vec, INDEX_op_shlv_vec, + INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_ushl_i32, + .fniv = gen_ushl_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_ushl_i64, + .fniv = gen_ushl_vec, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) +{ + TCGv_i32 lval = tcg_temp_new_i32(); + TCGv_i32 rval = tcg_temp_new_i32(); + TCGv_i32 lsh = tcg_temp_new_i32(); + TCGv_i32 rsh = tcg_temp_new_i32(); + TCGv_i32 zero = tcg_constant_i32(0); + TCGv_i32 max = tcg_constant_i32(31); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i32(lsh, shift); + tcg_gen_neg_i32(rsh, lsh); + tcg_gen_shl_i32(lval, src, lsh); + tcg_gen_umin_i32(rsh, rsh, max); + tcg_gen_sar_i32(rval, src, rsh); + tcg_gen_movcond_i32(TCG_COND_LEU, lval, lsh, max, lval, zero); + tcg_gen_movcond_i32(TCG_COND_LT, dst, lsh, zero, rval, lval); +} + +void gen_sshl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) +{ + TCGv_i64 lval = tcg_temp_new_i64(); + TCGv_i64 rval = tcg_temp_new_i64(); + TCGv_i64 lsh = tcg_temp_new_i64(); + TCGv_i64 rsh = tcg_temp_new_i64(); + TCGv_i64 zero = tcg_constant_i64(0); + TCGv_i64 max = tcg_constant_i64(63); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i64(lsh, shift); + tcg_gen_neg_i64(rsh, lsh); + tcg_gen_shl_i64(lval, src, lsh); + tcg_gen_umin_i64(rsh, rsh, max); + tcg_gen_sar_i64(rval, src, rsh); + tcg_gen_movcond_i64(TCG_COND_LEU, lval, lsh, max, lval, zero); + tcg_gen_movcond_i64(TCG_COND_LT, dst, lsh, zero, rval, lval); +} + +static void gen_sshl_vec(unsigned vece, TCGv_vec dst, + TCGv_vec src, TCGv_vec shift) +{ + TCGv_vec lval = tcg_temp_new_vec_matching(dst); + TCGv_vec rval = tcg_temp_new_vec_matching(dst); + TCGv_vec lsh = tcg_temp_new_vec_matching(dst); + TCGv_vec rsh = tcg_temp_new_vec_matching(dst); + TCGv_vec tmp = tcg_temp_new_vec_matching(dst); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_neg_vec(vece, rsh, shift); + if (vece == MO_8) { + tcg_gen_mov_vec(lsh, shift); + } else { + tcg_gen_dupi_vec(vece, tmp, 0xff); + tcg_gen_and_vec(vece, lsh, shift, tmp); + tcg_gen_and_vec(vece, rsh, rsh, tmp); + } + + /* Bound rsh so out of bound right shift gets -1. */ + tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1); + tcg_gen_umin_vec(vece, rsh, rsh, tmp); + tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp); + + tcg_gen_shlv_vec(vece, lval, src, lsh); + tcg_gen_sarv_vec(vece, rval, src, rsh); + + /* Select in-bound left shift. */ + tcg_gen_andc_vec(vece, lval, lval, tmp); + + /* Select between left and right shift. */ + if (vece == MO_8) { + tcg_gen_dupi_vec(vece, tmp, 0); + tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval); + } else { + tcg_gen_dupi_vec(vece, tmp, 0x80); + tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval); + } +} + +void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec, + INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_sshl_i32, + .fniv = gen_sshl_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_sshl_i64, + .fniv = gen_sshl_vec, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_add_vec(vece, x, a, b); + tcg_gen_usadd_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); +} + +void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_b, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_h, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_s, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_d, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_add_vec(vece, x, a, b); + tcg_gen_ssadd_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); +} + +void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_sub_vec(vece, x, a, b); + tcg_gen_ussub_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); +} + +void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_sub_vec(vece, x, a, b); + tcg_gen_sssub_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); +} + +void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_sabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_sub_i32(t, a, b); + tcg_gen_sub_i32(d, b, a); + tcg_gen_movcond_i32(TCG_COND_LT, d, a, b, d, t); +} + +static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_sub_i64(d, b, a); + tcg_gen_movcond_i64(TCG_COND_LT, d, a, b, d, t); +} + +static void gen_sabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_smin_vec(vece, t, a, b); + tcg_gen_smax_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); +} + +void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_sabd_i32, + .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_sabd_i64, + .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_sub_i32(t, a, b); + tcg_gen_sub_i32(d, b, a); + tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, d, t); +} + +static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_sub_i64(d, b, a); + tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, d, t); +} + +static void gen_uabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_umin_vec(vece, t, a, b); + tcg_gen_umax_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); +} + +void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_uabd_i32, + .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_uabd_i64, + .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_sabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_sabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); +} + +static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_sabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_saba_i32, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_saba_i64, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_uabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_uabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); +} + +static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_uabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_uaba_i32, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_uaba_i64, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index 187eacffd96..c5bc691d92b 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -2912,1594 +2912,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc) gen_rfe(s, pc, load_cpu_field(spsr)); } -static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, - uint32_t opr_sz, uint32_t max_sz, - gen_helper_gvec_3_ptr *fn) -{ - TCGv_ptr qc_ptr = tcg_temp_new_ptr(); - - tcg_gen_addi_ptr(qc_ptr, tcg_env, offsetof(CPUARMState, vfp.qc)); - tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr, - opr_sz, max_sz, 0, fn); -} - -void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static gen_helper_gvec_3_ptr * const fns[2] = { - gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32 - }; - tcg_debug_assert(vece >= 1 && vece <= 2); - gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); -} - -void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static gen_helper_gvec_3_ptr * const fns[2] = { - gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32 - }; - tcg_debug_assert(vece >= 1 && vece <= 2); - gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); -} - -#define GEN_CMP0(NAME, COND) \ - void NAME(unsigned vece, uint32_t d, uint32_t m, \ - uint32_t opr_sz, uint32_t max_sz) \ - { tcg_gen_gvec_cmpi(COND, vece, d, m, 0, opr_sz, max_sz); } - -GEN_CMP0(gen_gvec_ceq0, TCG_COND_EQ) -GEN_CMP0(gen_gvec_cle0, TCG_COND_LE) -GEN_CMP0(gen_gvec_cge0, TCG_COND_GE) -GEN_CMP0(gen_gvec_clt0, TCG_COND_LT) -GEN_CMP0(gen_gvec_cgt0, TCG_COND_GT) - -#undef GEN_CMP0 - -static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_sari_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_sari_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_sari_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - -void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sari_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_ssra8_i64, - .fniv = gen_ssra_vec, - .fno = gen_helper_gvec_ssra_b, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni8 = gen_ssra16_i64, - .fniv = gen_ssra_vec, - .fno = gen_helper_gvec_ssra_h, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_ssra32_i32, - .fniv = gen_ssra_vec, - .fno = gen_helper_gvec_ssra_s, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_ssra64_i64, - .fniv = gen_ssra_vec, - .fno = gen_helper_gvec_ssra_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize]. */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - /* - * Shifts larger than the element size are architecturally valid. - * Signed results in all sign bits. - */ - shift = MIN(shift, (8 << vece) - 1); - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); -} - -static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_shri_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - -void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_shri_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_usra8_i64, - .fniv = gen_usra_vec, - .fno = gen_helper_gvec_usra_b, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8, }, - { .fni8 = gen_usra16_i64, - .fniv = gen_usra_vec, - .fno = gen_helper_gvec_usra_h, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16, }, - { .fni4 = gen_usra32_i32, - .fniv = gen_usra_vec, - .fno = gen_helper_gvec_usra_s, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32, }, - { .fni8 = gen_usra64_i64, - .fniv = gen_usra_vec, - .fno = gen_helper_gvec_usra_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_64, }, - }; - - /* tszimm encoding produces immediates in the range [1..esize]. */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - /* - * Shifts larger than the element size are architecturally valid. - * Unsigned results in all zeros as input to accumulate: nop. - */ - if (shift < (8 << vece)) { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } else { - /* Nop, but we do need to clear the tail. */ - tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); - } -} - -/* - * Shift one less than the requested amount, and the low bit is - * the rounding bit. For the 8 and 16-bit operations, because we - * mask the low bit, we can perform a normal integer shift instead - * of a vector shift. - */ -static void gen_srshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, sh - 1); - tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); - tcg_gen_vec_sar8i_i64(d, a, sh); - tcg_gen_vec_add8_i64(d, d, t); -} - -static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, sh - 1); - tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); - tcg_gen_vec_sar16i_i64(d, a, sh); - tcg_gen_vec_add16_i64(d, d, t); -} - -static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) -{ - TCGv_i32 t; - - /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ - if (sh == 32) { - tcg_gen_movi_i32(d, 0); - return; - } - t = tcg_temp_new_i32(); - tcg_gen_extract_i32(t, a, sh - 1, 1); - tcg_gen_sari_i32(d, a, sh); - tcg_gen_add_i32(d, d, t); -} - -static void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_extract_i64(t, a, sh - 1, 1); - tcg_gen_sari_i64(d, a, sh); - tcg_gen_add_i64(d, d, t); -} - -static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec ones = tcg_temp_new_vec_matching(d); - - tcg_gen_shri_vec(vece, t, a, sh - 1); - tcg_gen_dupi_vec(vece, ones, 1); - tcg_gen_and_vec(vece, t, t, ones); - tcg_gen_sari_vec(vece, d, a, sh); - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_srshr8_i64, - .fniv = gen_srshr_vec, - .fno = gen_helper_gvec_srshr_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni8 = gen_srshr16_i64, - .fniv = gen_srshr_vec, - .fno = gen_helper_gvec_srshr_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_srshr32_i32, - .fniv = gen_srshr_vec, - .fno = gen_helper_gvec_srshr_s, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_srshr64_i64, - .fniv = gen_srshr_vec, - .fno = gen_helper_gvec_srshr_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize] */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - if (shift == (8 << vece)) { - /* - * Shifts larger than the element size are architecturally valid. - * Signed results in all sign bits. With rounding, this produces - * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. - * I.e. always zero. - */ - tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0); - } else { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } -} - -static void gen_srsra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - gen_srshr8_i64(t, a, sh); - tcg_gen_vec_add8_i64(d, d, t); -} - -static void gen_srsra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - gen_srshr16_i64(t, a, sh); - tcg_gen_vec_add16_i64(d, d, t); -} - -static void gen_srsra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) -{ - TCGv_i32 t = tcg_temp_new_i32(); - - gen_srshr32_i32(t, a, sh); - tcg_gen_add_i32(d, d, t); -} - -static void gen_srsra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - gen_srshr64_i64(t, a, sh); - tcg_gen_add_i64(d, d, t); -} - -static void gen_srsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - - gen_srshr_vec(vece, t, a, sh); - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_srsra8_i64, - .fniv = gen_srsra_vec, - .fno = gen_helper_gvec_srsra_b, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_8 }, - { .fni8 = gen_srsra16_i64, - .fniv = gen_srsra_vec, - .fno = gen_helper_gvec_srsra_h, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_srsra32_i32, - .fniv = gen_srsra_vec, - .fno = gen_helper_gvec_srsra_s, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_srsra64_i64, - .fniv = gen_srsra_vec, - .fno = gen_helper_gvec_srsra_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize] */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - /* - * Shifts larger than the element size are architecturally valid. - * Signed results in all sign bits. With rounding, this produces - * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. - * I.e. always zero. With accumulation, this leaves D unchanged. - */ - if (shift == (8 << vece)) { - /* Nop, but we do need to clear the tail. */ - tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); - } else { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } -} - -static void gen_urshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, sh - 1); - tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); - tcg_gen_vec_shr8i_i64(d, a, sh); - tcg_gen_vec_add8_i64(d, d, t); -} - -static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, sh - 1); - tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); - tcg_gen_vec_shr16i_i64(d, a, sh); - tcg_gen_vec_add16_i64(d, d, t); -} - -static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) -{ - TCGv_i32 t; - - /* Handle shift by the input size for the benefit of trans_URSHR_ri */ - if (sh == 32) { - tcg_gen_extract_i32(d, a, sh - 1, 1); - return; - } - t = tcg_temp_new_i32(); - tcg_gen_extract_i32(t, a, sh - 1, 1); - tcg_gen_shri_i32(d, a, sh); - tcg_gen_add_i32(d, d, t); -} - -static void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_extract_i64(t, a, sh - 1, 1); - tcg_gen_shri_i64(d, a, sh); - tcg_gen_add_i64(d, d, t); -} - -static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec ones = tcg_temp_new_vec_matching(d); - - tcg_gen_shri_vec(vece, t, a, shift - 1); - tcg_gen_dupi_vec(vece, ones, 1); - tcg_gen_and_vec(vece, t, t, ones); - tcg_gen_shri_vec(vece, d, a, shift); - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_shri_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_urshr8_i64, - .fniv = gen_urshr_vec, - .fno = gen_helper_gvec_urshr_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni8 = gen_urshr16_i64, - .fniv = gen_urshr_vec, - .fno = gen_helper_gvec_urshr_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_urshr32_i32, - .fniv = gen_urshr_vec, - .fno = gen_helper_gvec_urshr_s, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_urshr64_i64, - .fniv = gen_urshr_vec, - .fno = gen_helper_gvec_urshr_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize] */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - if (shift == (8 << vece)) { - /* - * Shifts larger than the element size are architecturally valid. - * Unsigned results in zero. With rounding, this produces a - * copy of the most significant bit. - */ - tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift - 1, opr_sz, max_sz); - } else { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } -} - -static void gen_ursra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - if (sh == 8) { - tcg_gen_vec_shr8i_i64(t, a, 7); - } else { - gen_urshr8_i64(t, a, sh); - } - tcg_gen_vec_add8_i64(d, d, t); -} - -static void gen_ursra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - if (sh == 16) { - tcg_gen_vec_shr16i_i64(t, a, 15); - } else { - gen_urshr16_i64(t, a, sh); - } - tcg_gen_vec_add16_i64(d, d, t); -} - -static void gen_ursra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) -{ - TCGv_i32 t = tcg_temp_new_i32(); - - if (sh == 32) { - tcg_gen_shri_i32(t, a, 31); - } else { - gen_urshr32_i32(t, a, sh); - } - tcg_gen_add_i32(d, d, t); -} - -static void gen_ursra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - if (sh == 64) { - tcg_gen_shri_i64(t, a, 63); - } else { - gen_urshr64_i64(t, a, sh); - } - tcg_gen_add_i64(d, d, t); -} - -static void gen_ursra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - - if (sh == (8 << vece)) { - tcg_gen_shri_vec(vece, t, a, sh - 1); - } else { - gen_urshr_vec(vece, t, a, sh); - } - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_shri_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen2i ops[4] = { - { .fni8 = gen_ursra8_i64, - .fniv = gen_ursra_vec, - .fno = gen_helper_gvec_ursra_b, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_8 }, - { .fni8 = gen_ursra16_i64, - .fniv = gen_ursra_vec, - .fno = gen_helper_gvec_ursra_h, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_ursra32_i32, - .fniv = gen_ursra_vec, - .fno = gen_helper_gvec_ursra_s, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_ursra64_i64, - .fniv = gen_ursra_vec, - .fno = gen_helper_gvec_ursra_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize] */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); -} - -static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); -} - -static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); -} - -static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); - tcg_gen_shri_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); -} - -void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 }; - const GVecGen2i ops[4] = { - { .fni8 = gen_shr8_ins_i64, - .fniv = gen_shr_ins_vec, - .fno = gen_helper_gvec_sri_b, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni8 = gen_shr16_ins_i64, - .fniv = gen_shr_ins_vec, - .fno = gen_helper_gvec_sri_h, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_shr32_ins_i32, - .fniv = gen_shr_ins_vec, - .fno = gen_helper_gvec_sri_s, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_shr64_ins_i64, - .fniv = gen_shr_ins_vec, - .fno = gen_helper_gvec_sri_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [1..esize]. */ - tcg_debug_assert(shift > 0); - tcg_debug_assert(shift <= (8 << vece)); - - /* Shift of esize leaves destination unchanged. */ - if (shift < (8 << vece)) { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } else { - /* Nop, but we do need to clear the tail. */ - tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); - } -} - -static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); -} - -static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); -} - -static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_shli_vec(vece, t, a, sh); - tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); -} - -void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - int64_t shift, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 }; - const GVecGen2i ops[4] = { - { .fni8 = gen_shl8_ins_i64, - .fniv = gen_shl_ins_vec, - .fno = gen_helper_gvec_sli_b, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni8 = gen_shl16_ins_i64, - .fniv = gen_shl_ins_vec, - .fno = gen_helper_gvec_sli_h, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_shl32_ins_i32, - .fniv = gen_shl_ins_vec, - .fno = gen_helper_gvec_sli_s, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_shl64_ins_i64, - .fniv = gen_shl_ins_vec, - .fno = gen_helper_gvec_sli_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - - /* tszimm encoding produces immediates in the range [0..esize-1]. */ - tcg_debug_assert(shift >= 0); - tcg_debug_assert(shift < (8 << vece)); - - if (shift == 0) { - tcg_gen_gvec_mov(vece, rd_ofs, rm_ofs, opr_sz, max_sz); - } else { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); - } -} - -static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_add_u8(d, d, a); -} - -static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_sub_u8(d, d, a); -} - -static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_add_u16(d, d, a); -} - -static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_sub_u16(d, d, a); -} - -static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_add_i32(d, d, a); -} - -static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_sub_i32(d, d, a); -} - -static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_add_i64(d, d, a); -} - -static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_sub_i64(d, d, a); -} - -static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_add_vec(vece, d, d, a); -} - -static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_sub_vec(vece, d, d, a); -} - -/* Note that while NEON does not support VMLA and VMLS as 64-bit ops, - * these tables are shared with AArch64 which does support them. - */ -void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_mul_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fni4 = gen_mla8_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni4 = gen_mla16_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_mla32_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_mla64_i64, - .fniv = gen_mla_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_mul_vec, INDEX_op_sub_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fni4 = gen_mls8_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni4 = gen_mls16_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_mls32_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_mls64_i64, - .fniv = gen_mls_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -/* CMTST : test is "if (X & Y != 0)". */ -static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_and_i32(d, a, b); - tcg_gen_negsetcond_i32(TCG_COND_NE, d, d, tcg_constant_i32(0)); -} - -void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_and_i64(d, a, b); - tcg_gen_negsetcond_i64(TCG_COND_NE, d, d, tcg_constant_i64(0)); -} - -static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_and_vec(vece, d, a, b); - tcg_gen_dupi_vec(vece, a, 0); - tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); -} - -void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { INDEX_op_cmp_vec, 0 }; - static const GVecGen3 ops[4] = { - { .fni4 = gen_helper_neon_tst_u8, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fni4 = gen_helper_neon_tst_u16, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_cmtst_i32, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_cmtst_i64, - .fniv = gen_cmtst_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) -{ - TCGv_i32 lval = tcg_temp_new_i32(); - TCGv_i32 rval = tcg_temp_new_i32(); - TCGv_i32 lsh = tcg_temp_new_i32(); - TCGv_i32 rsh = tcg_temp_new_i32(); - TCGv_i32 zero = tcg_constant_i32(0); - TCGv_i32 max = tcg_constant_i32(32); - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_ext8s_i32(lsh, shift); - tcg_gen_neg_i32(rsh, lsh); - tcg_gen_shl_i32(lval, src, lsh); - tcg_gen_shr_i32(rval, src, rsh); - tcg_gen_movcond_i32(TCG_COND_LTU, dst, lsh, max, lval, zero); - tcg_gen_movcond_i32(TCG_COND_LTU, dst, rsh, max, rval, dst); -} - -void gen_ushl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) -{ - TCGv_i64 lval = tcg_temp_new_i64(); - TCGv_i64 rval = tcg_temp_new_i64(); - TCGv_i64 lsh = tcg_temp_new_i64(); - TCGv_i64 rsh = tcg_temp_new_i64(); - TCGv_i64 zero = tcg_constant_i64(0); - TCGv_i64 max = tcg_constant_i64(64); - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_ext8s_i64(lsh, shift); - tcg_gen_neg_i64(rsh, lsh); - tcg_gen_shl_i64(lval, src, lsh); - tcg_gen_shr_i64(rval, src, rsh); - tcg_gen_movcond_i64(TCG_COND_LTU, dst, lsh, max, lval, zero); - tcg_gen_movcond_i64(TCG_COND_LTU, dst, rsh, max, rval, dst); -} - -static void gen_ushl_vec(unsigned vece, TCGv_vec dst, - TCGv_vec src, TCGv_vec shift) -{ - TCGv_vec lval = tcg_temp_new_vec_matching(dst); - TCGv_vec rval = tcg_temp_new_vec_matching(dst); - TCGv_vec lsh = tcg_temp_new_vec_matching(dst); - TCGv_vec rsh = tcg_temp_new_vec_matching(dst); - TCGv_vec msk, max; - - tcg_gen_neg_vec(vece, rsh, shift); - if (vece == MO_8) { - tcg_gen_mov_vec(lsh, shift); - } else { - msk = tcg_temp_new_vec_matching(dst); - tcg_gen_dupi_vec(vece, msk, 0xff); - tcg_gen_and_vec(vece, lsh, shift, msk); - tcg_gen_and_vec(vece, rsh, rsh, msk); - } - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_shlv_vec(vece, lval, src, lsh); - tcg_gen_shrv_vec(vece, rval, src, rsh); - - max = tcg_temp_new_vec_matching(dst); - tcg_gen_dupi_vec(vece, max, 8 << vece); - - /* - * The choice of LT (signed) and GEU (unsigned) are biased toward - * the instructions of the x86_64 host. For MO_8, the whole byte - * is significant so we must use an unsigned compare; otherwise we - * have already masked to a byte and so a signed compare works. - * Other tcg hosts have a full set of comparisons and do not care. - */ - if (vece == MO_8) { - tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max); - tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max); - tcg_gen_andc_vec(vece, lval, lval, lsh); - tcg_gen_andc_vec(vece, rval, rval, rsh); - } else { - tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max); - tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max); - tcg_gen_and_vec(vece, lval, lval, lsh); - tcg_gen_and_vec(vece, rval, rval, rsh); - } - tcg_gen_or_vec(vece, dst, lval, rval); -} - -void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_neg_vec, INDEX_op_shlv_vec, - INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_ushl_vec, - .fno = gen_helper_gvec_ushl_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fniv = gen_ushl_vec, - .fno = gen_helper_gvec_ushl_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_ushl_i32, - .fniv = gen_ushl_vec, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_ushl_i64, - .fniv = gen_ushl_vec, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) -{ - TCGv_i32 lval = tcg_temp_new_i32(); - TCGv_i32 rval = tcg_temp_new_i32(); - TCGv_i32 lsh = tcg_temp_new_i32(); - TCGv_i32 rsh = tcg_temp_new_i32(); - TCGv_i32 zero = tcg_constant_i32(0); - TCGv_i32 max = tcg_constant_i32(31); - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_ext8s_i32(lsh, shift); - tcg_gen_neg_i32(rsh, lsh); - tcg_gen_shl_i32(lval, src, lsh); - tcg_gen_umin_i32(rsh, rsh, max); - tcg_gen_sar_i32(rval, src, rsh); - tcg_gen_movcond_i32(TCG_COND_LEU, lval, lsh, max, lval, zero); - tcg_gen_movcond_i32(TCG_COND_LT, dst, lsh, zero, rval, lval); -} - -void gen_sshl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) -{ - TCGv_i64 lval = tcg_temp_new_i64(); - TCGv_i64 rval = tcg_temp_new_i64(); - TCGv_i64 lsh = tcg_temp_new_i64(); - TCGv_i64 rsh = tcg_temp_new_i64(); - TCGv_i64 zero = tcg_constant_i64(0); - TCGv_i64 max = tcg_constant_i64(63); - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_ext8s_i64(lsh, shift); - tcg_gen_neg_i64(rsh, lsh); - tcg_gen_shl_i64(lval, src, lsh); - tcg_gen_umin_i64(rsh, rsh, max); - tcg_gen_sar_i64(rval, src, rsh); - tcg_gen_movcond_i64(TCG_COND_LEU, lval, lsh, max, lval, zero); - tcg_gen_movcond_i64(TCG_COND_LT, dst, lsh, zero, rval, lval); -} - -static void gen_sshl_vec(unsigned vece, TCGv_vec dst, - TCGv_vec src, TCGv_vec shift) -{ - TCGv_vec lval = tcg_temp_new_vec_matching(dst); - TCGv_vec rval = tcg_temp_new_vec_matching(dst); - TCGv_vec lsh = tcg_temp_new_vec_matching(dst); - TCGv_vec rsh = tcg_temp_new_vec_matching(dst); - TCGv_vec tmp = tcg_temp_new_vec_matching(dst); - - /* - * Rely on the TCG guarantee that out of range shifts produce - * unspecified results, not undefined behaviour (i.e. no trap). - * Discard out-of-range results after the fact. - */ - tcg_gen_neg_vec(vece, rsh, shift); - if (vece == MO_8) { - tcg_gen_mov_vec(lsh, shift); - } else { - tcg_gen_dupi_vec(vece, tmp, 0xff); - tcg_gen_and_vec(vece, lsh, shift, tmp); - tcg_gen_and_vec(vece, rsh, rsh, tmp); - } - - /* Bound rsh so out of bound right shift gets -1. */ - tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1); - tcg_gen_umin_vec(vece, rsh, rsh, tmp); - tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp); - - tcg_gen_shlv_vec(vece, lval, src, lsh); - tcg_gen_sarv_vec(vece, rval, src, rsh); - - /* Select in-bound left shift. */ - tcg_gen_andc_vec(vece, lval, lval, tmp); - - /* Select between left and right shift. */ - if (vece == MO_8) { - tcg_gen_dupi_vec(vece, tmp, 0); - tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval); - } else { - tcg_gen_dupi_vec(vece, tmp, 0x80); - tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval); - } -} - -void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec, - INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_sshl_vec, - .fno = gen_helper_gvec_sshl_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fniv = gen_sshl_vec, - .fno = gen_helper_gvec_sshl_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_sshl_i32, - .fniv = gen_sshl_vec, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_sshl_i64, - .fniv = gen_sshl_vec, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, - TCGv_vec a, TCGv_vec b) -{ - TCGv_vec x = tcg_temp_new_vec_matching(t); - tcg_gen_add_vec(vece, x, a, b); - tcg_gen_usadd_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); -} - -void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen4 ops[4] = { - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_b, - .write_aofs = true, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_h, - .write_aofs = true, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_s, - .write_aofs = true, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_d, - .write_aofs = true, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, - TCGv_vec a, TCGv_vec b) -{ - TCGv_vec x = tcg_temp_new_vec_matching(t); - tcg_gen_add_vec(vece, x, a, b); - tcg_gen_ssadd_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); -} - -void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 - }; - static const GVecGen4 ops[4] = { - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_b, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_h, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_s, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_d, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_64 }, - }; - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, - TCGv_vec a, TCGv_vec b) -{ - TCGv_vec x = tcg_temp_new_vec_matching(t); - tcg_gen_sub_vec(vece, x, a, b); - tcg_gen_ussub_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); -} - -void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 - }; - static const GVecGen4 ops[4] = { - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_b, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_h, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_s, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_d, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_64 }, - }; - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, - TCGv_vec a, TCGv_vec b) -{ - TCGv_vec x = tcg_temp_new_vec_matching(t); - tcg_gen_sub_vec(vece, x, a, b); - tcg_gen_sssub_vec(vece, t, a, b); - tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); - tcg_gen_or_vec(vece, sat, sat, x); -} - -void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 - }; - static const GVecGen4 ops[4] = { - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_b, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_h, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_s, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_d, - .opt_opc = vecop_list, - .write_aofs = true, - .vece = MO_64 }, - }; - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_sabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 t = tcg_temp_new_i32(); - - tcg_gen_sub_i32(t, a, b); - tcg_gen_sub_i32(d, b, a); - tcg_gen_movcond_i32(TCG_COND_LT, d, a, b, d, t); -} - -static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_sub_i64(t, a, b); - tcg_gen_sub_i64(d, b, a); - tcg_gen_movcond_i64(TCG_COND_LT, d, a, b, d, t); -} - -static void gen_sabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - - tcg_gen_smin_vec(vece, t, a, b); - tcg_gen_smax_vec(vece, d, a, b); - tcg_gen_sub_vec(vece, d, d, t); -} - -void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sub_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_sabd_vec, - .fno = gen_helper_gvec_sabd_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fniv = gen_sabd_vec, - .fno = gen_helper_gvec_sabd_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_sabd_i32, - .fniv = gen_sabd_vec, - .fno = gen_helper_gvec_sabd_s, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_sabd_i64, - .fniv = gen_sabd_vec, - .fno = gen_helper_gvec_sabd_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_uabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 t = tcg_temp_new_i32(); - - tcg_gen_sub_i32(t, a, b); - tcg_gen_sub_i32(d, b, a); - tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, d, t); -} - -static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_sub_i64(t, a, b); - tcg_gen_sub_i64(d, b, a); - tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, d, t); -} - -static void gen_uabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - - tcg_gen_umin_vec(vece, t, a, b); - tcg_gen_umax_vec(vece, d, a, b); - tcg_gen_sub_vec(vece, d, d, t); -} - -void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sub_vec, INDEX_op_umin_vec, INDEX_op_umax_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_uabd_vec, - .fno = gen_helper_gvec_uabd_b, - .opt_opc = vecop_list, - .vece = MO_8 }, - { .fniv = gen_uabd_vec, - .fno = gen_helper_gvec_uabd_h, - .opt_opc = vecop_list, - .vece = MO_16 }, - { .fni4 = gen_uabd_i32, - .fniv = gen_uabd_vec, - .fno = gen_helper_gvec_uabd_s, - .opt_opc = vecop_list, - .vece = MO_32 }, - { .fni8 = gen_uabd_i64, - .fniv = gen_uabd_vec, - .fno = gen_helper_gvec_uabd_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 t = tcg_temp_new_i32(); - gen_sabd_i32(t, a, b); - tcg_gen_add_i32(d, d, t); -} - -static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - TCGv_i64 t = tcg_temp_new_i64(); - gen_sabd_i64(t, a, b); - tcg_gen_add_i64(d, d, t); -} - -static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - gen_sabd_vec(vece, t, a, b); - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sub_vec, INDEX_op_add_vec, - INDEX_op_smin_vec, INDEX_op_smax_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_saba_vec, - .fno = gen_helper_gvec_saba_b, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_8 }, - { .fniv = gen_saba_vec, - .fno = gen_helper_gvec_saba_h, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_saba_i32, - .fniv = gen_saba_vec, - .fno = gen_helper_gvec_saba_s, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_saba_i64, - .fniv = gen_saba_vec, - .fno = gen_helper_gvec_saba_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - -static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 t = tcg_temp_new_i32(); - gen_uabd_i32(t, a, b); - tcg_gen_add_i32(d, d, t); -} - -static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - TCGv_i64 t = tcg_temp_new_i64(); - gen_uabd_i64(t, a, b); - tcg_gen_add_i64(d, d, t); -} - -static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - TCGv_vec t = tcg_temp_new_vec_matching(d); - gen_uabd_vec(vece, t, a, b); - tcg_gen_add_vec(vece, d, d, t); -} - -void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { - INDEX_op_sub_vec, INDEX_op_add_vec, - INDEX_op_umin_vec, INDEX_op_umax_vec, 0 - }; - static const GVecGen3 ops[4] = { - { .fniv = gen_uaba_vec, - .fno = gen_helper_gvec_uaba_b, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_8 }, - { .fniv = gen_uaba_vec, - .fno = gen_helper_gvec_uaba_h, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_uaba_i32, - .fniv = gen_uaba_vec, - .fno = gen_helper_gvec_uaba_s, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_uaba_i64, - .fniv = gen_uaba_vec, - .fno = gen_helper_gvec_uaba_d, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list, - .load_dest = true, - .vece = MO_64 }, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); -} - static bool aa32_cpreg_encoding_in_impdef_space(uint8_t crn, uint8_t crm) { static const uint16_t mask[3] = { diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index 3b1a9f0fc5e..bdb5c7352f2 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -24,6 +24,7 @@ arm_ss.add(when: 'TARGET_AARCH64', if_true: gen_a64) arm_ss.add(files( 'cpu32.c', + 'gengvec.c', 'translate.c', 'translate-m-nocp.c', 'translate-mve.c', From patchwork Tue May 28 14:07:25 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799485 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257449wrz; Tue, 28 May 2024 07:13:08 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVBOJuI4IaYsubrKTuFfk59QqGYAVnfvc2gcldsJkCoXfhfdygDWSYWGPFEcnuXxcjgDCe64v/weSRaENAToeQo X-Google-Smtp-Source: AGHT+IEaGE4HzBw2fYB965hfmX4T0w+aWoi1RyvNNEb/PaGEZLswGK/KxLALRKZ6Q0Iq7zWllBHb X-Received: by 2002:a05:622a:587:b0:43a:f58b:2e71 with SMTP id d75a77b69052e-43fb0e4a8a3mr116269791cf.10.1716905588539; Tue, 28 May 2024 07:13:08 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905588; cv=none; d=google.com; s=arc-20160816; b=CNdBiIpS0bNSrUebzElHttDx6oJgf3NE2hiAxcdpw6kZXguPbtiiHi6vJcIYjNbPNr j/gONdQcbnnH16qcvWEBrAyZJUlnHZfVNoHaQmIKfzPvZfPBU2PQlyZ6W+9oXv57rHgh g0rAdo34efNK0ViSsIr9GSedQ5FURF/NEz8FeQr/EvpBgVhEFiCz4r5kz/xZZjkLAQZB 8//Wm8jrdTOEGffddsadPiO3MVhu2NhZftBp0OARPB0H865+hS4x7o95y90d4uQJst2p PzJ5k1lkiftxbs6YcIuA2ddDxjF5gx4dK7qkQLj2FpEeDCEh38vyf3W/rzre9YxiaF5G zDyg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=KpV1hGfKcjaIRpzJafDx+n88mRUQnurzIHBbhcYdDTQ=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=NyUaG/vgJ/uJ1S11RIUK0vhH6Y+hplZ0Umg6VelVR159Q69kjCDN3P1FtBx+RekX8A YmxUOnCWy1YXwLJD4k8xiFuf2bZntQ8xXFuSj+ZQL8k3gj5c4pgARhU2pdhAbBI1P7i8 8r6Rus87zF+RN0ET2Y+2lntQLvAmrGg4K33uUO2YTzSpO+5tTgNtMRnowKJJjg+1qnfN XP+fvuSCfkwDMU48wfmIvbQFmtJ9EOv5gk6roDfKfXBOZyGPDhBYMoxXeQmC9dSBrMg4 Glzpir4+GLkS1CvgmaUA9IhWgg5QhMUs3G0pL6XBqtdzGQ3zOiQ0suXgZdJn3KMrr0BL RPcw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=QoVjjtOQ; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18c493fsi102001011cf.558.2024.05.28.07.13.07 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:08 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=QoVjjtOQ; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUr-0001cO-QS; Tue, 28 May 2024 10:08:13 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUp-0001bI-70 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:11 -0400 Received: from mail-wr1-x42f.google.com ([2a00:1450:4864:20::42f]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUj-00073b-He for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: by mail-wr1-x42f.google.com with SMTP id ffacd0b85a97d-355080e6ff9so771287f8f.2 for ; Tue, 28 May 2024 07:08:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905284; x=1717510084; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=KpV1hGfKcjaIRpzJafDx+n88mRUQnurzIHBbhcYdDTQ=; b=QoVjjtOQ6SEL8nPoCIUSJIPnrz25Yw1QVyzaZNgFzRR4D8U4Hu9ns7YWuuPkfXxmNa y7Jl25hogmVlWiwaM7hAJmbFXDdKTPGKE7it9jJQIGDP5hfQbhkuRvcrG9osyFJ6Nbnr bwJpyN4K3gR1qHOPGtvr2cqDoA2GvVorgD5q7tw+5G+12R4RqurhRI/ufBSw5ycIxgz7 ilDHKj3WjZknHB/ySsEP2XypoNFrzefo5UFOuffIy2u5e9qJSNAyiYx63EVyUgiSeWAE 6Z5l/zHYwEgn5ts1GtfNx+GMpOYXbHUat4VaWrPqIZOCvrhIw+sQgH7/+R/vseUdEpsP I99w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905284; x=1717510084; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=KpV1hGfKcjaIRpzJafDx+n88mRUQnurzIHBbhcYdDTQ=; b=k6zI6/3S0B5GYVuvczlqTzVmfQf/zXIen58trrwbkBqETgl/NqbdlV3+3K/rkI/p6Q F6ih/sRehMaAJ9L3ZCpgQlsUmaNOmmGrDAcNaphQCFr2mAGYFhCBHSowfwRocRepa47P FSXDOsRNNLqyKQiutfxWtiUfzGryt1PyDr0FoXeIW402XDa/46BpHqZFKb6BrsgsRbJJ jlOAiC+5MUcIQBpZHPaFJ4yf8rkiXYxiZXPxKYlSyvL6IU1sE3PbfR/mnnN7XZr1I7CU TIiWJHHPW/p14QSDpoQy7mRMjT3cEj5w3zOb8UHAea2+rG7pZA0e7wfnJlMcQhm5Vy9z oSSg== X-Gm-Message-State: AOJu0Yyk3HQhEQfgb/4UU1TfCq8h+lnqf5H/SPIjLdoIscnft+AjExvb bsxxQYOhdJXYhG7WcqlDDjfsgj6ojU4YjgDHaOxk+dsmijymz4B52r3s9foCGTdJSf/2WGvUmsq Q X-Received: by 2002:a05:6000:2a5:b0:359:b737:68c9 with SMTP id ffacd0b85a97d-359b7376aa9mr3606009f8f.45.1716905284113; Tue, 28 May 2024 07:08:04 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.03 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:03 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 14/42] target/arm: Split out gengvec64.c Date: Tue, 28 May 2024 15:07:25 +0100 Message-Id: <20240528140753.3620597-15-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42f; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42f.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, T_SCC_BODY_TEXT_LINE=-0.01, T_SPF_TEMPERROR=0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Split some routines out of translate-a64.c and translate-sve.c that are used by both. Reviewed-by: Peter Maydell Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.h | 4 + target/arm/tcg/gengvec64.c | 190 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 26 ----- target/arm/tcg/translate-sve.c | 145 +------------------------ target/arm/tcg/meson.build | 1 + 5 files changed, 197 insertions(+), 169 deletions(-) create mode 100644 target/arm/tcg/gengvec64.c diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index 7b811b8ac51..91750f0ca91 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -193,6 +193,10 @@ void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz); +void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz); void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c new file mode 100644 index 00000000000..093b498b13d --- /dev/null +++ b/target/arm/tcg/gengvec64.c @@ -0,0 +1,190 @@ +/* + * AArch64 generic vector expansion + * + * Copyright (c) 2013 Alexander Graf + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see . + */ + +#include "qemu/osdep.h" +#include "translate.h" +#include "translate-a64.h" + + +static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) +{ + tcg_gen_rotli_i64(d, m, 1); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_rax1_vec(unsigned vece, TCGv_vec d, TCGv_vec n, TCGv_vec m) +{ + tcg_gen_rotli_vec(vece, d, m, 1); + tcg_gen_xor_vec(vece, d, d, n); +} + +void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3 op = { + .fni8 = gen_rax1_i64, + .fniv = gen_rax1_vec, + .opt_opc = vecop_list, + .fno = gen_helper_crypto_rax1, + .vece = MO_64, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &op); +} + +static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_8, 0xff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 8 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_xar16_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_16, 0xffff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 16 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); +} + +static void gen_xar_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, int32_t sh) +{ + tcg_gen_xor_i32(d, n, m); + tcg_gen_rotri_i32(d, d, sh); +} + +static void gen_xar_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_rotri_i64(d, d, sh); +} + +static void gen_xar_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, int64_t sh) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_rotri_vec(vece, d, d, sh); +} + +void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, int64_t shift, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3i ops[4] = { + { .fni8 = gen_xar8_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fni8 = gen_xar16_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_xar_i32, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_xar_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_gvec_xar_d, + .opt_opc = vecop, + .vece = MO_64 } + }; + int esize = 8 << vece; + + /* The SVE2 range is 1 .. esize; the AdvSIMD range is 0 .. esize-1. */ + tcg_debug_assert(shift >= 0); + tcg_debug_assert(shift <= esize); + shift &= esize - 1; + + if (shift == 0) { + /* xar with no rotate devolves to xor. */ + tcg_gen_gvec_xor(vece, rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_3i(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, + shift, &ops[vece]); + } +} + +static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_xor_i64(d, d, k); +} + +static void gen_eor3_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_xor_vec(vece, d, d, k); +} + +void gen_gvec_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_eor3_i64, + .fniv = gen_eor3_vec, + .fno = gen_helper_sve2_eor3, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_andc_i64(d, m, k); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_bcax_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_andc_vec(vece, d, m, k); + tcg_gen_xor_vec(vece, d, d, n); +} + +void gen_gvec_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bcax_i64, + .fniv = gen_bcax_vec, + .fno = gen_helper_sve2_bcax, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 0bdddb8517a..8842ff634d5 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -13623,32 +13623,6 @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) gen_gvec_op2_ool(s, true, rd, rn, 0, genfn); } -static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) -{ - tcg_gen_rotli_i64(d, m, 1); - tcg_gen_xor_i64(d, d, n); -} - -static void gen_rax1_vec(unsigned vece, TCGv_vec d, TCGv_vec n, TCGv_vec m) -{ - tcg_gen_rotli_vec(vece, d, m, 1); - tcg_gen_xor_vec(vece, d, d, n); -} - -void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop_list[] = { INDEX_op_rotli_vec, 0 }; - static const GVecGen3 op = { - .fni8 = gen_rax1_i64, - .fniv = gen_rax1_vec, - .opt_opc = vecop_list, - .fno = gen_helper_crypto_rax1, - .vece = MO_64, - }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &op); -} - /* Crypto three-reg SHA512 * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 * +-----------------------+------+---+---+-----+--------+------+------+ diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index ada05aa5302..798ab2bfb13 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -527,94 +527,6 @@ TRANS_FEAT(ORR_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_or, a) TRANS_FEAT(EOR_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_xor, a) TRANS_FEAT(BIC_zzz, aa64_sve, gen_gvec_fn_arg_zzz, tcg_gen_gvec_andc, a) -static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - uint64_t mask = dup_const(MO_8, 0xff >> sh); - - tcg_gen_xor_i64(t, n, m); - tcg_gen_shri_i64(d, t, sh); - tcg_gen_shli_i64(t, t, 8 - sh); - tcg_gen_andi_i64(d, d, mask); - tcg_gen_andi_i64(t, t, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_xar16_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) -{ - TCGv_i64 t = tcg_temp_new_i64(); - uint64_t mask = dup_const(MO_16, 0xffff >> sh); - - tcg_gen_xor_i64(t, n, m); - tcg_gen_shri_i64(d, t, sh); - tcg_gen_shli_i64(t, t, 16 - sh); - tcg_gen_andi_i64(d, d, mask); - tcg_gen_andi_i64(t, t, ~mask); - tcg_gen_or_i64(d, d, t); -} - -static void gen_xar_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, int32_t sh) -{ - tcg_gen_xor_i32(d, n, m); - tcg_gen_rotri_i32(d, d, sh); -} - -static void gen_xar_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) -{ - tcg_gen_xor_i64(d, n, m); - tcg_gen_rotri_i64(d, d, sh); -} - -static void gen_xar_vec(unsigned vece, TCGv_vec d, TCGv_vec n, - TCGv_vec m, int64_t sh) -{ - tcg_gen_xor_vec(vece, d, n, m); - tcg_gen_rotri_vec(vece, d, d, sh); -} - -void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, int64_t shift, - uint32_t opr_sz, uint32_t max_sz) -{ - static const TCGOpcode vecop[] = { INDEX_op_rotli_vec, 0 }; - static const GVecGen3i ops[4] = { - { .fni8 = gen_xar8_i64, - .fniv = gen_xar_vec, - .fno = gen_helper_sve2_xar_b, - .opt_opc = vecop, - .vece = MO_8 }, - { .fni8 = gen_xar16_i64, - .fniv = gen_xar_vec, - .fno = gen_helper_sve2_xar_h, - .opt_opc = vecop, - .vece = MO_16 }, - { .fni4 = gen_xar_i32, - .fniv = gen_xar_vec, - .fno = gen_helper_sve2_xar_s, - .opt_opc = vecop, - .vece = MO_32 }, - { .fni8 = gen_xar_i64, - .fniv = gen_xar_vec, - .fno = gen_helper_gvec_xar_d, - .opt_opc = vecop, - .vece = MO_64 } - }; - int esize = 8 << vece; - - /* The SVE2 range is 1 .. esize; the AdvSIMD range is 0 .. esize-1. */ - tcg_debug_assert(shift >= 0); - tcg_debug_assert(shift <= esize); - shift &= esize - 1; - - if (shift == 0) { - /* xar with no rotate devolves to xor. */ - tcg_gen_gvec_xor(vece, rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz); - } else { - tcg_gen_gvec_3i(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, - shift, &ops[vece]); - } -} - static bool trans_XAR(DisasContext *s, arg_rrri_esz *a) { if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { @@ -629,61 +541,8 @@ static bool trans_XAR(DisasContext *s, arg_rrri_esz *a) return true; } -static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) -{ - tcg_gen_xor_i64(d, n, m); - tcg_gen_xor_i64(d, d, k); -} - -static void gen_eor3_vec(unsigned vece, TCGv_vec d, TCGv_vec n, - TCGv_vec m, TCGv_vec k) -{ - tcg_gen_xor_vec(vece, d, n, m); - tcg_gen_xor_vec(vece, d, d, k); -} - -static void gen_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, - uint32_t a, uint32_t oprsz, uint32_t maxsz) -{ - static const GVecGen4 op = { - .fni8 = gen_eor3_i64, - .fniv = gen_eor3_vec, - .fno = gen_helper_sve2_eor3, - .vece = MO_64, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - }; - tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); -} - -TRANS_FEAT(EOR3, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_eor3, a) - -static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) -{ - tcg_gen_andc_i64(d, m, k); - tcg_gen_xor_i64(d, d, n); -} - -static void gen_bcax_vec(unsigned vece, TCGv_vec d, TCGv_vec n, - TCGv_vec m, TCGv_vec k) -{ - tcg_gen_andc_vec(vece, d, m, k); - tcg_gen_xor_vec(vece, d, d, n); -} - -static void gen_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, - uint32_t a, uint32_t oprsz, uint32_t maxsz) -{ - static const GVecGen4 op = { - .fni8 = gen_bcax_i64, - .fniv = gen_bcax_vec, - .fno = gen_helper_sve2_bcax, - .vece = MO_64, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - }; - tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); -} - -TRANS_FEAT(BCAX, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_bcax, a) +TRANS_FEAT(EOR3, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_gvec_eor3, a) +TRANS_FEAT(BCAX, aa64_sve2, gen_gvec_fn_arg_zzzz, gen_gvec_bcax, a) static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, uint32_t a, uint32_t oprsz, uint32_t maxsz) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index bdb5c7352f2..508932a249f 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -43,6 +43,7 @@ arm_ss.add(files( arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'cpu64.c', + 'gengvec64.c', 'translate-a64.c', 'translate-sve.c', 'translate-sme.c', From patchwork Tue May 28 14:07:26 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799495 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257880wrz; Tue, 28 May 2024 07:13:54 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVlIZ2Vrbf+1fnC1AbiM7yprcwVokN+xl/xLygj/tBMlfxLngqFsDfzkxANOW6Yd5xerEWSlj4dpYHuqBOEIU8P X-Google-Smtp-Source: AGHT+IEuGOSJIXQYsjFWdsSIPlAckUuo/rEBWIHONU5W7mqmKSBDed8rLjiaeP4mI2aQ3+OlYmmP X-Received: by 2002:a05:6820:1620:b0:5b8:80f1:8f3 with SMTP id 006d021491bc7-5b9bdcffb68mr3547355eaf.1.1716905634076; Tue, 28 May 2024 07:13:54 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905634; cv=none; d=google.com; s=arc-20160816; b=WTY9RStLEceio9xG6jNy5PYJxyfvRDU4SfLZvrY0Dhs57pZblycw3gJq2NmX9MKSK7 E2VYx68esMqUklCqPhhk7/jvcL6iOHnIqG1KvSsoAEaKoU3xQTuqZL7TUf8nAMS4jcSo RgMHge5I64VL4Mc1T8nuCuLWGO3b4NYT2PuSwWJGqTCwHJ9O4uLgXPnoeIjXR7+ymZ7Y ijwVZRHhIt0aFUeJ/IT3Y8unkB57wvuVOp3SQYiN+vIOlghvqCUqLc3o29xJbGpj/c34 GYWbECsFgmttGNCPY6u16y+b6HFp3MREkvFvLpjJF/xphRxxBiZNTpd3EBFEobSmUvjm 9zyQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=m26zEpA71QDIamA2ozgsiGZ5k+PMbcICXgXPxohnPH0=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=d8AaVTOiOazeJr6S3p/0vvcq+I0dKEVBWLHf13bdt0luIWa1zasMq1YfASdA68jT1g ty6YXWhgqbl0PEMJWVuS1UZMQEw19vZ17Zl8Ker3SGFqrBq89SwC7v2KjRmHhCst4NRj POPr000EiS8Pn6CCMQDgenFiyBuk1LWaHhLevQ++Ia7eMLhFbFCf8nWvIQSec47Sb//D lCmXg/INA+iTzQD2QeMhMmKS3wwVRSLujNgXFEBob9HEGDTekCpMX6t7DqYas3EcF2/G QaioE6WrbJIlJ4zXfLh1CLrwjONBROcbhsyRhz/C5Suv9rZyoHyOzyZemPaJ2Eqax2O+ JCmA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=cbzXETg1; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 71dfb90a1353d-4e65b81034bsi1213449e0c.71.2024.05.28.07.13.53 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:54 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=cbzXETg1; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUn-0001aY-JB; Tue, 28 May 2024 10:08:09 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUm-0001Zr-Hp for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:08 -0400 Received: from mail-wm1-x334.google.com ([2a00:1450:4864:20::334]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUk-00073h-Hd for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:08 -0400 Received: by mail-wm1-x334.google.com with SMTP id 5b1f17b1804b1-4211b3c0ef3so6336065e9.0 for ; Tue, 28 May 2024 07:08:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905284; x=1717510084; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=m26zEpA71QDIamA2ozgsiGZ5k+PMbcICXgXPxohnPH0=; b=cbzXETg1P9H3qPdRDlZhePbFUcdlypxwgCESorsbgix1/wtedfQ7M1TrsGykmPYJLF xXJsS+h3robptDieJaBlgvveYkXMRpIyJb9EET6y75d19q1fI9mPfcj5FQaLJZrooC8X UVhkNAhYLgEF/3f78a/zQUS+8LqmXrvv6t1T6voxAoIdp0i/U6Z49N8pDi41ktq+2cRS iERkVP5F0N8/mM+ODpB45I657MVptdml0kYI7HCgs2sFYEQsHeo7rdfhTYIy4zLGL7Br mRll90sLmLFihzwmd7IizPiGHPnedNTjONhVadbH1NqeWGlqpZ3CHqtFLISuB3f89Dga LDDg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905284; x=1717510084; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=m26zEpA71QDIamA2ozgsiGZ5k+PMbcICXgXPxohnPH0=; b=mTaRtnBL/9jTUMX5SAldiNcEN80MAyYvINFGiPk6A7HvY7VV6IwiHV5gobORDYotr2 8b17h5iVVyjTgUT/GFWVkV0MWGuRnfFu+by+1aRbXewgssBcqx2S1ayzMnMgVyXAdXfG XD9fXVlA9tEfpEesKNv7DWpGji6WjNlN2mC2viOoDwD6fyqKRMEsvYOIN0Li/SwXk+YK NGbeX/pqDtFVpmtZ8VARI0P6W2tP1yxci8MdumHCFggTY+WRB8+gsgaYqoV+NF5sUKdY KYr39i7ZYFuTZ6N/zW3SZj5mMIedp/KKJVcaeSUbw/9oBvUiPaYFX3gGlNT/+3gyslud hPtQ== X-Gm-Message-State: AOJu0Yyyc4R0mYb6sSP8fjIiW95bexOyr/xJgC8GQlA8R2We0DqKkXDU Ba92qMFBBRVHE/JvF/LXLFRuOM8fShul5w63ij8fg5JTacCKgK0yQYVVn+gVG4T2UbPXNgG2pg2 / X-Received: by 2002:a5d:4e43:0:b0:354:f9f0:a7ed with SMTP id ffacd0b85a97d-3552fdfa5d4mr7701946f8f.47.1716905284572; Tue, 28 May 2024 07:08:04 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.04 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:04 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 15/42] target/arm: Convert Cryptographic AES to decodetree Date: Tue, 28 May 2024 15:07:26 +0100 Message-Id: <20240528140753.3620597-16-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::334; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x334.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 21 +++++++-- target/arm/tcg/translate-a64.c | 86 +++++++++++++++------------------- 2 files changed, 54 insertions(+), 53 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 0e7656fd158..1de09903dc4 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -19,11 +19,17 @@ # This file is processed by scripts/decodetree.py # -&r rn -&ri rd imm -&rri_sf rd rn imm sf -&i imm +%rd 0:5 +&r rn +&ri rd imm +&rri_sf rd rn imm sf +&i imm +&qrr_e q rd rn esz +&qrrr_e q rd rn rm esz + +@rr_q1e0 ........ ........ ...... rn:5 rd:5 &qrr_e q=1 esz=0 +@r2r_q1e0 ........ ........ ...... rm:5 rd:5 &qrrr_e rn=%rd q=1 esz=0 ### Data Processing - Immediate @@ -590,3 +596,10 @@ CPYFE 00 011 0 01100 ..... .... 01 ..... ..... @cpy CPYP 00 011 1 01000 ..... .... 01 ..... ..... @cpy CPYM 00 011 1 01010 ..... .... 01 ..... ..... @cpy CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy + +### Cryptographic AES + +AESE 01001110 00 10100 00100 10 ..... ..... @r2r_q1e0 +AESD 01001110 00 10100 00101 10 ..... ..... @r2r_q1e0 +AESMC 01001110 00 10100 00110 10 ..... ..... @rr_q1e0 +AESIMC 01001110 00 10100 00111 10 ..... ..... @rr_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 8842ff634d5..3894db4bee2 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1313,6 +1313,34 @@ bool sme_enabled_check_with_svcr(DisasContext *s, unsigned req) return true; } +/* + * Expanders for AdvSIMD translation functions. + */ + +static bool do_gvec_op2_ool(DisasContext *s, arg_qrr_e *a, int data, + gen_helper_gvec_2 *fn) +{ + if (!a->q && a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_op2_ool(s, a->q, a->rd, a->rn, data, fn); + } + return true; +} + +static bool do_gvec_op3_ool(DisasContext *s, arg_qrrr_e *a, int data, + gen_helper_gvec_3 *fn) +{ + if (!a->q && a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_op3_ool(s, a->q, a->rd, a->rn, a->rm, data, fn); + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the @@ -4560,6 +4588,15 @@ static bool trans_EXTR(DisasContext *s, arg_extract *a) return true; } +/* + * Cryptographic AES + */ + +TRANS_FEAT(AESE, aa64_aes, do_gvec_op3_ool, a, 0, gen_helper_crypto_aese) +TRANS_FEAT(AESD, aa64_aes, do_gvec_op3_ool, a, 0, gen_helper_crypto_aesd) +TRANS_FEAT(AESMC, aa64_aes, do_gvec_op2_ool, a, 0, gen_helper_crypto_aesmc) +TRANS_FEAT(AESIMC, aa64_aes, do_gvec_op2_ool, a, 0, gen_helper_crypto_aesimc) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13460,54 +13497,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto AES - * 31 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +-----------------+------+-----------+--------+-----+------+------+ - * | 0 1 0 0 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 | Rn | Rd | - * +-----------------+------+-----------+--------+-----+------+------+ - */ -static void disas_crypto_aes(DisasContext *s, uint32_t insn) -{ - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 12, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - gen_helper_gvec_2 *genfn2 = NULL; - gen_helper_gvec_3 *genfn3 = NULL; - - if (!dc_isar_feature(aa64_aes, s) || size != 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0x4: /* AESE */ - genfn3 = gen_helper_crypto_aese; - break; - case 0x6: /* AESMC */ - genfn2 = gen_helper_crypto_aesmc; - break; - case 0x5: /* AESD */ - genfn3 = gen_helper_crypto_aesd; - break; - case 0x7: /* AESIMC */ - genfn2 = gen_helper_crypto_aesimc; - break; - default: - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - if (genfn2) { - gen_gvec_op2_ool(s, true, rd, rn, 0, genfn2); - } else { - gen_gvec_op3_ool(s, true, rd, rd, rn, 0, genfn3); - } -} - /* Crypto three-reg SHA * 31 24 23 22 21 20 16 15 14 12 11 10 9 5 4 0 * +-----------------+------+---+------+---+--------+-----+------+------+ @@ -13917,7 +13906,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0x4e280800, 0xff3e0c00, disas_crypto_aes }, { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha }, { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha }, { 0xce608000, 0xffe0b000, disas_crypto_three_reg_sha512 }, From patchwork Tue May 28 14:07:27 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799471 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256273wrz; Tue, 28 May 2024 07:11:14 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCU0B5ZUpN00t28Vy8DWlwxwE+u6HMq4+Z52ga8GvjLl7FWlpqLOG56v6Qrqh/EpkECFlfbKubRyjvDOO9YdhFQz X-Google-Smtp-Source: AGHT+IHEfFie5s7k73Wqy9TRrLVFaUy3yXlZvlbCjp6MdPAQGnSj0YmEKEL76erlo6jI160bkgc1 X-Received: by 2002:a05:622a:51:b0:43e:17e6:606f with SMTP id d75a77b69052e-43fb0f1ddb4mr138664431cf.67.1716905474163; Tue, 28 May 2024 07:11:14 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905474; cv=none; d=google.com; s=arc-20160816; b=04HsN3E975iIs3CQHE+b/Mm50aYUQCF/oVh3UIE4d0gGmRPBNTUiY6Iy7uIzXC8YtZ pErk+eaO2GBhtVTli3/ElRVSerL87cX6eyY3Q+ffpTgkiuy6Sn6gFl5vtVL7r8hylk45 T9BFPTcRLYGzsWkhjuKSD2Mx9ArMBE3wXtDyDscAEWS1M5JoBj5M0f4miJS6M4cWSn5o E/+/3y/Px/97Zn2BDkuyfdukbNv85FcYGbF9FbeV0//+wh065dQczr7U5rJ2zM4sCgRm QJekd1v3ka47+BCcdmA7hlXrg5weEEa5PWUNq+ZU9bwa63FSHusx7abdo6zS+B8qJWtU H/3g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=VyVyKHqgPj/49154pa++4vUGSFOhznrmsFlJvMnj4KY=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=SJ0HCFtGku0e31Ih7xg7CxqULh1iWvof05MshUp6XxZ/fxgkDgsG0bVWnvV8vYUeJG ZZlCZD6yP4pitV2xtyZ5JISPgeQWItUGJCjDayR1YXwyKyEh8L45Bp9Tg3DsgULegpgl 4YK7K+tR37RGv456xxvE7IVNB1EmYhF5FukJ8xxj02V9/E7F5uyrCInP92PiA4wEXw53 SVC6Nt6V40LOA3JAG3LHO9v6ONkR8z7UxTmF4hU15Mel3FUouVFitjZOTSSIFQbQYZ0z hAXIQ46gA3Z9D13mUDXuvOHM+0kqNsMibBH2QeySuauGYfMaGK43YreG/GVlkyEMQHJ/ 7BwQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=S3ebgitn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb17bd637si106036881cf.104.2024.05.28.07.11.13 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:11:14 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=S3ebgitn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUp-0001bZ-W5; Tue, 28 May 2024 10:08:12 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUo-0001ag-63 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: from mail-wr1-x430.google.com ([2a00:1450:4864:20::430]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUl-00073p-He for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:09 -0400 Received: by mail-wr1-x430.google.com with SMTP id ffacd0b85a97d-355080e6ff9so771308f8f.2 for ; Tue, 28 May 2024 07:08:06 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905285; x=1717510085; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=VyVyKHqgPj/49154pa++4vUGSFOhznrmsFlJvMnj4KY=; b=S3ebgitnQEWCAFTCU5LSvtD+3Ii+ZM6XKuI+anIx9MjhMsESPXp9299Q2WSrRjrBRT EO2yJ5hACLdObBIdoGDDptmamG+GgovXuf87gCyhT40cxDXvOKbvw92zGOcExMV2HUFK P9n4vtUErRMHQPYXcvxCzQxtq0DcIh85saxmDufh9diIBZNmW7dXFldkpMw7cU1AOQK9 XQRyJwqgpAvC8essKFM3rDNslqVFse565KiB5v0yH1VZwLmQcI0hMiOf6YH6SodEFvp0 R0+PGAah8MuaMcX6zomdmjcgHmLG7YF0dY7+EKhJnl49+H+0zctcyPNcHLtT7a6e2X6o gH+A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905285; x=1717510085; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VyVyKHqgPj/49154pa++4vUGSFOhznrmsFlJvMnj4KY=; b=roW9arCsvV5b4rKiU8+I6ha58EHMfW7Zq2Hugc24SGGjMbuUagWVXc6wnekMiQ+ukn vh0pRXpwaG2W2ww2I7lVjVZ6sZwJ7+Ds13+iyi6YVjLGAwewGy3Om6QMVR7Y0paIFQgv nwMzaB4uATb6suEiPUA0ng9bmAJxauWKV8RjlueBqiFTxYteX4F+V8gCWGa8h0cv/LoA pdVmRZB6OMr1vhZFgquMs3sXede0Gq3JcqYNK5p0g6jGVhCfVJdaqSEmzLPJkahxPAjw 0j90zpRac2mhJUfWhG3C1S4pcqRojHAW1eXGq58MBqVl6Bsmhs+qzke/Q+Uobw9eo8V/ kWCg== X-Gm-Message-State: AOJu0Yz9KSktCRvOzv+aGIFd6RbZQmoTbzxaWHXpUlnRA/TBZP5KpZMA JKLeTvL6zlkMAiUPdwaZyzleHRNa/M3Lh+x1MV6h5YVxRAu0zvmtx9dqe6bIEY4il7rsSv2JF/U Y X-Received: by 2002:a5d:4f04:0:b0:351:c7c7:985f with SMTP id ffacd0b85a97d-3552fe19145mr8542101f8f.53.1716905285246; Tue, 28 May 2024 07:08:05 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.04 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:04 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 16/42] target/arm: Convert Cryptographic 3-register SHA to decodetree Date: Tue, 28 May 2024 15:07:27 +0100 Message-Id: <20240528140753.3620597-17-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::430; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x430.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 11 +++++ target/arm/tcg/translate-a64.c | 78 +++++----------------------------- 2 files changed, 21 insertions(+), 68 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 1de09903dc4..7590659ee68 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -30,6 +30,7 @@ @rr_q1e0 ........ ........ ...... rn:5 rd:5 &qrr_e q=1 esz=0 @r2r_q1e0 ........ ........ ...... rm:5 rd:5 &qrrr_e rn=%rd q=1 esz=0 +@rrr_q1e0 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=0 ### Data Processing - Immediate @@ -603,3 +604,13 @@ AESE 01001110 00 10100 00100 10 ..... ..... @r2r_q1e0 AESD 01001110 00 10100 00101 10 ..... ..... @r2r_q1e0 AESMC 01001110 00 10100 00110 10 ..... ..... @rr_q1e0 AESIMC 01001110 00 10100 00111 10 ..... ..... @rr_q1e0 + +### Cryptographic three-register SHA + +SHA1C 0101 1110 000 ..... 000000 ..... ..... @rrr_q1e0 +SHA1P 0101 1110 000 ..... 000100 ..... ..... @rrr_q1e0 +SHA1M 0101 1110 000 ..... 001000 ..... ..... @rrr_q1e0 +SHA1SU0 0101 1110 000 ..... 001100 ..... ..... @rrr_q1e0 +SHA256H 0101 1110 000 ..... 010000 ..... ..... @rrr_q1e0 +SHA256H2 0101 1110 000 ..... 010100 ..... ..... @rrr_q1e0 +SHA256SU1 0101 1110 000 ..... 011000 ..... ..... @rrr_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 3894db4bee2..5bef39d4e7d 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4589,7 +4589,7 @@ static bool trans_EXTR(DisasContext *s, arg_extract *a) } /* - * Cryptographic AES + * Cryptographic AES, SHA */ TRANS_FEAT(AESE, aa64_aes, do_gvec_op3_ool, a, 0, gen_helper_crypto_aese) @@ -4597,6 +4597,15 @@ TRANS_FEAT(AESD, aa64_aes, do_gvec_op3_ool, a, 0, gen_helper_crypto_aesd) TRANS_FEAT(AESMC, aa64_aes, do_gvec_op2_ool, a, 0, gen_helper_crypto_aesmc) TRANS_FEAT(AESIMC, aa64_aes, do_gvec_op2_ool, a, 0, gen_helper_crypto_aesimc) +TRANS_FEAT(SHA1C, aa64_sha1, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha1c) +TRANS_FEAT(SHA1P, aa64_sha1, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha1p) +TRANS_FEAT(SHA1M, aa64_sha1, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha1m) +TRANS_FEAT(SHA1SU0, aa64_sha1, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha1su0) + +TRANS_FEAT(SHA256H, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256h) +TRANS_FEAT(SHA256H2, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256h2) +TRANS_FEAT(SHA256SU1, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256su1) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13497,72 +13506,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto three-reg SHA - * 31 24 23 22 21 20 16 15 14 12 11 10 9 5 4 0 - * +-----------------+------+---+------+---+--------+-----+------+------+ - * | 0 1 0 1 1 1 1 0 | size | 0 | Rm | 0 | opcode | 0 0 | Rn | Rd | - * +-----------------+------+---+------+---+--------+-----+------+------+ - */ -static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) -{ - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 12, 3); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - gen_helper_gvec_3 *genfn; - bool feature; - - if (size != 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0: /* SHA1C */ - genfn = gen_helper_crypto_sha1c; - feature = dc_isar_feature(aa64_sha1, s); - break; - case 1: /* SHA1P */ - genfn = gen_helper_crypto_sha1p; - feature = dc_isar_feature(aa64_sha1, s); - break; - case 2: /* SHA1M */ - genfn = gen_helper_crypto_sha1m; - feature = dc_isar_feature(aa64_sha1, s); - break; - case 3: /* SHA1SU0 */ - genfn = gen_helper_crypto_sha1su0; - feature = dc_isar_feature(aa64_sha1, s); - break; - case 4: /* SHA256H */ - genfn = gen_helper_crypto_sha256h; - feature = dc_isar_feature(aa64_sha256, s); - break; - case 5: /* SHA256H2 */ - genfn = gen_helper_crypto_sha256h2; - feature = dc_isar_feature(aa64_sha256, s); - break; - case 6: /* SHA256SU1 */ - genfn = gen_helper_crypto_sha256su1; - feature = dc_isar_feature(aa64_sha256, s); - break; - default: - unallocated_encoding(s); - return; - } - - if (!feature) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); -} - /* Crypto two-reg SHA * 31 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----------------+------+-----------+--------+-----+------+------+ @@ -13906,7 +13849,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha }, { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha }, { 0xce608000, 0xffe0b000, disas_crypto_three_reg_sha512 }, { 0xcec08000, 0xfffff000, disas_crypto_two_reg_sha512 }, From patchwork Tue May 28 14:07:28 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799486 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257479wrz; Tue, 28 May 2024 07:13:12 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWVttT9Rm+pi7tRmGn/H4IrU+ywFcU8CR246/7h8DkhSTawgKq4nFJ6mjfk2BE/KkijYIoMoQBWsEFxaO2++mKj X-Google-Smtp-Source: AGHT+IEkznP5GVYFJy7QEVcubQUWesdJLCos60lXFkbQtO1HpjfqNO2tLcjMws2E8gfXP6GdnCIU X-Received: by 2002:a67:ba12:0:b0:47b:fe0b:a92e with SMTP id ada2fe7eead31-48a3856aac5mr13909848137.16.1716905591961; Tue, 28 May 2024 07:13:11 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905591; cv=none; d=google.com; s=arc-20160816; b=Z/mrftVvFsQDfTAp8T0OA1pJL4lLbaufaqig54shHgt95m+mOIVj+b9LLH8t9nLGvR tuey+hc1XCNd+b04mjCCjju+GB3lsW41u5+N87hFl5Fxa6umEodPCGieE7kiS512+aZ8 ZfyB8k1e8SwA6+vEkhUCJAnJkl9tg5mhEcsp6rj78VgVyzezU1rFglTiD09qIHVZFk9e BvgUb+Gj+r964nA2r5g7Z4b4pO9OOakzbglZ9PPFsw8rdIA+1Dc/LEsHwj88Eh8JWAjE l+oRxfrWP9hkZQU1BYmv7SLzKhSp02kxu75F0Nrw3yJVeVLYpcFuExKkOsaRx7KOByKZ 1rMQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=lODoRdU3R+1K0U+odF5v8UJ1tylJpMXFPv+66x4TqM0=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=Gr3wT7m+41NjQB/qYX5SdZQZWGzTo2dMqf/WSPeIoyv8UvnBktnj+ePH3BZX+YG1I2 o2vdyO+dkDP8iIqr/aGCSkoPIseM718ueGt0MpgsCxPc9giJQnLaJopPY2gVQgIpD3Vg kRkciRzI70cvFyI0atrpQN6Q9qgPD45F+m+sbRIcWxFWGeUafTxqgu+/Ww2ecrffF6hd OkQ0mqrbxnAd8+lyCTDHZ2Dui0hhQeuk8PcENh4AS0+SBW8+eNY9laANh0k24w8GwW7y Ua5S6xH6xC9w0aHkJIS+Bb4XS/YnKrnX5/V02dxyrfbrJvoCOdA4f/mp1ne9cxyXrlYc vE8A==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=qXgf2nP6; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a34be28si1791183137.447.2024.05.28.07.13.11 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:11 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=qXgf2nP6; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUq-0001bi-NO; Tue, 28 May 2024 10:08:12 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUp-0001bL-BZ for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:11 -0400 Received: from mail-wr1-x42a.google.com ([2a00:1450:4864:20::42a]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUm-000741-4E for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:11 -0400 Received: by mail-wr1-x42a.google.com with SMTP id ffacd0b85a97d-3564a0bea19so826543f8f.2 for ; Tue, 28 May 2024 07:08:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905286; x=1717510086; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=lODoRdU3R+1K0U+odF5v8UJ1tylJpMXFPv+66x4TqM0=; b=qXgf2nP6zPJiYpfhcZOn7ztIjONqmYbY8pH8adb6xQEQahAMPpUce8bnqlXjg3Z00f 4k1LLGTxdi9yC/Y7NBIOPydEIcclw0fXUEb1M94Kv7ZUK+03C36V+NLEYrLVgMiPcnb0 VlfwrIPfJnSPVugPRdFopxdWpnXNnb5HeADpkw8KMdfwKECcBFniOMOlMTTtvAjDBfOy 7quRz69qVHPuyVqCMrtv3Qy2bVl4hkw5BY3LY+4oe9fRwrQ5Ru9kcMRA12/yPBQyxl9n G+RdzM80dzNMPzs4BHXlzlMhnw7VdU9+lsfR9ZRu166yc1rKoMO7kvcPME+aDIoR5xix /P8g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905286; x=1717510086; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=lODoRdU3R+1K0U+odF5v8UJ1tylJpMXFPv+66x4TqM0=; b=Ghu4UPeEeMaVGlVMydTbxw5YqHuis9jQ1we4CGAAkh+Nv+eF17d0tl5bC+Xhm3YxTg ZxwaFOyDNTtHAZ0vI4XGM6oU+AMJSAxztoJMPs02t9nUMspqkXxQIh4UwJkF5aDrpH0A wdJXgzgdfgf5kPYKaSdPllOvgqIrsTQCqshQ+ITwQTof9AVFN0/L+3+/SBEqP050l7YX lFl6unah+ONZ1+gtQsTjlXmd12Zu4wH3/ShBlcBjEoyJ+LmMpKKPmBrJnfrzbSwAtb8B J1qOMjHHOsEbGjPndGv3n68JQsigY8cVkmOEVjXfGKVuhnRZVLEIGAcibYjWu+nWUhSo BmlQ== X-Gm-Message-State: AOJu0YypZ/IdeGntqLC/Hnn5vCWGxIciWoSPHthGRt6Z151v31VkPEs9 H/X1gIOLWPsgnMY6Z/9HCopkgLhWFpf5f+7kx3fFJlR2AvcwlgAFr0L9unf9sz9oLpEbi+G7PC2 B X-Received: by 2002:adf:fa44:0:b0:354:fa0d:1427 with SMTP id ffacd0b85a97d-35526c25695mr12497787f8f.15.1716905285750; Tue, 28 May 2024 07:08:05 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.05 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:05 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 17/42] target/arm: Convert Cryptographic 2-register SHA to decodetree Date: Tue, 28 May 2024 15:07:28 +0100 Message-Id: <20240528140753.3620597-18-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42a; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42a.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 6 ++++ target/arm/tcg/translate-a64.c | 54 +++------------------------------- 2 files changed, 10 insertions(+), 50 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7590659ee68..350afabc779 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -614,3 +614,9 @@ SHA1SU0 0101 1110 000 ..... 001100 ..... ..... @rrr_q1e0 SHA256H 0101 1110 000 ..... 010000 ..... ..... @rrr_q1e0 SHA256H2 0101 1110 000 ..... 010100 ..... ..... @rrr_q1e0 SHA256SU1 0101 1110 000 ..... 011000 ..... ..... @rrr_q1e0 + +### Cryptographic two-register SHA + +SHA1H 0101 1110 0010 1000 0000 10 ..... ..... @rr_q1e0 +SHA1SU1 0101 1110 0010 1000 0001 10 ..... ..... @rr_q1e0 +SHA256SU0 0101 1110 0010 1000 0010 10 ..... ..... @rr_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 5bef39d4e7d..1d20bf0c35b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4606,6 +4606,10 @@ TRANS_FEAT(SHA256H, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256 TRANS_FEAT(SHA256H2, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256h2) TRANS_FEAT(SHA256SU1, aa64_sha256, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha256su1) +TRANS_FEAT(SHA1H, aa64_sha1, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha1h) +TRANS_FEAT(SHA1SU1, aa64_sha1, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha1su1) +TRANS_FEAT(SHA256SU0, aa64_sha256, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha256su0) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13506,55 +13510,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto two-reg SHA - * 31 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +-----------------+------+-----------+--------+-----+------+------+ - * | 0 1 0 1 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 | Rn | Rd | - * +-----------------+------+-----------+--------+-----+------+------+ - */ -static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) -{ - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 12, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - gen_helper_gvec_2 *genfn; - bool feature; - - if (size != 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0: /* SHA1H */ - feature = dc_isar_feature(aa64_sha1, s); - genfn = gen_helper_crypto_sha1h; - break; - case 1: /* SHA1SU1 */ - feature = dc_isar_feature(aa64_sha1, s); - genfn = gen_helper_crypto_sha1su1; - break; - case 2: /* SHA256SU0 */ - feature = dc_isar_feature(aa64_sha256, s); - genfn = gen_helper_crypto_sha256su0; - break; - default: - unallocated_encoding(s); - return; - } - - if (!feature) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - gen_gvec_op2_ool(s, true, rd, rn, 0, genfn); -} - /* Crypto three-reg SHA512 * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 * +-----------------------+------+---+---+-----+--------+------+------+ @@ -13849,7 +13804,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha }, { 0xce608000, 0xffe0b000, disas_crypto_three_reg_sha512 }, { 0xcec08000, 0xfffff000, disas_crypto_two_reg_sha512 }, { 0xce000000, 0xff808000, disas_crypto_four_reg }, From patchwork Tue May 28 14:07:29 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799482 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257209wrz; Tue, 28 May 2024 07:12:43 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCV7vEjHhvxdPFhp53pX4oR2cIawoASq1pqEdg57IhAPncG5Oq6ymzl4okjjDsBh67LpXjICkMxgdFDTTnG1GkRB X-Google-Smtp-Source: AGHT+IECFwDNeX/o+wUzcYZ6BzzQTYTRBt/MRF2X+pY9w3S+AEAZkQQxXIt29DdlNtdqZ5C1rq6s X-Received: by 2002:a67:cb02:0:b0:47f:40f7:2b5f with SMTP id ada2fe7eead31-48a38503ef3mr12362174137.5.1716905562995; Tue, 28 May 2024 07:12:42 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905562; cv=none; d=google.com; s=arc-20160816; b=lFVUaGUubykW8dBV6btK3np1Jd3isVLHOFhGbxcN6iDiZggLEz24SUlEWy7yhx/YFb 3ioW0u/7f/1Yz/p64YPevVtsPb70ngNtHsnS8e3RBefKkSlU635QouByJ5jOzfPYL7UM rOadjTfw9Qm2PtBgJpLIuIkXMkre0cm6ARhEsUI+BQuJCCegg1/qLzBoOaS/ZIEwMPnB /HpZD8HSmzDG10Q1RnCvf44usCVvvl+CDJfIxZ+06bDHvx0TAqgsra+O4CmqBrqdYmPb rKjHrn6uMyvs1ZNGraSTDgMuSDCiN00Q0ITlug4Y7jKtEnYFMSDnpisXg/ryFl+NqCZp wl0Q== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=VPzY7vRQK/tFc1bvvOxU2Y3WTOQVdjIhkOjnl3uekmc=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=G6oL7vIoFixEzVlwSHWAspWhoqqHeNyly4ioeHBKt5Uj+g2pit64NNzThJQ5tHaqRW nRq+aeVLRr9mYSucUaqMrFy7Wi/tsoUUXq5HzpqIv/VHZL+R0Jbo4QajAGU1ub7QhaQ3 iAx6LFln4Lg73Jgif+xrv4pHsZBoOfAojr702uYsXVQUbvitTTVPXeajOkAiOM6WM47E Sfquj3EcSDp6LQQxF736/KkjBDmxVxg8o4Idj1vUa3ySh6UURKJzliH+7j1m9CD1KooO +aN4CVb82CZAYlYo2UmpohLKzA476TnagvkQ7psL7e5KsZPqwYymhFDdxMuzSppVs4yX g5jA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="LxRJ6/tz"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a205794si2081473137.27.2024.05.28.07.12.42 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:42 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="LxRJ6/tz"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUq-0001ba-Dt; Tue, 28 May 2024 10:08:12 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUo-0001b0-H0 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: from mail-wr1-x429.google.com ([2a00:1450:4864:20::429]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUl-000743-PR for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:10 -0400 Received: by mail-wr1-x429.google.com with SMTP id ffacd0b85a97d-354faf5f1b4so666916f8f.1 for ; Tue, 28 May 2024 07:08:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905286; x=1717510086; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=VPzY7vRQK/tFc1bvvOxU2Y3WTOQVdjIhkOjnl3uekmc=; b=LxRJ6/tzWmIDtSrD1vv0klFkgFJot0fSlUuI+QtfYrtMcMzqmVX2gCyhwPzBP26+6H whIPVItCMgl1VdmXOPKei9B1M26FlLuhBoxpw6oGfZ1gCYLZgO43UkcZXJ1YUOny1VAi SYlpDH+DR5qDUHK7VPIZHYFhQ6lj5vysWrFE05uM5RqcnrTtxxujio/sOXo7xKFWuO8n oQO1JQTWrLK0zPxG2/48cG20IU+Fsx7BTba31f/KrQ3BP3oqGfs0HHtbDrWn3DZSIF0k 7MTIfyeox4Ube5vgUlBpksW02VvD5xq3vUcYfafVD17TttsnZE8meDWRTyHpvIHzzb76 W1Aw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905286; x=1717510086; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VPzY7vRQK/tFc1bvvOxU2Y3WTOQVdjIhkOjnl3uekmc=; b=SBJFqr9snTVeq4f5UFmRR1RPkG/E0zkBWn8kBruk78ncggzM4/oWAgc8M3FHs/GKa8 zcqtIQBXcOvIjZPz2cqEHdJcz4JJBadYLUY02hYFlrrlxU8ciDT9VwKA8UHA8rhINvw3 T/yCQWA1K1ByXp8RH1ms/+ES1Mdi79z+qhKDX6VoCgg5DhCFoDDTcEkjSJ1ULy09BVax quB9Foajjj4IyMAUnGNqwp6zimyfDG6uvvcHirQqEjpZeXashvZFox0EvcXWYfZWoY+s iYDTVMEmxCMhfk+LZGEu5GFTIC0aibB8AHt/C6GdLCziSnNeCWjat7xsj0yagIaCimW6 ohQA== X-Gm-Message-State: AOJu0YwxUJKYXNvlPrJVUu2xx63vUaNeMjZBk6WdVFDpfa4644y5FlJv RR5E94/eTwM2IGODVCym1U073yjhcmfDMNhzQ298KYyGX0oFHxHdMwjrj4rhzyUUSAqmb02mTJ5 o X-Received: by 2002:a5d:62cc:0:b0:354:d098:8d67 with SMTP id ffacd0b85a97d-3552fe179a1mr10570355f8f.57.1716905286211; Tue, 28 May 2024 07:08:06 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.05 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:05 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 18/42] target/arm: Convert Cryptographic 3-register SHA512 to decodetree Date: Tue, 28 May 2024 15:07:29 +0100 Message-Id: <20240528140753.3620597-19-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::429; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x429.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 11 ++++ target/arm/tcg/translate-a64.c | 97 ++++++++-------------------------- 2 files changed, 32 insertions(+), 76 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 350afabc779..c342c276089 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -31,6 +31,7 @@ @rr_q1e0 ........ ........ ...... rn:5 rd:5 &qrr_e q=1 esz=0 @r2r_q1e0 ........ ........ ...... rm:5 rd:5 &qrrr_e rn=%rd q=1 esz=0 @rrr_q1e0 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=0 +@rrr_q1e3 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=3 ### Data Processing - Immediate @@ -620,3 +621,13 @@ SHA256SU1 0101 1110 000 ..... 011000 ..... ..... @rrr_q1e0 SHA1H 0101 1110 0010 1000 0000 10 ..... ..... @rr_q1e0 SHA1SU1 0101 1110 0010 1000 0001 10 ..... ..... @rr_q1e0 SHA256SU0 0101 1110 0010 1000 0010 10 ..... ..... @rr_q1e0 + +### Cryptographic three-register SHA512 + +SHA512H 1100 1110 011 ..... 100000 ..... ..... @rrr_q1e0 +SHA512H2 1100 1110 011 ..... 100001 ..... ..... @rrr_q1e0 +SHA512SU1 1100 1110 011 ..... 100010 ..... ..... @rrr_q1e0 +RAX1 1100 1110 011 ..... 100011 ..... ..... @rrr_q1e3 +SM3PARTW1 1100 1110 011 ..... 110000 ..... ..... @rrr_q1e0 +SM3PARTW2 1100 1110 011 ..... 110001 ..... ..... @rrr_q1e0 +SM4EKEY 1100 1110 011 ..... 110010 ..... ..... @rrr_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1d20bf0c35b..77b24cd52ed 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1341,6 +1341,17 @@ static bool do_gvec_op3_ool(DisasContext *s, arg_qrrr_e *a, int data, return true; } +static bool do_gvec_fn3(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) +{ + if (!a->q && a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_fn3(s, a->q, a->rd, a->rn, a->rm, fn, a->esz); + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the @@ -4589,7 +4600,7 @@ static bool trans_EXTR(DisasContext *s, arg_extract *a) } /* - * Cryptographic AES, SHA + * Cryptographic AES, SHA, SHA512 */ TRANS_FEAT(AESE, aa64_aes, do_gvec_op3_ool, a, 0, gen_helper_crypto_aese) @@ -4610,6 +4621,15 @@ TRANS_FEAT(SHA1H, aa64_sha1, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha1h) TRANS_FEAT(SHA1SU1, aa64_sha1, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha1su1) TRANS_FEAT(SHA256SU0, aa64_sha256, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha256su0) +TRANS_FEAT(SHA512H, aa64_sha512, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha512h) +TRANS_FEAT(SHA512H2, aa64_sha512, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha512h2) +TRANS_FEAT(SHA512SU1, aa64_sha512, do_gvec_op3_ool, a, 0, gen_helper_crypto_sha512su1) +TRANS_FEAT(RAX1, aa64_sha3, do_gvec_fn3, a, gen_gvec_rax1) +TRANS_FEAT(SM3PARTW1, aa64_sm3, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm3partw1) +TRANS_FEAT(SM3PARTW2, aa64_sm3, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm3partw2) +TRANS_FEAT(SM4EKEY, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4ekey) + + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13510,80 +13530,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto three-reg SHA512 - * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 - * +-----------------------+------+---+---+-----+--------+------+------+ - * | 1 1 0 0 1 1 1 0 0 1 1 | Rm | 1 | O | 0 0 | opcode | Rn | Rd | - * +-----------------------+------+---+---+-----+--------+------+------+ - */ -static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) -{ - int opcode = extract32(insn, 10, 2); - int o = extract32(insn, 14, 1); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - bool feature; - gen_helper_gvec_3 *oolfn = NULL; - GVecGen3Fn *gvecfn = NULL; - - if (o == 0) { - switch (opcode) { - case 0: /* SHA512H */ - feature = dc_isar_feature(aa64_sha512, s); - oolfn = gen_helper_crypto_sha512h; - break; - case 1: /* SHA512H2 */ - feature = dc_isar_feature(aa64_sha512, s); - oolfn = gen_helper_crypto_sha512h2; - break; - case 2: /* SHA512SU1 */ - feature = dc_isar_feature(aa64_sha512, s); - oolfn = gen_helper_crypto_sha512su1; - break; - case 3: /* RAX1 */ - feature = dc_isar_feature(aa64_sha3, s); - gvecfn = gen_gvec_rax1; - break; - default: - g_assert_not_reached(); - } - } else { - switch (opcode) { - case 0: /* SM3PARTW1 */ - feature = dc_isar_feature(aa64_sm3, s); - oolfn = gen_helper_crypto_sm3partw1; - break; - case 1: /* SM3PARTW2 */ - feature = dc_isar_feature(aa64_sm3, s); - oolfn = gen_helper_crypto_sm3partw2; - break; - case 2: /* SM4EKEY */ - feature = dc_isar_feature(aa64_sm4, s); - oolfn = gen_helper_crypto_sm4ekey; - break; - default: - unallocated_encoding(s); - return; - } - } - - if (!feature) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - if (oolfn) { - gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); - } else { - gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); - } -} - /* Crypto two-reg SHA512 * 31 12 11 10 9 5 4 0 * +-----------------------------------------+--------+------+------+ @@ -13804,7 +13750,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0xce608000, 0xffe0b000, disas_crypto_three_reg_sha512 }, { 0xcec08000, 0xfffff000, disas_crypto_two_reg_sha512 }, { 0xce000000, 0xff808000, disas_crypto_four_reg }, { 0xce800000, 0xffe00000, disas_crypto_xar }, From patchwork Tue May 28 14:07:30 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799496 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257934wrz; Tue, 28 May 2024 07:14:00 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCV2ecICMEZUO2C8GnTFtLr2g13nHmUhRqip15TTRyaDqi204ce+Y5+ls2S//iYZbYTMNrkFYZN7B/iIVdZIhAQe X-Google-Smtp-Source: AGHT+IF/1SQfUYuHQNpc20M0klVLm/gCtULkvK9mOVbjrfMtbYzdrTNNO5GLMp/Nn6d15tTbdN9v X-Received: by 2002:a05:6122:2512:b0:4da:aabe:6f6c with SMTP id 71dfb90a1353d-4e4f0272160mr12316827e0c.7.1716905640213; Tue, 28 May 2024 07:14:00 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905640; cv=none; d=google.com; s=arc-20160816; b=ye8k7u9tGaA71vey+2F/oGmVe036SXyW7zpmzyCBbZgp7CVZUtlRaaDVjBIeCgTE/y nGC/hDfVxeGLp9Twf+BQdv0bZyvewMRqKBWVeNXE19fJSvpG/BFvAcRIkM0bJCR7Rj2D ueGshBe5ZH91yJohiEoOK01AAcTcQNBFYPFLKS0l+2sXLJFQU5DLEJguqeazmoWQoFD4 YTDgUAu77Qqf4hhPWCXq5adJSXu0fcyiF69WiDCH76eMAa0OjKMw5ehshUJxZjJ1Bipw 1yXVAYM6FDa6D/wCsgIfLy0jgvNTN4GrmGrNoa/CTHtvYpsUzmS6svWSySpToZdCWK8d +KmA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=xlqr8OCRH9VlaXuwhAgRGhxeV6jrq6Fx27rZAA3V29g=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=Q04RE+kY+KlRXxhSjaq+MjVDcJcN8K+as95v5Pr9soB1gCBb25Dh0kIwz5uCVuX+rK mMXNmDmusHcDn+dX4ZNYexYI37Ra+Z10PllwZhpL2mZO325HUAtAUzFK99NeS6ejLIWV sfFrhTTKNDET3TSc8UyrqWKDIhgRycK4VlXt8uppvCEg/muO8vnYuacZhzF3yuUwYgIc LtXIgNUOcU9crICVSLRZ1eiLgeEg5DY9Ei5I1rfLN6cjCmA2f6iewDLYDgB8LCSoKzB2 DSy0lLAusWfYhBa0/dsHfNXr5MEVaWkIjf34DLrIaHf6HbPgAOoxAtfSk/Thzt7tj0m4 SLlg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=VtUJiIuK; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 71dfb90a1353d-4e4f072a84csi1815525e0c.47.2024.05.28.07.14.00 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:14:00 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=VtUJiIuK; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUr-0001cQ-U4; Tue, 28 May 2024 10:08:13 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUq-0001bj-P4 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:12 -0400 Received: from mail-wm1-x32c.google.com ([2a00:1450:4864:20::32c]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUm-00074H-PU for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:12 -0400 Received: by mail-wm1-x32c.google.com with SMTP id 5b1f17b1804b1-420180b58c5so6690615e9.3 for ; Tue, 28 May 2024 07:08:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905287; x=1717510087; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=xlqr8OCRH9VlaXuwhAgRGhxeV6jrq6Fx27rZAA3V29g=; b=VtUJiIuKaQN1TTp0BjAQYsVDeeQj/+UdU31Qnysy7gYAp0XiAporrnzl2ieDGIeyoL 0hJdSm12A5kcxtPXG2Q1ZLNnYJqjk2lLVQ1HapZDF5Nc6M4TWAxN1TwBV8VBvEncvJvt pna9qh/pt75QwblMyYvbzcUMWlGI1Z9sBL+fHdjR9lLnYKBviXlX7XQrLNpMZ+LQykE9 S82NcdtNC0IotmQjkJ9WRd8R+0zgGB6e5CwktKgCoUROAxj18m9W2y/WiTdhrUudp4ul H+qLZ6Xpszfl7vz+dnuYNgkExr9rD4Q3xlZOdLn8M98jFDE7pci2YDITkOCmOMdS7hH1 oypQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905287; x=1717510087; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=xlqr8OCRH9VlaXuwhAgRGhxeV6jrq6Fx27rZAA3V29g=; b=Nahsvyhmc7QVz+szarJCqyUuhkXNGUa8sbAMoRaQAXXzJ5kwODPpeLmk58t5BrrLne m9XbBgYlnPPtXMUnv/mMzcZ5Ob9msgSKLDAAqHrB+QnwV2FT34IaZqXdTj82a0JkBE9D lKmLccgE9odTEKguWJ/J0TqFP8/7hB3G7paVUv6GV2gZVC3DkpaZ9c5PKnl2vrc/f3fn ++AD6TapKgRtrsGBfDCW/zQ+skXJmkVrYUBONd/kau0+3iGe55V3tGpCGeAQxP/kLFlD fbo7PE9TrOlGsntkrjJ7lerdw4NWfCvD8W1Xtg8wZyz34zudmuXD16Ap/sPcNMEHIHfg WNqQ== X-Gm-Message-State: AOJu0Yyw9kOSkzeVwJNeCDsW8WIkY+aVCZFDFN8gXE2qE4vIp/Xd/sbx YnDVdSiJK2tRpJVmirls8ZJ64a/qi9gRnZhw/eKblq3jS3Pguij3BGHTrJKDXYK01t6ogY994Is p X-Received: by 2002:a05:600c:1d21:b0:41f:e56c:ef81 with SMTP id 5b1f17b1804b1-421089b1b4dmr109249355e9.1.1716905287219; Tue, 28 May 2024 07:08:07 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.06 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:06 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 19/42] target/arm: Convert Cryptographic 2-register SHA512 to decodetree Date: Tue, 28 May 2024 15:07:30 +0100 Message-Id: <20240528140753.3620597-20-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::32c; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x32c.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 5 ++++ target/arm/tcg/translate-a64.c | 50 ++-------------------------------- 2 files changed, 8 insertions(+), 47 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index c342c276089..5a46205751c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -631,3 +631,8 @@ RAX1 1100 1110 011 ..... 100011 ..... ..... @rrr_q1e3 SM3PARTW1 1100 1110 011 ..... 110000 ..... ..... @rrr_q1e0 SM3PARTW2 1100 1110 011 ..... 110001 ..... ..... @rrr_q1e0 SM4EKEY 1100 1110 011 ..... 110010 ..... ..... @rrr_q1e0 + +### Cryptographic two-register SHA512 + +SHA512SU0 1100 1110 110 00000 100000 ..... ..... @rr_q1e0 +SM4E 1100 1110 110 00000 100001 ..... ..... @r2r_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 77b24cd52ed..eed0abe9121 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4629,6 +4629,9 @@ TRANS_FEAT(SM3PARTW1, aa64_sm3, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm3part TRANS_FEAT(SM3PARTW2, aa64_sm3, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm3partw2) TRANS_FEAT(SM4EKEY, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4ekey) +TRANS_FEAT(SHA512SU0, aa64_sha512, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha512su0) +TRANS_FEAT(SM4E, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4e) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the @@ -13530,52 +13533,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto two-reg SHA512 - * 31 12 11 10 9 5 4 0 - * +-----------------------------------------+--------+------+------+ - * | 1 1 0 0 1 1 1 0 1 1 0 0 0 0 0 0 1 0 0 0 | opcode | Rn | Rd | - * +-----------------------------------------+--------+------+------+ - */ -static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) -{ - int opcode = extract32(insn, 10, 2); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - bool feature; - - switch (opcode) { - case 0: /* SHA512SU0 */ - feature = dc_isar_feature(aa64_sha512, s); - break; - case 1: /* SM4E */ - feature = dc_isar_feature(aa64_sm4, s); - break; - default: - unallocated_encoding(s); - return; - } - - if (!feature) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - switch (opcode) { - case 0: /* SHA512SU0 */ - gen_gvec_op2_ool(s, true, rd, rn, 0, gen_helper_crypto_sha512su0); - break; - case 1: /* SM4E */ - gen_gvec_op3_ool(s, true, rd, rd, rn, 0, gen_helper_crypto_sm4e); - break; - default: - g_assert_not_reached(); - } -} - /* Crypto four-register * 31 23 22 21 20 16 15 14 10 9 5 4 0 * +-------------------+-----+------+---+------+------+------+ @@ -13750,7 +13707,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0xcec08000, 0xfffff000, disas_crypto_two_reg_sha512 }, { 0xce000000, 0xff808000, disas_crypto_four_reg }, { 0xce800000, 0xffe00000, disas_crypto_xar }, { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, From patchwork Tue May 28 14:07:31 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799481 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257205wrz; Tue, 28 May 2024 07:12:41 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX7pDxJVhrlHo9d/gPo2cJret06rKnTM+wPogNTXE3nP54LJUCYoItaKSHgELNULVn/7036JkuPCsE6FIQPp7Od X-Google-Smtp-Source: AGHT+IGDKwxSa/6UQXQO+hW6jb38sOl80o2PQMvdTwk51edLI07X2J2SIAcSiqw5peSXjoJnmUMm X-Received: by 2002:a67:e90a:0:b0:47c:dd:2cd2 with SMTP id ada2fe7eead31-48a2bb19348mr12934452137.1.1716905561608; Tue, 28 May 2024 07:12:41 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905561; cv=none; d=google.com; s=arc-20160816; b=mfVSspFcnJqZy46PmbGN1DIOgfOlrj1CaPkcUucWuFtZwC/4NBDtoClsiaTVtgOGJV D73iIJHpRN4fLPfebTbzKnG4xwMysHjBU2SzeFYqyg3EgH7fjFPyjXev0pH4huDb1mcK LIc3wyJ8xW8oT+6N7L3FKUWEZOwICP95ol9jkEcYZddA2bh6lGE/4Nhr69sLSud8zZWb eamsgCmNloS8ttHQFDtSvsDe/QcyunljOcO2qXIi2JV73/MNb585XJc9bwfqSVmFBi3B IpTvmuGmoOZwhkHOVZM9bpZ3vF8kqMC5c6SfBYkXHYQMf+vGl5aDqqxjD7C6e5tGquSJ M0BA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=C2ZawCgaAF0BqPJgysZJWZ6oeUE16YF5bG4KbeMKEd4=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=MENIWYa4buDrIbDl4iGK9wyLVeypKoyrWT04h3jwNJbjT50Wfg9WLqJRMyn8br+n7j bOJWRcQJ+n+PJ1hsuKD4rEtOunsFRwRbA/11B8kZysjF+tal8uzH+HlETVsSnsBz5n47 O6kjw1+WoY8ve0dJNFTHK6q7xc65WQoxmblLStUletvVDA5TMM0iCdaRjOHeq20abCgy jtBvC0O3le6liXnXyeWapG8BFYfAkJMW2jvjlDZ2wl3hFrvDSe3NXlGM+r7V9RW8Se5J e9FUxJamqnCliAfWk60r3GH4m5fyOom4NLWoon2KshsqD6wH4GYgtYbMYzb/FZGSAJO/ +NJQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=uf30j7Sh; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a2247f8si2164420137.191.2024.05.28.07.12.41 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:41 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=uf30j7Sh; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUv-0001f0-0G; Tue, 28 May 2024 10:08:17 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUs-0001cX-2l for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:14 -0400 Received: from mail-wr1-x435.google.com ([2a00:1450:4864:20::435]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUn-00074M-1r for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:13 -0400 Received: by mail-wr1-x435.google.com with SMTP id ffacd0b85a97d-354be94c874so729257f8f.3 for ; Tue, 28 May 2024 07:08:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905288; x=1717510088; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=C2ZawCgaAF0BqPJgysZJWZ6oeUE16YF5bG4KbeMKEd4=; b=uf30j7ShCoZ84luW3n9l4krBftB8KaMNk+Egk+6d/iSa/9pmiGryMzcqCs8GK652HJ tD3JHz1hyRN/PJxKZ1Vxhq394r6HPI2CaDF3LQIfGll+S8nm5SPETlvLXsv9pq+AvUtU o0upvY+wmNDozADb5ZGTjK1VtvrekPzhiErpWTBoilWP2oaR7CGYstCBUa11O2H5ytn8 Y/CfjvSscvIXd5733PGT1ZgXXuYEQlgzMzKMOBqF9dmhY75TogzhM4zDb4D7tfO1QC01 ve6ERLuByzP05hRlBmm1I8aZn7yAG88VFFroIGKnohxsIh9mwxdzkn2vPhXft4Wj3NXL yUZQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905288; x=1717510088; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=C2ZawCgaAF0BqPJgysZJWZ6oeUE16YF5bG4KbeMKEd4=; b=lugLoZ7W8NBpFjBd5aGhs4falc+Td5TH0LChbI1AiKfTtRV82kE+8JnjTHPDsFXRbt SDUHAhBIoy05zK0xqdbjF4urMUatN2wtWvretxnp20rO69IBNcMbeLArUXgzmVYhNVd4 esKtFDHWJoOaj7bOxEZGrsBS/W5p3ykjtbjPc3c+VnppuXa1dxnqa4/qbtzRFz3EyshD 1hK/8C7VQ2pnB2953jgqTUS2mn6Kg3k+zzrBhYaWH1BZEkTe7F9rrIbMHdMcH9r6gyKh 3Ie7arM+GXsPDYw1tVEjK7o7/iKSz82j5I5RQv42PAog6yvt0xHajIFwqWigVTremDYr xuDQ== X-Gm-Message-State: AOJu0YwvofA2fU0vm2xUviLKUfdwty045Eg/Vu11TcuVe9bMH0L2RZYx ugCH1DE1ApWuETvDUVyOizIMA+Das/3GHceurnOBDyuapqi/Ba5utY4hmas6ABNUEgPJwMc3SDq X X-Received: by 2002:adf:9bce:0:b0:355:348:50f9 with SMTP id ffacd0b85a97d-3552fdfcaacmr9310685f8f.71.1716905287755; Tue, 28 May 2024 07:08:07 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.07 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:07 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 20/42] target/arm: Convert Cryptographic 4-register to decodetree Date: Tue, 28 May 2024 15:07:31 +0100 Message-Id: <20240528140753.3620597-21-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::435; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x435.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 8 ++ target/arm/tcg/translate-a64.c | 132 +++++++++++---------------------- 2 files changed, 51 insertions(+), 89 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 5a46205751c..ef6902e86a5 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -27,11 +27,13 @@ &i imm &qrr_e q rd rn esz &qrrr_e q rd rn rm esz +&qrrrr_e q rd rn rm ra esz @rr_q1e0 ........ ........ ...... rn:5 rd:5 &qrr_e q=1 esz=0 @r2r_q1e0 ........ ........ ...... rm:5 rd:5 &qrrr_e rn=%rd q=1 esz=0 @rrr_q1e0 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=0 @rrr_q1e3 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=3 +@rrrr_q1e3 ........ ... rm:5 . ra:5 rn:5 rd:5 &qrrrr_e q=1 esz=3 ### Data Processing - Immediate @@ -636,3 +638,9 @@ SM4EKEY 1100 1110 011 ..... 110010 ..... ..... @rrr_q1e0 SHA512SU0 1100 1110 110 00000 100000 ..... ..... @rr_q1e0 SM4E 1100 1110 110 00000 100001 ..... ..... @r2r_q1e0 + +### Cryptographic four-register + +EOR3 1100 1110 000 ..... 0 ..... ..... ..... @rrrr_q1e3 +BCAX 1100 1110 001 ..... 0 ..... ..... ..... @rrrr_q1e3 +SM3SS1 1100 1110 010 ..... 0 ..... ..... ..... @rrrr_q1e3 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index eed0abe9121..2951e7eb59e 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1352,6 +1352,17 @@ static bool do_gvec_fn3(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) return true; } +static bool do_gvec_fn4(DisasContext *s, arg_qrrrr_e *a, GVecGen4Fn *fn) +{ + if (!a->q && a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_fn4(s, a->q, a->rd, a->rn, a->rm, a->ra, fn, a->esz); + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the @@ -4632,6 +4643,38 @@ TRANS_FEAT(SM4EKEY, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4ekey) TRANS_FEAT(SHA512SU0, aa64_sha512, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha512su0) TRANS_FEAT(SM4E, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4e) +TRANS_FEAT(EOR3, aa64_sha3, do_gvec_fn4, a, gen_gvec_eor3) +TRANS_FEAT(BCAX, aa64_sha3, do_gvec_fn4, a, gen_gvec_bcax) + +static bool trans_SM3SS1(DisasContext *s, arg_SM3SS1 *a) +{ + if (!dc_isar_feature(aa64_sm3, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 tcg_op1 = tcg_temp_new_i32(); + TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i32 tcg_op3 = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + unsigned vsz, dofs; + + read_vec_element_i32(s, tcg_op1, a->rn, 3, MO_32); + read_vec_element_i32(s, tcg_op2, a->rm, 3, MO_32); + read_vec_element_i32(s, tcg_op3, a->ra, 3, MO_32); + + tcg_gen_rotri_i32(tcg_res, tcg_op1, 20); + tcg_gen_add_i32(tcg_res, tcg_res, tcg_op2); + tcg_gen_add_i32(tcg_res, tcg_res, tcg_op3); + tcg_gen_rotri_i32(tcg_res, tcg_res, 25); + + /* Clear the whole register first, then store bits [127:96]. */ + vsz = vec_full_reg_size(s); + dofs = vec_full_reg_offset(s, a->rd); + tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0); + write_vec_element_i32(s, tcg_res, a->rd, 3, MO_32); + } + return true; +} /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the @@ -13533,94 +13576,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto four-register - * 31 23 22 21 20 16 15 14 10 9 5 4 0 - * +-------------------+-----+------+---+------+------+------+ - * | 1 1 0 0 1 1 1 0 0 | Op0 | Rm | 0 | Ra | Rn | Rd | - * +-------------------+-----+------+---+------+------+------+ - */ -static void disas_crypto_four_reg(DisasContext *s, uint32_t insn) -{ - int op0 = extract32(insn, 21, 2); - int rm = extract32(insn, 16, 5); - int ra = extract32(insn, 10, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - bool feature; - - switch (op0) { - case 0: /* EOR3 */ - case 1: /* BCAX */ - feature = dc_isar_feature(aa64_sha3, s); - break; - case 2: /* SM3SS1 */ - feature = dc_isar_feature(aa64_sm3, s); - break; - default: - unallocated_encoding(s); - return; - } - - if (!feature) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - if (op0 < 2) { - TCGv_i64 tcg_op1, tcg_op2, tcg_op3, tcg_res[2]; - int pass; - - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_op3 = tcg_temp_new_i64(); - tcg_res[0] = tcg_temp_new_i64(); - tcg_res[1] = tcg_temp_new_i64(); - - for (pass = 0; pass < 2; pass++) { - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - read_vec_element(s, tcg_op3, ra, pass, MO_64); - - if (op0 == 0) { - /* EOR3 */ - tcg_gen_xor_i64(tcg_res[pass], tcg_op2, tcg_op3); - } else { - /* BCAX */ - tcg_gen_andc_i64(tcg_res[pass], tcg_op2, tcg_op3); - } - tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1); - } - write_vec_element(s, tcg_res[0], rd, 0, MO_64); - write_vec_element(s, tcg_res[1], rd, 1, MO_64); - } else { - TCGv_i32 tcg_op1, tcg_op2, tcg_op3, tcg_res, tcg_zero; - - tcg_op1 = tcg_temp_new_i32(); - tcg_op2 = tcg_temp_new_i32(); - tcg_op3 = tcg_temp_new_i32(); - tcg_res = tcg_temp_new_i32(); - tcg_zero = tcg_constant_i32(0); - - read_vec_element_i32(s, tcg_op1, rn, 3, MO_32); - read_vec_element_i32(s, tcg_op2, rm, 3, MO_32); - read_vec_element_i32(s, tcg_op3, ra, 3, MO_32); - - tcg_gen_rotri_i32(tcg_res, tcg_op1, 20); - tcg_gen_add_i32(tcg_res, tcg_res, tcg_op2); - tcg_gen_add_i32(tcg_res, tcg_res, tcg_op3); - tcg_gen_rotri_i32(tcg_res, tcg_res, 25); - - write_vec_element_i32(s, tcg_zero, rd, 0, MO_32); - write_vec_element_i32(s, tcg_zero, rd, 1, MO_32); - write_vec_element_i32(s, tcg_zero, rd, 2, MO_32); - write_vec_element_i32(s, tcg_res, rd, 3, MO_32); - } -} - /* Crypto XAR * 31 21 20 16 15 10 9 5 4 0 * +-----------------------+------+--------+------+------+ @@ -13707,7 +13662,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0xce000000, 0xff808000, disas_crypto_four_reg }, { 0xce800000, 0xffe00000, disas_crypto_xar }, { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, From patchwork Tue May 28 14:07:32 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799491 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257775wrz; Tue, 28 May 2024 07:13:41 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVO+XyO+sWstK+QMc+fLuyFDt38ouvtsQR0eqAmb7YUVrQwMbPzFCcEc7lKxj0wtURlMSnw0K7E7Hf1Ipu0HlyE X-Google-Smtp-Source: AGHT+IHKIBRRVc7oJh3fxLHLKX3h/8tytPdvBTDeox0DOuClYN8/AMTsIIIZPP1CO5N4znJmRQo6 X-Received: by 2002:a05:6870:7b4a:b0:24f:dde9:d72d with SMTP id 586e51a60fabf-24fdde9d851mr9160403fac.54.1716905621311; Tue, 28 May 2024 07:13:41 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905621; cv=none; d=google.com; s=arc-20160816; b=uhHTRw/xHXISL5d+7EHYROjodB8wARu0hcvUNuOVNTzxFv5D+wZP3PMFlJ6D4qcJmw KvUDuB08hMFbEsYv2jeNxfqc7vzzgKbmgb2xgzf1I2pCjRDJAftFHFUXDoIcO+ZIwR8G 7j67p+RAtzoo3fYqOoEw9OOhQ77nkGcPAcka0lwKlpzeb6Q+XRZA6pgXEqqIIKpGmjQS 0vmCDMWrIl8j1dV4VEKJf0bNy1HQKpIxIvx9Hu9aL1drcdNOpaZjyt0L4Bt8s0eREb7S y0gckZrq9bN7lbQWaNhORzgOopQJfbHK4/dnKvhbN4cPREEhE7732sTTijTcaFrW026k YPrw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=T9M0UZJDFFcR7IKXfZzYHCl9cYvAnk5miuB+Cg9H1ls=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=Y74pl3jtUk4QmUWcgXghZYx61fnvUOuoNVzTwqs+lHXuv4tVik+ZlshCUM2kEd/bQC naO4DWTge3W46Nx7NJNMcU4GFwkq26N8EXzG/AfIZfp5ZaS/pYgxt9FV3xRFf3hsjPpc z1gzIlRdfAu0Dd3/FUHBEgQWk/apmu8KafDYurwIcHMTFr7i6st+4wXDpy42pvvWYcQC JdinFBxIbX30Tse/H+H/XRInUN2xM0tHydUz9yVUctw6JDk6xWDTYRiSu7yFOl87KWbO G2MgDWoUbPn8gnvtqnYKou30FdKwlwwvVasVISVIgRkupLsTBjFHyNfnBAeRsTKkhWJ5 DPrA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=HqRSsyZn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a45372bsi1789269137.824.2024.05.28.07.13.41 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:41 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=HqRSsyZn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUt-0001e0-PZ; Tue, 28 May 2024 10:08:15 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUr-0001cP-Q1 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:13 -0400 Received: from mail-wr1-x42e.google.com ([2a00:1450:4864:20::42e]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUn-00074V-Ix for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:13 -0400 Received: by mail-wr1-x42e.google.com with SMTP id ffacd0b85a97d-35502a992c9so908610f8f.3 for ; Tue, 28 May 2024 07:08:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905288; x=1717510088; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=T9M0UZJDFFcR7IKXfZzYHCl9cYvAnk5miuB+Cg9H1ls=; b=HqRSsyZnTe6Yw1QJCKM99VarIps6lv4MhmrqBWph8Lpsl8RStAFQlqZfswCZEBpKOt K71+fqZgySX7tE6icClW7gyuiiIvPEhqU1QyL9nqEcyHxwsCRa2ZbRHrLyEpK1A2YTo6 X67spcNJx/+BwBhKqDjanJHANYTOaeSbyiM4Y1SYhH0wB/luakzhHVQnmkIOo/QKAKcW FLHhGA5Pp06ZCANKy8o7XGFy9F7i/r7Pqo7MR86NtOBDbpkuhhwh7qVJhpLbSu0atuxU 1e27tQGlxbNQ3Ac+e6/0t0kqVZGXcf+ZNSdxlJxNxy6d1W1IxV49d/zdlRoPB2CYMBIC EGYg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905288; x=1717510088; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=T9M0UZJDFFcR7IKXfZzYHCl9cYvAnk5miuB+Cg9H1ls=; b=qSxLUM+09N4BV8I/3kNzpGzAjm0RojpQtQuJrIBl3Q8XZ34lGS2eArJBACWAInNK7R F3tYprwj+TO/VT3QeA9TfyDJ9AAEMqidUnHDAD84081c+YiQxfB8O3ZFJA4F40+o1PXV 53jfb0hYz/Sx3XP++jq2y1gP4XrVspm9Iazh5RSrzJu4eVPLT/CJc+Jo8os8rG/YS27t 8Mr4Jr9sJG65ca88gYEh71wlmLZ8Sbo8LMP16it1ZKh/LCGEqOpXgJDD6xm2JwVO9uD8 S5HRs8eKgd9unvVohzGpArnUuVMlAT8QOAn2dfF58I8q4At1+6dh1+oWSWuUaHthIzzm rzQw== X-Gm-Message-State: AOJu0YxIKnz3gEYEun0rfBDeEAgFYrjhCueanIQLGzNGDcAigcThpRAb 22E71Kx96iUQXdoDjpOA0+J+BovmCFUzwFlFiKUAGp7Useo5hgtcNxIdw947MqMcskNLiZXXw7Z 1 X-Received: by 2002:a5d:408d:0:b0:355:4cb:5048 with SMTP id ffacd0b85a97d-3552fe02949mr10638527f8f.43.1716905288217; Tue, 28 May 2024 07:08:08 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.07 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:07 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 21/42] target/arm: Convert Cryptographic 3-register, imm2 to decodetree Date: Tue, 28 May 2024 15:07:32 +0100 Message-Id: <20240528140753.3620597-22-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42e; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42e.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 10 ++++++++ target/arm/tcg/translate-a64.c | 43 ++++++++++------------------------ 2 files changed, 22 insertions(+), 31 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index ef6902e86a5..1292312a7f9 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -644,3 +644,13 @@ SM4E 1100 1110 110 00000 100001 ..... ..... @r2r_q1e0 EOR3 1100 1110 000 ..... 0 ..... ..... ..... @rrrr_q1e3 BCAX 1100 1110 001 ..... 0 ..... ..... ..... @rrrr_q1e3 SM3SS1 1100 1110 010 ..... 0 ..... ..... ..... @rrrr_q1e3 + +### Cryptographic three-register, imm2 + +&crypto3i rd rn rm imm +@crypto3i ........ ... rm:5 .. imm:2 .. rn:5 rd:5 &crypto3i + +SM3TT1A 11001110 010 ..... 10 .. 00 ..... ..... @crypto3i +SM3TT1B 11001110 010 ..... 10 .. 01 ..... ..... @crypto3i +SM3TT2A 11001110 010 ..... 10 .. 10 ..... ..... @crypto3i +SM3TT2B 11001110 010 ..... 10 .. 11 ..... ..... @crypto3i diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 2951e7eb59e..cf3a7dfa99f 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4676,6 +4676,18 @@ static bool trans_SM3SS1(DisasContext *s, arg_SM3SS1 *a) return true; } +static bool do_crypto3i(DisasContext *s, arg_crypto3i *a, gen_helper_gvec_3 *fn) +{ + if (fp_access_check(s)) { + gen_gvec_op3_ool(s, true, a->rd, a->rn, a->rm, a->imm, fn); + } + return true; +} +TRANS_FEAT(SM3TT1A, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt1a) +TRANS_FEAT(SM3TT1B, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt1b) +TRANS_FEAT(SM3TT2A, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt2a) +TRANS_FEAT(SM3TT2B, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt2b) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13604,36 +13616,6 @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) vec_full_reg_size(s)); } -/* Crypto three-reg imm2 - * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 - * +-----------------------+------+-----+------+--------+------+------+ - * | 1 1 0 0 1 1 1 0 0 1 0 | Rm | 1 0 | imm2 | opcode | Rn | Rd | - * +-----------------------+------+-----+------+--------+------+------+ - */ -static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) -{ - static gen_helper_gvec_3 * const fns[4] = { - gen_helper_crypto_sm3tt1a, gen_helper_crypto_sm3tt1b, - gen_helper_crypto_sm3tt2a, gen_helper_crypto_sm3tt2b, - }; - int opcode = extract32(insn, 10, 2); - int imm2 = extract32(insn, 12, 2); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - if (!dc_isar_feature(aa64_sm3, s)) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - gen_gvec_op3_ool(s, true, rd, rn, rm, imm2, fns[opcode]); -} - /* C3.6 Data processing - SIMD, inc Crypto * * As the decode gets a little complex we are using a table based @@ -13663,7 +13645,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0xce800000, 0xffe00000, disas_crypto_xar }, - { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x5e400400, 0xdf60c400, disas_simd_scalar_three_reg_same_fp16 }, From patchwork Tue May 28 14:07:33 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799492 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257820wrz; Tue, 28 May 2024 07:13:46 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVw1gXt5puEKZuPZVn9hP0vb6PVx+HM5wnC47Q/hC2VZT/thcnfD+ShyNvuQLtKHaUbnRT8nR7VzKnTMVnAINQE X-Google-Smtp-Source: AGHT+IGCOQJx6ST5DMVhwM3WXn4jwJXZnzv/SboDBVnZMaEkCGvg4Y82FA/GiJTKob+fBFPHS/n4 X-Received: by 2002:a05:6870:d608:b0:24f:cddc:ccfe with SMTP id 586e51a60fabf-24fcddcdee4mr9317575fac.0.1716905626628; Tue, 28 May 2024 07:13:46 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905626; cv=none; d=google.com; s=arc-20160816; b=B7ddl0AYOmojSLqJec5SgN0BUxQ7Ou3iXxCZZYiMDapw0vKqajdhgT/qWklxwz1sfl QCKnjErwzQoRBHfy6KbSAyKyVmUr7NWk0UZ0bWcvJx1iPueERu+EvKhaXPbF0qyXerxy tfhgbxUgjCzS2xvf9DitPUk3K1EszIm9Nd5Ma7jceedHGtRK4RF9Qr/CU94oImkDxPS1 itVBod5JyH5jqptKYEfKyJ9d8+oW301hCLckw0JTn4NZlxg73pUQUlxpGeIQMetDNrS/ jN71XRJkvzhANb1HwHmLgNaHgkhj2MkgxVHfdkDxrqsh6efunFgAD1xWvjfjaUxp9S/P 1YWA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=7BpILccreJv3wPcv9huqs/UAol5xV2assISwJtuW028=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=CQ9A4MqyzXDOiZx6lQlRZ8dTT+2yeMbgsz2zheZDkGX6GUVc+sNFnrnrvltci602si gMfKXFjM+8NPMeIU/3R6XM4HAaLSkLrRcN8YH5YFCyVFVwBMhvUxoyreC3i1IOntFbyj fhBOVR3eR8YOCJ+SHEtZD4AdUwWZX75KD4ZTL5D+EMGjhohEk2lJcOSS9/J77Qfh/VRG S2xeTj+dNVK5AEFvYzSslPrviCtyhL7Ly82MngTNd+esrIiyywB0n1d9JP3WtZAshBLo Sd6iv8O/LGElUWWZwnkQhPkgpGXE9UTsK0+WApCG6RNoYfs86PiwF4tJ94OYTyN0h8Ga s4iw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=IBIsfOCa; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a206a54si2101698137.145.2024.05.28.07.13.46 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:46 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=IBIsfOCa; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUt-0001ds-Bq; Tue, 28 May 2024 10:08:15 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUs-0001cf-8m for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:14 -0400 Received: from mail-wm1-x332.google.com ([2a00:1450:4864:20::332]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUo-00074a-3z for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:13 -0400 Received: by mail-wm1-x332.google.com with SMTP id 5b1f17b1804b1-421087b6f3fso6866285e9.1 for ; Tue, 28 May 2024 07:08:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905288; x=1717510088; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=7BpILccreJv3wPcv9huqs/UAol5xV2assISwJtuW028=; b=IBIsfOCaxabwhP53mrIqLIwBTcuasN31Aq7McSggh45QFBeVjPgGRV16JUbW849MH3 AyKPegqjOjPJTOF6QdTbE6T6JSAzavSqZTsCK5/sEfDDcCXC/JEe7oM1968nq8nEX+od Q5bPXwIZW4ps6TuxIXKrpdjiuEyZycCgNvFtuAXzMaZTeDzYOmXYs7Mizo4HoWczLBZ/ 5ds0Q1BgKxEdSvL5FER8WVhYu7ZsFkZeNrtQUCYDme5HE3YtYhs/9iPXK/pTlDhQiDw2 crEGA7DMccsX0COtapLdnVBfkeoXVnse0EdKv/M3sVgfpWmFluQkMhaWBS8Q3q8xVtUQ Ta4w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905288; x=1717510088; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=7BpILccreJv3wPcv9huqs/UAol5xV2assISwJtuW028=; b=UwkPYrguDtt4Un0OOeJ2pXlWuRpM/RlqkhdMHd8jY1zBRtvkwRP+erHDpGTeDZvmOU DGNRL+9K7zrK2BaBQ3z+DHaSA5QRFsiKKQdS81tCQXM3zejEFO0YuhzQvUCmL/knG18b 4QrXMUYlZ/hw6sO1PrFZ0KGIgvvYngGck/NJ5/Oe+7t7YPDiR1fz0+fl0boOMEJsj1xj laqim75RiG8vC3RJKE6/ylCHtkfV0qS5HDxKxG1z2/w0uFF41OAVbDo1asWazJGO+6Ik OpSru3v96p6kkTDk5qn2ji1NTebJ3Ga7kD4MbRJPbf69QyPT0c+K9jFsAtJ0stt8wwVe vTkg== X-Gm-Message-State: AOJu0YwCHB/ZXfQPN97JrfNsOQF+85y5o1kHNbZ5tr8ps+13YWO+bRf1 gQTwkotSFQIot3OXXljjAiUkinsIwc+7/7MurDgUBHZ78pHoIYFnWFTrHnYD9rk3XnMQ6iHhinE Y X-Received: by 2002:adf:fcce:0:b0:34b:81b3:2c62 with SMTP id ffacd0b85a97d-3552219d1e6mr8183411f8f.35.1716905288645; Tue, 28 May 2024 07:08:08 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.08 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:08 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 22/42] target/arm: Convert XAR to decodetree Date: Tue, 28 May 2024 15:07:33 +0100 Message-Id: <20240528140753.3620597-23-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::332; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x332.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 43 +++++++++++----------------------- 2 files changed, 18 insertions(+), 29 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 1292312a7f9..7f354af25d3 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -654,3 +654,7 @@ SM3TT1A 11001110 010 ..... 10 .. 00 ..... ..... @crypto3i SM3TT1B 11001110 010 ..... 10 .. 01 ..... ..... @crypto3i SM3TT2A 11001110 010 ..... 10 .. 10 ..... ..... @crypto3i SM3TT2B 11001110 010 ..... 10 .. 11 ..... ..... @crypto3i + +### Cryptographic XAR + +XAR 1100 1110 100 rm:5 imm:6 rn:5 rd:5 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index cf3a7dfa99f..75f1e6a7b90 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4688,6 +4688,20 @@ TRANS_FEAT(SM3TT1B, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt1b) TRANS_FEAT(SM3TT2A, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt2a) TRANS_FEAT(SM3TT2B, aa64_sm3, do_crypto3i, a, gen_helper_crypto_sm3tt2b) +static bool trans_XAR(DisasContext *s, arg_XAR *a) +{ + if (!dc_isar_feature(aa64_sha3, s)) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_xar(MO_64, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), a->imm, 16, + vec_full_reg_size(s)); + } + return true; +} + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -13588,34 +13602,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } } -/* Crypto XAR - * 31 21 20 16 15 10 9 5 4 0 - * +-----------------------+------+--------+------+------+ - * | 1 1 0 0 1 1 1 0 1 0 0 | Rm | imm6 | Rn | Rd | - * +-----------------------+------+--------+------+------+ - */ -static void disas_crypto_xar(DisasContext *s, uint32_t insn) -{ - int rm = extract32(insn, 16, 5); - int imm6 = extract32(insn, 10, 6); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - if (!dc_isar_feature(aa64_sha3, s)) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - gen_gvec_xar(MO_64, vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), imm6, 16, - vec_full_reg_size(s)); -} - /* C3.6 Data processing - SIMD, inc Crypto * * As the decode gets a little complex we are using a table based @@ -13644,7 +13630,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0xce800000, 0xffe00000, disas_crypto_xar }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x5e400400, 0xdf60c400, disas_simd_scalar_three_reg_same_fp16 }, From patchwork Tue May 28 14:07:34 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799484 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257332wrz; Tue, 28 May 2024 07:12:57 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCW85Gy3bLOXhI6zQapc78APh3zloL1oMmr3JSxkauIKL5P9heak6VbTXc7QANkon+0VJKhcFAUGJ18SrDoIhZW4 X-Google-Smtp-Source: AGHT+IEbzw6U+L/sgcLfTnq81jGPAU/VBSLNfhsbL9NxE5uOqGx5j0KahLouL/FtEYlI7GAkWOXR X-Received: by 2002:a05:6358:3992:b0:197:8ee2:4ce2 with SMTP id e5c5f4694b2df-197e5468524mr1346082255d.21.1716905577046; Tue, 28 May 2024 07:12:57 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905577; cv=none; d=google.com; s=arc-20160816; b=UQ2olsdRvQc9J8xenPu/i7lXtQo62+MRqwZlYaUKcdu+g8L9wQL7Oy6oDgToyuDwDZ RNHUFDyphbfjhZMmg409QE4V9pPxXu8yjRkbIvesfQLQ7TfEY6/Ak7YGOdQL2xSLFNUN O2z9eSnnV1vrhAH8MGxtl7QtMnvwLn+Jp8PISWsY6V3b+tTENz4OqgvBKuduAAjtWYAK SHDiCxBk02BkI3xlCS+hlTooH1gOFs/Mb8dKDkLQIZNjfsRQGAlufyd0sAaB1sAslY/Y xXGzYdGz5as0SmPUf4zocj/dEXbz6XMhP6IuJouDdDdp/TsPEGRZBj8zAsASEv1Nx0k3 T7Nw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=VQanNBgx1xY3YRgc4AuBmfTchfpgui/MN2iOCvJqyv4=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=iRJE8dMFEVvSfvVJ/kMp7svsi5wnKZkfHTNWG2ro2y5UXyUaAnLBCgCXHJiPGVUXds vMpDgw98Uziaj1n+maU79ml2sqgJt62XFSzA+5IfBKLU3+SWnYQLjBBF0nZAg6DTODLm 5Bn7UC3Y/Dg5x0Dxe4yEV6zgM1KJ8DaMS4Zfpm/j42jVvShY7oVErHOpUFqjFRoK3iLM JL8FrBL9ns8uF1gUUPSP+EjZLuml3Wt2WW/LL38G8+eQg6+aLWPqQEEbrx2o56b0Xjb4 iO99nh0StuMc9vwgdj7S2JD/K//Q/8mFEG6DDw5Cd0DyOaFZD/azpwtM4Yne35f0IB42 k3VQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=rvR8zttx; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ac162b3837si104767496d6.438.2024.05.28.07.12.56 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:57 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=rvR8zttx; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hD-1Y; Tue, 28 May 2024 10:08:20 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUv-0001f2-14 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:17 -0400 Received: from mail-wm1-x331.google.com ([2a00:1450:4864:20::331]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUo-00074f-OK for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: by mail-wm1-x331.google.com with SMTP id 5b1f17b1804b1-4210aa012e5so7390335e9.0 for ; Tue, 28 May 2024 07:08:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905289; x=1717510089; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=VQanNBgx1xY3YRgc4AuBmfTchfpgui/MN2iOCvJqyv4=; b=rvR8zttxEM0Aw6ecSMuxwrpcQToZ0uS3jLsoIcDAyTP9fzIDr4l3Idvw1Dxh0J9HMz yjLwRJ6/L+5WHvtslbbcVKeORH2mA0WAYqtvZOnlDcraPtkuOt2VbSGRr3EeFtPGZNec AN2YMjNlK+rSLx+f0Rl09j7sRXGMGTntQ58cm0gecq5xOXz6+TiW1J4ET7YOdHTMFUoI RUVFFAfFbbxSOwFGnGTdUGLh745F+bapsnjulKGxrVxEBx0Z6h9LmOaeNo0XaxV7gxfS 3GqnbpL936pHw3tpBqIY9Gexm4KvKX4tlsLy//as+9S9pqFv5rsbE/ZPtvxVu01BQWsa lbOw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905289; x=1717510089; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VQanNBgx1xY3YRgc4AuBmfTchfpgui/MN2iOCvJqyv4=; b=DH+Iosy5B7ayXANy/flk40kEfZohIyf8AhJgLh0ESbUMVtiusem68uPmQoDUFy1T/s VBpIdmeYyRH0flWrDn6vy1GAwyKmajKtLVp0uoezHJPzG3p0IKreH4AUuG0L+Wi3tR9v aWr9YEBOlH908WqrXpFcSefR8BGSaEaN2xwinzCtKaw6RQdiyDW2E3uXRxKv3j1FKGpT C0Xt0EuS9yesXxPizvRssAEdsJ79MVtBq6jwfkMwnYQnR+mdQ9F/2FHuHofzssFEupiw BpAsnX7BNt4+gFCBOL6VwGg1JMz9wihGOMpRxcPfso54ut/ARt+AXKy89XWRAZOKNeMJ Z3iQ== X-Gm-Message-State: AOJu0Yz2TMp1TPTapG/XhmEkhk8Cq4cbYtwrl3QQFANWAKIm4NMsCS+f 8ZMccaUDWKYbUU2tSd5pBE/9Gm84Go6l/TZMu2HzrFlr7/JB1qhgBiUMgWirPjEXAUYC9qWco+4 + X-Received: by 2002:a5d:4691:0:b0:357:d4a7:5d52 with SMTP id ffacd0b85a97d-357d4b6a068mr5151042f8f.36.1716905289125; Tue, 28 May 2024 07:08:09 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.08 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:08 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 23/42] target/arm: Convert Advanced SIMD copy to decodetree Date: Tue, 28 May 2024 15:07:34 +0100 Message-Id: <20240528140753.3620597-24-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::331; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x331.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 13 + target/arm/tcg/translate-a64.c | 426 +++++++++++---------------------- 2 files changed, 152 insertions(+), 287 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7f354af25d3..d5bfeae7a82 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -658,3 +658,16 @@ SM3TT2B 11001110 010 ..... 10 .. 11 ..... ..... @crypto3i ### Cryptographic XAR XAR 1100 1110 100 rm:5 imm:6 rn:5 rd:5 + +### Advanced SIMD scalar copy + +DUP_element_s 0101 1110 000 imm:5 0 0000 1 rn:5 rd:5 + +### Advanced SIMD copy + +DUP_element_v 0 q:1 00 1110 000 imm:5 0 0000 1 rn:5 rd:5 +DUP_general 0 q:1 00 1110 000 imm:5 0 0001 1 rn:5 rd:5 +INS_general 0 1 00 1110 000 imm:5 0 0011 1 rn:5 rd:5 +SMOV 0 q:1 00 1110 000 imm:5 0 0101 1 rn:5 rd:5 +UMOV 0 q:1 00 1110 000 imm:5 0 0111 1 rn:5 rd:5 +INS_element 0 1 10 1110 000 di:5 0 si:4 1 rn:5 rd:5 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 75f1e6a7b90..1a12bf22fd8 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4702,6 +4702,145 @@ static bool trans_XAR(DisasContext *s, arg_XAR *a) return true; } +/* + * Advanced SIMD copy + */ + +static bool decode_esz_idx(int imm, MemOp *pesz, unsigned *pidx) +{ + unsigned esz = ctz32(imm); + if (esz <= MO_64) { + *pesz = esz; + *pidx = imm >> (esz + 1); + return true; + } + return false; +} + +static bool trans_DUP_element_s(DisasContext *s, arg_DUP_element_s *a) +{ + MemOp esz; + unsigned idx; + + if (!decode_esz_idx(a->imm, &esz, &idx)) { + return false; + } + if (fp_access_check(s)) { + /* + * This instruction just extracts the specified element and + * zero-extends it into the bottom of the destination register. + */ + TCGv_i64 tmp = tcg_temp_new_i64(); + read_vec_element(s, tmp, a->rn, idx, esz); + write_fp_dreg(s, a->rd, tmp); + } + return true; +} + +static bool trans_DUP_element_v(DisasContext *s, arg_DUP_element_v *a) +{ + MemOp esz; + unsigned idx; + + if (!decode_esz_idx(a->imm, &esz, &idx)) { + return false; + } + if (esz == MO_64 && !a->q) { + return false; + } + if (fp_access_check(s)) { + tcg_gen_gvec_dup_mem(esz, vec_full_reg_offset(s, a->rd), + vec_reg_offset(s, a->rn, idx, esz), + a->q ? 16 : 8, vec_full_reg_size(s)); + } + return true; +} + +static bool trans_DUP_general(DisasContext *s, arg_DUP_general *a) +{ + MemOp esz; + unsigned idx; + + if (!decode_esz_idx(a->imm, &esz, &idx)) { + return false; + } + if (esz == MO_64 && !a->q) { + return false; + } + if (fp_access_check(s)) { + tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), + a->q ? 16 : 8, vec_full_reg_size(s), + cpu_reg(s, a->rn)); + } + return true; +} + +static bool do_smov_umov(DisasContext *s, arg_SMOV *a, MemOp is_signed) +{ + MemOp esz; + unsigned idx; + + if (!decode_esz_idx(a->imm, &esz, &idx)) { + return false; + } + if (is_signed) { + if (esz == MO_64 || (esz == MO_32 && !a->q)) { + return false; + } + } else { + if (esz == MO_64 ? !a->q : a->q) { + return false; + } + } + if (fp_access_check(s)) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + read_vec_element(s, tcg_rd, a->rn, idx, esz | is_signed); + if (is_signed && !a->q) { + tcg_gen_ext32u_i64(tcg_rd, tcg_rd); + } + } + return true; +} + +TRANS(SMOV, do_smov_umov, a, MO_SIGN) +TRANS(UMOV, do_smov_umov, a, 0) + +static bool trans_INS_general(DisasContext *s, arg_INS_general *a) +{ + MemOp esz; + unsigned idx; + + if (!decode_esz_idx(a->imm, &esz, &idx)) { + return false; + } + if (fp_access_check(s)) { + write_vec_element(s, cpu_reg(s, a->rn), a->rd, idx, esz); + clear_vec_high(s, true, a->rd); + } + return true; +} + +static bool trans_INS_element(DisasContext *s, arg_INS_element *a) +{ + MemOp esz; + unsigned didx, sidx; + + if (!decode_esz_idx(a->di, &esz, &didx)) { + return false; + } + sidx = a->si >> esz; + if (fp_access_check(s)) { + TCGv_i64 tmp = tcg_temp_new_i64(); + + read_vec_element(s, tmp, a->rn, sidx, esz); + write_vec_element(s, tmp, a->rd, didx, esz); + + /* INS is considered a 128-bit write for SVE. */ + clear_vec_high(s, true, a->rd); + } + return true; +} + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -7760,268 +7899,6 @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) write_fp_dreg(s, rd, tcg_res); } -/* DUP (Element, Vector) - * - * 31 30 29 21 20 16 15 10 9 5 4 0 - * +---+---+-------------------+--------+-------------+------+------+ - * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 0 1 | Rn | Rd | - * +---+---+-------------------+--------+-------------+------+------+ - * - * size: encoded in imm5 (see ARM ARM LowestSetBit()) - */ -static void handle_simd_dupe(DisasContext *s, int is_q, int rd, int rn, - int imm5) -{ - int size = ctz32(imm5); - int index; - - if (size > 3 || (size == 3 && !is_q)) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - index = imm5 >> (size + 1); - tcg_gen_gvec_dup_mem(size, vec_full_reg_offset(s, rd), - vec_reg_offset(s, rn, index, size), - is_q ? 16 : 8, vec_full_reg_size(s)); -} - -/* DUP (element, scalar) - * 31 21 20 16 15 10 9 5 4 0 - * +-----------------------+--------+-------------+------+------+ - * | 0 1 0 1 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 0 1 | Rn | Rd | - * +-----------------------+--------+-------------+------+------+ - */ -static void handle_simd_dupes(DisasContext *s, int rd, int rn, - int imm5) -{ - int size = ctz32(imm5); - int index; - TCGv_i64 tmp; - - if (size > 3) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - index = imm5 >> (size + 1); - - /* This instruction just extracts the specified element and - * zero-extends it into the bottom of the destination register. - */ - tmp = tcg_temp_new_i64(); - read_vec_element(s, tmp, rn, index, size); - write_fp_dreg(s, rd, tmp); -} - -/* DUP (General) - * - * 31 30 29 21 20 16 15 10 9 5 4 0 - * +---+---+-------------------+--------+-------------+------+------+ - * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 1 1 | Rn | Rd | - * +---+---+-------------------+--------+-------------+------+------+ - * - * size: encoded in imm5 (see ARM ARM LowestSetBit()) - */ -static void handle_simd_dupg(DisasContext *s, int is_q, int rd, int rn, - int imm5) -{ - int size = ctz32(imm5); - uint32_t dofs, oprsz, maxsz; - - if (size > 3 || ((size == 3) && !is_q)) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - dofs = vec_full_reg_offset(s, rd); - oprsz = is_q ? 16 : 8; - maxsz = vec_full_reg_size(s); - - tcg_gen_gvec_dup_i64(size, dofs, oprsz, maxsz, cpu_reg(s, rn)); -} - -/* INS (Element) - * - * 31 21 20 16 15 14 11 10 9 5 4 0 - * +-----------------------+--------+------------+---+------+------+ - * | 0 1 1 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd | - * +-----------------------+--------+------------+---+------+------+ - * - * size: encoded in imm5 (see ARM ARM LowestSetBit()) - * index: encoded in imm5<4:size+1> - */ -static void handle_simd_inse(DisasContext *s, int rd, int rn, - int imm4, int imm5) -{ - int size = ctz32(imm5); - int src_index, dst_index; - TCGv_i64 tmp; - - if (size > 3) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - dst_index = extract32(imm5, 1+size, 5); - src_index = extract32(imm4, size, 4); - - tmp = tcg_temp_new_i64(); - - read_vec_element(s, tmp, rn, src_index, size); - write_vec_element(s, tmp, rd, dst_index, size); - - /* INS is considered a 128-bit write for SVE. */ - clear_vec_high(s, true, rd); -} - - -/* INS (General) - * - * 31 21 20 16 15 10 9 5 4 0 - * +-----------------------+--------+-------------+------+------+ - * | 0 1 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 1 1 1 | Rn | Rd | - * +-----------------------+--------+-------------+------+------+ - * - * size: encoded in imm5 (see ARM ARM LowestSetBit()) - * index: encoded in imm5<4:size+1> - */ -static void handle_simd_insg(DisasContext *s, int rd, int rn, int imm5) -{ - int size = ctz32(imm5); - int idx; - - if (size > 3) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - idx = extract32(imm5, 1 + size, 4 - size); - write_vec_element(s, cpu_reg(s, rn), rd, idx, size); - - /* INS is considered a 128-bit write for SVE. */ - clear_vec_high(s, true, rd); -} - -/* - * UMOV (General) - * SMOV (General) - * - * 31 30 29 21 20 16 15 12 10 9 5 4 0 - * +---+---+-------------------+--------+-------------+------+------+ - * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 1 U 1 1 | Rn | Rd | - * +---+---+-------------------+--------+-------------+------+------+ - * - * U: unsigned when set - * size: encoded in imm5 (see ARM ARM LowestSetBit()) - */ -static void handle_simd_umov_smov(DisasContext *s, int is_q, int is_signed, - int rn, int rd, int imm5) -{ - int size = ctz32(imm5); - int element; - TCGv_i64 tcg_rd; - - /* Check for UnallocatedEncodings */ - if (is_signed) { - if (size > 2 || (size == 2 && !is_q)) { - unallocated_encoding(s); - return; - } - } else { - if (size > 3 - || (size < 3 && is_q) - || (size == 3 && !is_q)) { - unallocated_encoding(s); - return; - } - } - - if (!fp_access_check(s)) { - return; - } - - element = extract32(imm5, 1+size, 4); - - tcg_rd = cpu_reg(s, rd); - read_vec_element(s, tcg_rd, rn, element, size | (is_signed ? MO_SIGN : 0)); - if (is_signed && !is_q) { - tcg_gen_ext32u_i64(tcg_rd, tcg_rd); - } -} - -/* AdvSIMD copy - * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0 - * +---+---+----+-----------------+------+---+------+---+------+------+ - * | 0 | Q | op | 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd | - * +---+---+----+-----------------+------+---+------+---+------+------+ - */ -static void disas_simd_copy(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int imm4 = extract32(insn, 11, 4); - int op = extract32(insn, 29, 1); - int is_q = extract32(insn, 30, 1); - int imm5 = extract32(insn, 16, 5); - - if (op) { - if (is_q) { - /* INS (element) */ - handle_simd_inse(s, rd, rn, imm4, imm5); - } else { - unallocated_encoding(s); - } - } else { - switch (imm4) { - case 0: - /* DUP (element - vector) */ - handle_simd_dupe(s, is_q, rd, rn, imm5); - break; - case 1: - /* DUP (general) */ - handle_simd_dupg(s, is_q, rd, rn, imm5); - break; - case 3: - if (is_q) { - /* INS (general) */ - handle_simd_insg(s, rd, rn, imm5); - } else { - unallocated_encoding(s); - } - break; - case 5: - case 7: - /* UMOV/SMOV (is_q indicates 32/64; imm4 indicates signedness) */ - handle_simd_umov_smov(s, is_q, (imm4 == 5), rn, rd, imm5); - break; - default: - unallocated_encoding(s); - break; - } - } -} - /* AdvSIMD modified immediate * 31 30 29 28 19 18 16 15 12 11 10 9 5 4 0 * +---+---+----+---------------------+-----+-------+----+---+-------+------+ @@ -8085,29 +7962,6 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) } } -/* AdvSIMD scalar copy - * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0 - * +-----+----+-----------------+------+---+------+---+------+------+ - * | 0 1 | op | 1 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd | - * +-----+----+-----------------+------+---+------+---+------+------+ - */ -static void disas_simd_scalar_copy(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int imm4 = extract32(insn, 11, 4); - int imm5 = extract32(insn, 16, 5); - int op = extract32(insn, 29, 1); - - if (op != 0 || imm4 != 0) { - unallocated_encoding(s); - return; - } - - /* DUP (element, scalar) */ - handle_simd_dupes(s, rd, rn, imm5); -} - /* AdvSIMD scalar pairwise * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ @@ -13614,7 +13468,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x0e200000, 0x9f200c00, disas_simd_three_reg_diff }, { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, { 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes }, - { 0x0e000400, 0x9fe08400, disas_simd_copy }, { 0x0f000000, 0x9f000400, disas_simd_indexed }, /* vector indexed */ /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */ { 0x0f000400, 0x9ff80400, disas_simd_mod_imm }, @@ -13627,7 +13480,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, { 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise }, - { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, From patchwork Tue May 28 14:07:35 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799470 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256231wrz; Tue, 28 May 2024 07:11:10 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVpzkFQ52w4V7KzNYqrQBIa4XNbOMaZ5a0GFnpaojeXc7R2mSHynXuM+gvdsHAVYujYwWsNPYkB0FjiVIz6DXgT X-Google-Smtp-Source: AGHT+IFYq+vnZ4OEDt9qL51FrVwalGnG5P76LPUgUgn5NqPBJJFMaR5S3oxDwKnfdfgYhbBIjong X-Received: by 2002:a05:6122:3c54:b0:4e4:e998:bf88 with SMTP id 71dfb90a1353d-4e4f02e3f3dmr11740688e0c.13.1716905469557; Tue, 28 May 2024 07:11:09 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905469; cv=none; d=google.com; s=arc-20160816; b=X7HcDM2pO7CPspMSRPNievaaUza/3yCidhkyRMsP+RNgGUDBaPHoJfAj4cMx5jtmje Jhf625ozFmrh9V5hvoXPPcYCE/Krt2mF5ytbNMIkcXU2HE0binH3sNkP6FFA7Sl+5DAu tnUkHTMhFcHZ1T3KbQ/Pnd52eJcugmlBxSrCI6Kk2p0Gqx4qfeVY/IJPa/qt6Yqi98kV EZZ0WMawZEm1ZEUmWWJZRcAC/R9TIrwEJxBlcIeJsqAcv+KWsxctyMjiJPig6oVpGZpN GDhke7RQIUWLV5YfghJBMfhn5M30md/e/YpDP935fLStS0auB1AQywyhwx8GfiAZS27Z 33QQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=nzpF4AQcfjFkoWhI+EwyRMg4UCuFlPoJuN0iNAJd+X0=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=MJV7frg2A6nMc6jpJjwigxKYE3pJ2a/fli9amjATan74pRAfgsSG1pMUXfIMoDX7qR 7HRpxgfVchtNi5SoguqUlmXvPK1G39iEI4Lz7vLvitqosW44ixUmHcs9jSys6tpR4URa jBSgUmPhb2ScWeVxbJk2GNny4j04FLzjNzkALQ5bKgbNjyoUB9gLUwh09wt1pWKa9J5Q znLs7dqhtTEfgqF5/oyS0D4V5kjY3f4HZUSahv21gUHDAkJHbyFXG0FRjt/uZ7YcRlXV HByQW+PTGqVmbZ1n7mF1HdopVA5bpq0EwBajKs3BvzVBb8sgtMqg4tjg53OlQzRN7nNX rhNw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ILvh9MRz; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a3997b1si2138538137.578.2024.05.28.07.11.09 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:11:09 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ILvh9MRz; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUw-0001fx-AZ; Tue, 28 May 2024 10:08:18 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUu-0001ec-IM for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: from mail-lj1-x230.google.com ([2a00:1450:4864:20::230]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUp-000753-WD for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: by mail-lj1-x230.google.com with SMTP id 38308e7fff4ca-2e724bc466fso8969281fa.3 for ; Tue, 28 May 2024 07:08:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905290; x=1717510090; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=nzpF4AQcfjFkoWhI+EwyRMg4UCuFlPoJuN0iNAJd+X0=; b=ILvh9MRzHxankLFelMDpn+5irFwQ+9AUzM1jka8xTopeX+yNW0VZ3KGnG4YXK+tpRd Vpyg+G2q0vcgtp7wbPSVzItX1GufqTj5VW0KM6OXgW9hzUiFskxddkQQr8+RQUHFqO/9 owOsG9W0+f66ACn14Bnz/HtjUohGoUSRlWZKrQXuNJetqe7SWS3MIa58V22ttrGvVGVL yr14IgJq+jri7UOgXphWfT8/aBQkjIYj7shjv2T4LOlGb2E+vGjR3caR2d/FewOqtbNT lpda6oeIsRe8OqcmuIhS3epu5TymrmY7EFWaESQAFl5T30xXcjp9Jw9p6fry5TGM/KfP aQIA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905290; x=1717510090; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=nzpF4AQcfjFkoWhI+EwyRMg4UCuFlPoJuN0iNAJd+X0=; b=XXlvTa2SAAKuUxonYnIB5yE3JhTHPmuhDxTzdGQ0RUH8/opFOVr4+8v7DvfD+ptGMR rTRDBaxFfxFO+wocakZrVwP7eWyZP/m61HhoK+Gi7vlgcXSBCTv0eiT3q05kfrL9gA17 xTYU12a73edqOHiNVG0Wh0hKWh9ZqQ+ODBmt8jUGJjaKfDC2vqoct3TFeIwvpP/tW5G9 UgV/rH2/OWMOCzJsMPfgN5IJAt346d9IEKoYk+PkMYMwWQou33ztssj4rTxmUzl6XMN8 hhUO2kXP7WqzN2L/OcksELivnIJlxwa5NFn8sg+xPa5Biwi+wYCPixoemGrmMVtN2aiO E2XA== X-Gm-Message-State: AOJu0YwleFgDDCGJxeid5mpFgewkoNYyL3GxVTmOWtjk/X9RLn/Z4r3b Bnlj5pUMqaWHLjSIsAkmkNOGWIc/SvCJ9iXKKB42RqJTbHCfOinD9aEEtsbstio17nkL5IVx2W/ U X-Received: by 2002:a2e:a456:0:b0:2df:faf0:c5e4 with SMTP id 38308e7fff4ca-2e95b0c4efemr113192951fa.23.1716905289712; Tue, 28 May 2024 07:08:09 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.09 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:09 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 24/42] target/arm: Convert FMULX to decodetree Date: Tue, 28 May 2024 15:07:35 +0100 Message-Id: <20240528140753.3620597-25-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::230; envelope-from=peter.maydell@linaro.org; helo=mail-lj1-x230.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Convert all forms (scalar, vector, scalar indexed, vector indexed), which allows us to remove switch table entries elsewhere. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/helper-a64.h | 8 ++ target/arm/tcg/a64.decode | 45 +++++++ target/arm/tcg/translate-a64.c | 221 +++++++++++++++++++++++++++------ target/arm/tcg/vec_helper.c | 39 +++--- 4 files changed, 259 insertions(+), 54 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index 05181653999..b79751a7170 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -132,3 +132,11 @@ DEF_HELPER_4(cpye, void, env, i32, i32, i32) DEF_HELPER_4(cpyfp, void, env, i32, i32, i32) DEF_HELPER_4(cpyfm, void, env, i32, i32, i32) DEF_HELPER_4(cpyfe, void, env, i32, i32, i32) + +DEF_HELPER_FLAGS_5(gvec_fmulx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index d5bfeae7a82..2e0e01be017 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -20,21 +20,44 @@ # %rd 0:5 +%esz_sd 22:1 !function=plus_2 +%hl 11:1 21:1 +%hlm 11:1 20:2 &r rn &ri rd imm &rri_sf rd rn imm sf &i imm +&rrr_e rd rn rm esz +&rrx_e rd rn rm idx esz &qrr_e q rd rn esz &qrrr_e q rd rn rm esz +&qrrx_e q rd rn rm idx esz &qrrrr_e q rd rn rm ra esz +@rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 +@rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd + +@rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm +@rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl +@rrx_d ........ .. . rm:5 .... idx:1 . rn:5 rd:5 &rrx_e esz=3 + @rr_q1e0 ........ ........ ...... rn:5 rd:5 &qrr_e q=1 esz=0 @r2r_q1e0 ........ ........ ...... rm:5 rd:5 &qrrr_e rn=%rd q=1 esz=0 @rrr_q1e0 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=0 @rrr_q1e3 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=3 @rrrr_q1e3 ........ ... rm:5 . ra:5 rn:5 rd:5 &qrrrr_e q=1 esz=3 +@qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 +@qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd + +@qrrx_h . q:1 .. .... .. .. rm:4 .... . . rn:5 rd:5 \ + &qrrx_e esz=1 idx=%hlm +@qrrx_s . q:1 .. .... .. . rm:5 .... . . rn:5 rd:5 \ + &qrrx_e esz=2 idx=%hl +@qrrx_d . q:1 .. .... .. . rm:5 .... idx:1 . rn:5 rd:5 \ + &qrrx_e esz=3 + ### Data Processing - Immediate # PC-rel addressing @@ -671,3 +694,25 @@ INS_general 0 1 00 1110 000 imm:5 0 0011 1 rn:5 rd:5 SMOV 0 q:1 00 1110 000 imm:5 0 0101 1 rn:5 rd:5 UMOV 0 q:1 00 1110 000 imm:5 0 0111 1 rn:5 rd:5 INS_element 0 1 10 1110 000 di:5 0 si:4 1 rn:5 rd:5 + +### Advanced SIMD scalar three same + +FMULX_s 0101 1110 010 ..... 00011 1 ..... ..... @rrr_h +FMULX_s 0101 1110 0.1 ..... 11011 1 ..... ..... @rrr_sd + +### Advanced SIMD three same + +FMULX_v 0.00 1110 010 ..... 00011 1 ..... ..... @qrrr_h +FMULX_v 0.00 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd + +### Advanced SIMD scalar x indexed element + +FMULX_si 0111 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h +FMULX_si 0111 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s +FMULX_si 0111 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d + +### Advanced SIMD vector x indexed element + +FMULX_vi 0.10 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h +FMULX_vi 0.10 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s +FMULX_vi 0.10 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1a12bf22fd8..8cbe6cd70f2 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4841,6 +4841,178 @@ static bool trans_INS_element(DisasContext *s, arg_INS_element *a) return true; } +/* + * Advanced SIMD three same + */ + +typedef struct FPScalar { + void (*gen_h)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); + void (*gen_s)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); + void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); +} FPScalar; + +static bool do_fp3_scalar(DisasContext *s, arg_rrr_e *a, const FPScalar *f) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t0 = read_fp_dreg(s, a->rn); + TCGv_i64 t1 = read_fp_dreg(s, a->rm); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_dreg(s, a->rd, t0); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_sreg(s, a->rn); + TCGv_i32 t1 = read_fp_sreg(s, a->rm); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_sreg(s, a->rd, t0); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_hreg(s, a->rn); + TCGv_i32 t1 = read_fp_hreg(s, a->rm); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + write_fp_sreg(s, a->rd, t0); + } + break; + default: + return false; + } + return true; +} + +static const FPScalar f_scalar_fmulx = { + gen_helper_advsimd_mulxh, + gen_helper_vfp_mulxs, + gen_helper_vfp_mulxd, +}; +TRANS(FMULX_s, do_fp3_scalar, a, &f_scalar_fmulx) + +static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, + gen_helper_gvec_3_ptr * const fns[3]) +{ + MemOp esz = a->esz; + + switch (esz) { + case MO_64: + if (!a->q) { + return false; + } + break; + case MO_32: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + break; + default: + return false; + } + if (fp_access_check(s)) { + gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, + esz == MO_16, 0, fns[esz - 1]); + } + return true; +} + +static gen_helper_gvec_3_ptr * const f_vector_fmulx[3] = { + gen_helper_gvec_fmulx_h, + gen_helper_gvec_fmulx_s, + gen_helper_gvec_fmulx_d, +}; +TRANS(FMULX_v, do_fp3_vector, a, f_vector_fmulx) + +/* + * Advanced SIMD scalar/vector x indexed element + */ + +static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t0 = read_fp_dreg(s, a->rn); + TCGv_i64 t1 = tcg_temp_new_i64(); + + read_vec_element(s, t1, a->rm, a->idx, MO_64); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_dreg(s, a->rd, t0); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_sreg(s, a->rn); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t1, a->rm, a->idx, MO_32); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_sreg(s, a->rd, t0); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_hreg(s, a->rn); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t1, a->rm, a->idx, MO_16); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + write_fp_sreg(s, a->rd, t0); + } + break; + default: + g_assert_not_reached(); + } + return true; +} + +TRANS(FMULX_si, do_fp3_scalar_idx, a, &f_scalar_fmulx) + +static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, + gen_helper_gvec_3_ptr * const fns[3]) +{ + MemOp esz = a->esz; + + switch (esz) { + case MO_64: + if (!a->q) { + return false; + } + break; + case MO_32: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + break; + default: + g_assert_not_reached(); + } + if (fp_access_check(s)) { + gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, + esz == MO_16, a->idx, fns[esz - 1]); + } + return true; +} + +static gen_helper_gvec_3_ptr * const f_vector_idx_fmulx[3] = { + gen_helper_gvec_fmulx_idx_h, + gen_helper_gvec_fmulx_idx_s, + gen_helper_gvec_fmulx_idx_d, +}; +TRANS(FMULX_vi, do_fp3_vector_idx, a, f_vector_idx_fmulx) + + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -9011,9 +9183,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x1a: /* FADD */ gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1b: /* FMULX */ - gen_helper_vfp_mulxd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9058,6 +9227,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x1b: /* FMULX */ g_assert_not_reached(); } @@ -9084,9 +9254,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x1a: /* FADD */ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1b: /* FMULX */ - gen_helper_vfp_mulxs(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9134,6 +9301,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x1b: /* FMULX */ g_assert_not_reached(); } @@ -9172,7 +9340,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) /* Floating point: U, size[1] and opcode indicate operation */ int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6); switch (fpopcode) { - case 0x1b: /* FMULX */ case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ case 0x5d: /* FACGE */ @@ -9183,6 +9350,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x7a: /* FABD */ break; default: + case 0x1b: /* FMULX */ unallocated_encoding(s); return; } @@ -9335,7 +9503,6 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, TCGv_i32 tcg_res; switch (fpopcode) { - case 0x03: /* FMULX */ case 0x04: /* FCMEQ (reg) */ case 0x07: /* FRECPS */ case 0x0f: /* FRSQRTS */ @@ -9346,6 +9513,7 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, case 0x1d: /* FACGT */ break; default: + case 0x03: /* FMULX */ unallocated_encoding(s); return; } @@ -9365,9 +9533,6 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, tcg_res = tcg_temp_new_i32(); switch (fpopcode) { - case 0x03: /* FMULX */ - gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x04: /* FCMEQ (reg) */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9394,6 +9559,7 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x03: /* FMULX */ g_assert_not_reached(); } @@ -11051,7 +11217,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) handle_simd_3same_pair(s, is_q, 0, fpopcode, size ? MO_64 : MO_32, rn, rm, rd); return; - case 0x1b: /* FMULX */ case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ case 0x5d: /* FACGE */ @@ -11097,6 +11262,7 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) return; default: + case 0x1b: /* FMULX */ unallocated_encoding(s); return; } @@ -11441,7 +11607,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x0: /* FMAXNM */ case 0x1: /* FMLA */ case 0x2: /* FADD */ - case 0x3: /* FMULX */ case 0x4: /* FCMEQ */ case 0x6: /* FMAX */ case 0x7: /* FRECPS */ @@ -11467,6 +11632,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) pairwise = true; break; default: + case 0x3: /* FMULX */ unallocated_encoding(s); return; } @@ -11543,9 +11709,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x2: /* FADD */ gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x3: /* FMULX */ - gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x4: /* FCMEQ */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -11597,6 +11760,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x3: /* FMULX */ g_assert_not_reached(); } @@ -12816,7 +12980,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x01: /* FMLA */ case 0x05: /* FMLS */ case 0x09: /* FMUL */ - case 0x19: /* FMULX */ is_fp = 1; break; case 0x1d: /* SQRDMLAH */ @@ -12885,6 +13048,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) /* is_fp, but we pass tcg_env not fp_status. */ break; default: + case 0x19: /* FMULX */ unallocated_encoding(s); return; } @@ -13108,10 +13272,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x09: /* FMUL */ gen_helper_vfp_muld(tcg_res, tcg_op, tcg_idx, fpst); break; - case 0x19: /* FMULX */ - gen_helper_vfp_mulxd(tcg_res, tcg_op, tcg_idx, fpst); - break; default: + case 0x19: /* FMULX */ g_assert_not_reached(); } @@ -13224,24 +13386,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) g_assert_not_reached(); } break; - case 0x19: /* FMULX */ - switch (size) { - case 1: - if (is_scalar) { - gen_helper_advsimd_mulxh(tcg_res, tcg_op, - tcg_idx, fpst); - } else { - gen_helper_advsimd_mulx2h(tcg_res, tcg_op, - tcg_idx, fpst); - } - break; - case 2: - gen_helper_vfp_mulxs(tcg_res, tcg_op, tcg_idx, fpst); - break; - default: - g_assert_not_reached(); - } - break; case 0x0c: /* SQDMULH */ if (size == 1) { gen_helper_neon_qdmulh_s16(tcg_res, tcg_env, @@ -13283,6 +13427,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } break; default: + case 0x19: /* FMULX */ g_assert_not_reached(); } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 1f93510b85c..86845819236 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1248,6 +1248,9 @@ DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16) DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32) #ifdef TARGET_AARCH64 +DO_3OP(gvec_fmulx_h, helper_advsimd_mulxh, float16) +DO_3OP(gvec_fmulx_s, helper_vfp_mulxs, float32) +DO_3OP(gvec_fmulx_d, helper_vfp_mulxd, float64) DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) DO_3OP(gvec_recps_s, helper_recpsf_f32, float32) @@ -1385,7 +1388,7 @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, H8) #undef DO_MLA_IDX -#define DO_FMUL_IDX(NAME, ADD, TYPE, H) \ +#define DO_FMUL_IDX(NAME, ADD, MUL, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ intptr_t i, j, oprsz = simd_oprsz(desc); \ @@ -1395,33 +1398,37 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ TYPE mm = m[H(i + idx)]; \ for (j = 0; j < segment; j++) { \ - d[i + j] = TYPE##_##ADD(d[i + j], \ - TYPE##_mul(n[i + j], mm, stat), stat); \ + d[i + j] = ADD(d[i + j], MUL(n[i + j], mm, stat), stat); \ } \ } \ clear_tail(d, oprsz, simd_maxsz(desc)); \ } -#define float16_nop(N, M, S) (M) -#define float32_nop(N, M, S) (M) -#define float64_nop(N, M, S) (M) +#define nop(N, M, S) (M) -DO_FMUL_IDX(gvec_fmul_idx_h, nop, float16, H2) -DO_FMUL_IDX(gvec_fmul_idx_s, nop, float32, H4) -DO_FMUL_IDX(gvec_fmul_idx_d, nop, float64, H8) +DO_FMUL_IDX(gvec_fmul_idx_h, nop, float16_mul, float16, H2) +DO_FMUL_IDX(gvec_fmul_idx_s, nop, float32_mul, float32, H4) +DO_FMUL_IDX(gvec_fmul_idx_d, nop, float64_mul, float64, H8) + +#ifdef TARGET_AARCH64 + +DO_FMUL_IDX(gvec_fmulx_idx_h, nop, helper_advsimd_mulxh, float16, H2) +DO_FMUL_IDX(gvec_fmulx_idx_s, nop, helper_vfp_mulxs, float32, H4) +DO_FMUL_IDX(gvec_fmulx_idx_d, nop, helper_vfp_mulxd, float64, H8) + +#endif + +#undef nop /* * Non-fused multiply-accumulate operations, for Neon. NB that unlike * the fused ops below they assume accumulate both from and into Vd. */ -DO_FMUL_IDX(gvec_fmla_nf_idx_h, add, float16, H2) -DO_FMUL_IDX(gvec_fmla_nf_idx_s, add, float32, H4) -DO_FMUL_IDX(gvec_fmls_nf_idx_h, sub, float16, H2) -DO_FMUL_IDX(gvec_fmls_nf_idx_s, sub, float32, H4) +DO_FMUL_IDX(gvec_fmla_nf_idx_h, float16_add, float16_mul, float16, H2) +DO_FMUL_IDX(gvec_fmla_nf_idx_s, float32_add, float32_mul, float32, H4) +DO_FMUL_IDX(gvec_fmls_nf_idx_h, float16_sub, float16_mul, float16, H2) +DO_FMUL_IDX(gvec_fmls_nf_idx_s, float32_sub, float32_mul, float32, H4) -#undef float16_nop -#undef float32_nop -#undef float64_nop #undef DO_FMUL_IDX #define DO_FMLA_IDX(NAME, TYPE, H) \ From patchwork Tue May 28 14:07:36 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799487 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257484wrz; Tue, 28 May 2024 07:13:12 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVn+g6U8cROcXB5Dt/58Wg7XN8d/8iSUBc0bPPsqWupD3F3cT49AtnRauYwXNPFB5VPj4HG6BA3tspQi7wzN8ys X-Google-Smtp-Source: AGHT+IFwaHoEMUHVHkKCGRPPs82mWCeZ7vab1vji6SykJmnPphAjXHVronYa4OzFWLin/IIjUBtJ X-Received: by 2002:a05:622a:51:b0:43d:ee0c:c5df with SMTP id d75a77b69052e-43fb0f0705cmr130993151cf.64.1716905592673; Tue, 28 May 2024 07:13:12 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905592; cv=none; d=google.com; s=arc-20160816; b=NjmZT8sLMSszMsvYYtsqJBZRt4AwqhooUkiUP+9cdHVzOkzykHJMWKohtOYIDHs9l3 0psiecHuQfB5c/nCvaJCygNUhIpxolIu+ZoAKxF9CFQ0JQqpHrnGGW+FgsaV5xWcEMUZ koRVIKG/afpM0wCwMJHro7MVYZM8HSvxPC/YQZMuY2+AmXrJ21shBKqqIpPxscggM5Jt tUpL/np/ARtlXNRUKI/pRiCvjLs6/suWMHJJYnw0rbTCSR6l6nKoSOP2h3a/6zom7zsn u2NLYWqFzGMhEVLVKzBqERoJtjCSViyYTGLztwPkJ0ASIj2RD21NM+XJlNkzKz/80T8j VNxg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=CXnH1T2mixpoTkxtiIiA2t1K5JWhAP3FKUem4UK21B0=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=zkrfBh9x/tsmRHi803tsLBvdMN04tMZ4L2SCq9+4Nz60RckZic28kr0S/O7jJCS7tw LBFBVYqSmChLUgZIPRgpbyrI1y32UTPwB6TyeCgifsoW7GmMt4BNm2jx5rjde3dG15g9 a8cz4WDgfNBOcHnJ0cpKJYSIJyElJ5TCugvjGcRkRB1OB2uarObSqMwMxT9RPDr8eCZb Wh/iIOHyeanAFsGfsVICKhsPWRfY3GbxHOHgUpQi22n008DfeG+ZXrDPbdtWdmr59KLu hIXn72Eb+B2Xi8KmHsg73VPIEB0l2h8QJoPL1p0WCJUxQil8TLdWM+XTAo01PxcmE0F4 pqZQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=P5XE4ZXe; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18c5babsi113009981cf.611.2024.05.28.07.13.12 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:12 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=P5XE4ZXe; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUv-0001fP-MY; Tue, 28 May 2024 10:08:17 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUu-0001eO-D6 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: from mail-wr1-x431.google.com ([2a00:1450:4864:20::431]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUp-000754-Lg for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: by mail-wr1-x431.google.com with SMTP id ffacd0b85a97d-354de3c5d00so541262f8f.1 for ; Tue, 28 May 2024 07:08:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905290; x=1717510090; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=CXnH1T2mixpoTkxtiIiA2t1K5JWhAP3FKUem4UK21B0=; b=P5XE4ZXe6aJ67w2cHRGi3rXS92/TKbAMThIh0oV3AVveLwfy5zVwwaJo9aU7AixGYh JydLWVHs5/Jf9RNNd4/n1twiBDNtv+BUERcmA0j/t+80m/T6j00Z2C6oLZxrCLYQiNDg /PHGqeuOaIVQ5nu3xqS2Q5a0rxq1yn9Uk0UbFpNV724xzFPaVmioMn/tEYP9XegdMO7r 3gvzk4esOtoS3/k8oUuieBswDTmbR55AoRSf/3obf/BPyBiCO3OlK0HwSIPtXSPMc7Y9 Bn1i+mqhrJkfXpxruO4ElwoGmV6UuqGmlYqAzCYYDZ1tkKuTWvaHghbqyYK+3mnPnwUU no+w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905290; x=1717510090; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=CXnH1T2mixpoTkxtiIiA2t1K5JWhAP3FKUem4UK21B0=; b=hb9J41PWuSsTnfasvLgpQYm3AQ206LYTRGRWrvPG29zx3J5rqmVUQl1qHAEXrsMXmM 1uBuKrxoFB7ENIg2jZr3oFVm5MegIDXFXugweeUNiyJhi/JcJqlkAkdnKboch6du4oKv cy4PtKA7/Y+rpCLumep+DP0Wo1X9q6Yp5TEaIt3x/CR2Twea6/LMnTGgVHEYH/UZbF6h ue2e4ktviBOeLjkoEuSRjQVcROk/tT3hRlQvBUgzj8T8dLzQDrrw9FShqGOTXiVlRMMw I2byj9c3RhoQhenUauZJZHQ2xzHDGTiQRwKMlOgarLyyKh7BluO8KHt2gVKN00i63tgw 1KPA== X-Gm-Message-State: AOJu0YxyQGJcPum0sh8XEYuHAaX6DD/PcyhAeQwc9TUQWaiVeDpXUw6x Q/9NjVgmatRXgne38OEEGvtQAWcHkIWo58E0JiWdvjb3e62JXZlEFL9slO7nXqm5JDfm7EwrYrS W X-Received: by 2002:a05:6000:247:b0:356:af95:e31d with SMTP id ffacd0b85a97d-356af95e4d7mr7786761f8f.6.1716905290229; Tue, 28 May 2024 07:08:10 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.09 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:10 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 25/42] target/arm: Convert FADD, FSUB, FDIV, FMUL to decodetree Date: Tue, 28 May 2024 15:07:36 +0100 Message-Id: <20240528140753.3620597-26-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::431; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x431.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/helper-a64.h | 4 + target/arm/tcg/translate.h | 5 + target/arm/tcg/a64.decode | 27 +++++ target/arm/tcg/translate-a64.c | 205 +++++++++++++++++---------------- target/arm/tcg/vec_helper.c | 4 + 5 files changed, 143 insertions(+), 102 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index b79751a7170..371388f61b5 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -133,6 +133,10 @@ DEF_HELPER_4(cpyfp, void, env, i32, i32, i32) DEF_HELPER_4(cpyfm, void, env, i32, i32, i32) DEF_HELPER_4(cpyfe, void, env, i32, i32, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fmulx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmulx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmulx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 80e85096a83..ecfa242eef3 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -252,6 +252,11 @@ static inline int shl_12(DisasContext *s, int x) return x << 12; } +static inline int xor_2(DisasContext *s, int x) +{ + return x ^ 2; +} + static inline int neon_3same_fp_size(DisasContext *s, int x) { /* Convert 0==fp32, 1==fp16 into a MO_* value */ diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 2e0e01be017..82daafbef52 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -21,6 +21,7 @@ %rd 0:5 %esz_sd 22:1 !function=plus_2 +%esz_hsd 22:2 !function=xor_2 %hl 11:1 21:1 %hlm 11:1 20:2 @@ -37,6 +38,7 @@ @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd +@rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm @rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl @@ -697,22 +699,47 @@ INS_element 0 1 10 1110 000 di:5 0 si:4 1 rn:5 rd:5 ### Advanced SIMD scalar three same +FADD_s 0001 1110 ..1 ..... 0010 10 ..... ..... @rrr_hsd +FSUB_s 0001 1110 ..1 ..... 0011 10 ..... ..... @rrr_hsd +FDIV_s 0001 1110 ..1 ..... 0001 10 ..... ..... @rrr_hsd +FMUL_s 0001 1110 ..1 ..... 0000 10 ..... ..... @rrr_hsd + FMULX_s 0101 1110 010 ..... 00011 1 ..... ..... @rrr_h FMULX_s 0101 1110 0.1 ..... 11011 1 ..... ..... @rrr_sd ### Advanced SIMD three same +FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h +FADD_v 0.00 1110 0.1 ..... 11010 1 ..... ..... @qrrr_sd + +FSUB_v 0.00 1110 110 ..... 00010 1 ..... ..... @qrrr_h +FSUB_v 0.00 1110 1.1 ..... 11010 1 ..... ..... @qrrr_sd + +FDIV_v 0.10 1110 010 ..... 00111 1 ..... ..... @qrrr_h +FDIV_v 0.10 1110 0.1 ..... 11111 1 ..... ..... @qrrr_sd + +FMUL_v 0.10 1110 010 ..... 00011 1 ..... ..... @qrrr_h +FMUL_v 0.10 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd + FMULX_v 0.00 1110 010 ..... 00011 1 ..... ..... @qrrr_h FMULX_v 0.00 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd ### Advanced SIMD scalar x indexed element +FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h +FMUL_si 0101 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s +FMUL_si 0101 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d + FMULX_si 0111 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h FMULX_si 0111 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s FMULX_si 0111 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d ### Advanced SIMD vector x indexed element +FMUL_vi 0.00 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h +FMUL_vi 0.00 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s +FMUL_vi 0.00 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d + FMULX_vi 0.10 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h FMULX_vi 0.10 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s FMULX_vi 0.10 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 8cbe6cd70f2..97c3d758d62 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4887,6 +4887,34 @@ static bool do_fp3_scalar(DisasContext *s, arg_rrr_e *a, const FPScalar *f) return true; } +static const FPScalar f_scalar_fadd = { + gen_helper_vfp_addh, + gen_helper_vfp_adds, + gen_helper_vfp_addd, +}; +TRANS(FADD_s, do_fp3_scalar, a, &f_scalar_fadd) + +static const FPScalar f_scalar_fsub = { + gen_helper_vfp_subh, + gen_helper_vfp_subs, + gen_helper_vfp_subd, +}; +TRANS(FSUB_s, do_fp3_scalar, a, &f_scalar_fsub) + +static const FPScalar f_scalar_fdiv = { + gen_helper_vfp_divh, + gen_helper_vfp_divs, + gen_helper_vfp_divd, +}; +TRANS(FDIV_s, do_fp3_scalar, a, &f_scalar_fdiv) + +static const FPScalar f_scalar_fmul = { + gen_helper_vfp_mulh, + gen_helper_vfp_muls, + gen_helper_vfp_muld, +}; +TRANS(FMUL_s, do_fp3_scalar, a, &f_scalar_fmul) + static const FPScalar f_scalar_fmulx = { gen_helper_advsimd_mulxh, gen_helper_vfp_mulxs, @@ -4922,6 +4950,34 @@ static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, return true; } +static gen_helper_gvec_3_ptr * const f_vector_fadd[3] = { + gen_helper_gvec_fadd_h, + gen_helper_gvec_fadd_s, + gen_helper_gvec_fadd_d, +}; +TRANS(FADD_v, do_fp3_vector, a, f_vector_fadd) + +static gen_helper_gvec_3_ptr * const f_vector_fsub[3] = { + gen_helper_gvec_fsub_h, + gen_helper_gvec_fsub_s, + gen_helper_gvec_fsub_d, +}; +TRANS(FSUB_v, do_fp3_vector, a, f_vector_fsub) + +static gen_helper_gvec_3_ptr * const f_vector_fdiv[3] = { + gen_helper_gvec_fdiv_h, + gen_helper_gvec_fdiv_s, + gen_helper_gvec_fdiv_d, +}; +TRANS(FDIV_v, do_fp3_vector, a, f_vector_fdiv) + +static gen_helper_gvec_3_ptr * const f_vector_fmul[3] = { + gen_helper_gvec_fmul_h, + gen_helper_gvec_fmul_s, + gen_helper_gvec_fmul_d, +}; +TRANS(FMUL_v, do_fp3_vector, a, f_vector_fmul) + static gen_helper_gvec_3_ptr * const f_vector_fmulx[3] = { gen_helper_gvec_fmulx_h, gen_helper_gvec_fmulx_s, @@ -4975,6 +5031,7 @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) return true; } +TRANS(FMUL_si, do_fp3_scalar_idx, a, &f_scalar_fmul) TRANS(FMULX_si, do_fp3_scalar_idx, a, &f_scalar_fmulx) static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, @@ -5005,6 +5062,13 @@ static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, return true; } +static gen_helper_gvec_3_ptr * const f_vector_idx_fmul[3] = { + gen_helper_gvec_fmul_idx_h, + gen_helper_gvec_fmul_idx_s, + gen_helper_gvec_fmul_idx_d, +}; +TRANS(FMUL_vi, do_fp3_vector_idx, a, f_vector_idx_fmul) + static gen_helper_gvec_3_ptr * const f_vector_idx_fmulx[3] = { gen_helper_gvec_fmulx_idx_h, gen_helper_gvec_fmulx_idx_s, @@ -6827,18 +6891,6 @@ static void handle_fp_2src_single(DisasContext *s, int opcode, tcg_op2 = read_fp_sreg(s, rm); switch (opcode) { - case 0x0: /* FMUL */ - gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1: /* FDIV */ - gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2: /* FADD */ - gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3: /* FSUB */ - gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x4: /* FMAX */ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -6855,6 +6907,12 @@ static void handle_fp_2src_single(DisasContext *s, int opcode, gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_negs(tcg_res, tcg_res); break; + default: + case 0x0: /* FMUL */ + case 0x1: /* FDIV */ + case 0x2: /* FADD */ + case 0x3: /* FSUB */ + g_assert_not_reached(); } write_fp_sreg(s, rd, tcg_res); @@ -6875,18 +6933,6 @@ static void handle_fp_2src_double(DisasContext *s, int opcode, tcg_op2 = read_fp_dreg(s, rm); switch (opcode) { - case 0x0: /* FMUL */ - gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1: /* FDIV */ - gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2: /* FADD */ - gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3: /* FSUB */ - gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x4: /* FMAX */ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -6903,6 +6949,12 @@ static void handle_fp_2src_double(DisasContext *s, int opcode, gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_negd(tcg_res, tcg_res); break; + default: + case 0x0: /* FMUL */ + case 0x1: /* FDIV */ + case 0x2: /* FADD */ + case 0x3: /* FSUB */ + g_assert_not_reached(); } write_fp_dreg(s, rd, tcg_res); @@ -6923,18 +6975,6 @@ static void handle_fp_2src_half(DisasContext *s, int opcode, tcg_op2 = read_fp_hreg(s, rm); switch (opcode) { - case 0x0: /* FMUL */ - gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1: /* FDIV */ - gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2: /* FADD */ - gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3: /* FSUB */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x4: /* FMAX */ gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -6952,6 +6992,10 @@ static void handle_fp_2src_half(DisasContext *s, int opcode, tcg_gen_xori_i32(tcg_res, tcg_res, 0x8000); break; default: + case 0x0: /* FMUL */ + case 0x1: /* FDIV */ + case 0x2: /* FADD */ + case 0x3: /* FSUB */ g_assert_not_reached(); } @@ -9180,9 +9224,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x18: /* FMAXNM */ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1a: /* FADD */ - gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9195,27 +9236,18 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x38: /* FMINNM */ gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x3a: /* FSUB */ - gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x3e: /* FMIN */ gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5b: /* FMUL */ - gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x5c: /* FCMGE */ gen_helper_neon_cge_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x5d: /* FACGE */ gen_helper_neon_acge_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5f: /* FDIV */ - gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7a: /* FABD */ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_absd(tcg_res, tcg_res); @@ -9227,7 +9259,11 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x3a: /* FSUB */ + case 0x5b: /* FMUL */ + case 0x5f: /* FDIV */ g_assert_not_reached(); } @@ -9251,9 +9287,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, tcg_res, fpst); break; - case 0x1a: /* FADD */ - gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9269,27 +9302,18 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x38: /* FMINNM */ gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x3a: /* FSUB */ - gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x3e: /* FMIN */ gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5b: /* FMUL */ - gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x5c: /* FCMGE */ gen_helper_neon_cge_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x5d: /* FACGE */ gen_helper_neon_acge_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5f: /* FDIV */ - gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7a: /* FABD */ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_abss(tcg_res, tcg_res); @@ -9301,7 +9325,11 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x3a: /* FSUB */ + case 0x5b: /* FMUL */ + case 0x5f: /* FDIV */ g_assert_not_reached(); } @@ -11224,15 +11252,11 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x19: /* FMLA */ case 0x39: /* FMLS */ case 0x18: /* FMAXNM */ - case 0x1a: /* FADD */ case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ - case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ - case 0x5b: /* FMUL */ case 0x5c: /* FCMGE */ - case 0x5f: /* FDIV */ case 0x7a: /* FABD */ case 0x7c: /* FCMGT */ if (!fp_access_check(s)) { @@ -11262,7 +11286,11 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) return; default: + case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x3a: /* FSUB */ + case 0x5b: /* FMUL */ + case 0x5f: /* FDIV */ unallocated_encoding(s); return; } @@ -11606,19 +11634,15 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x0: /* FMAXNM */ case 0x1: /* FMLA */ - case 0x2: /* FADD */ case 0x4: /* FCMEQ */ case 0x6: /* FMAX */ case 0x7: /* FRECPS */ case 0x8: /* FMINNM */ case 0x9: /* FMLS */ - case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0xf: /* FRSQRTS */ - case 0x13: /* FMUL */ case 0x14: /* FCMGE */ case 0x15: /* FACGE */ - case 0x17: /* FDIV */ case 0x1a: /* FABD */ case 0x1c: /* FCMGT */ case 0x1d: /* FACGT */ @@ -11632,7 +11656,11 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) pairwise = true; break; default: + case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0xa: /* FSUB */ + case 0x13: /* FMUL */ + case 0x17: /* FDIV */ unallocated_encoding(s); return; } @@ -11706,9 +11734,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, fpst); break; - case 0x2: /* FADD */ - gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x4: /* FCMEQ */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -11728,27 +11753,18 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, fpst); break; - case 0xa: /* FSUB */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0xe: /* FMIN */ gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0xf: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x13: /* FMUL */ - gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x14: /* FCMGE */ gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x15: /* FACGE */ gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x17: /* FDIV */ - gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1a: /* FABD */ gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); @@ -11760,7 +11776,11 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0xa: /* FSUB */ + case 0x13: /* FMUL */ + case 0x17: /* FDIV */ g_assert_not_reached(); } @@ -12979,7 +12999,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x01: /* FMLA */ case 0x05: /* FMLS */ - case 0x09: /* FMUL */ is_fp = 1; break; case 0x1d: /* SQRDMLAH */ @@ -13048,6 +13067,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) /* is_fp, but we pass tcg_env not fp_status. */ break; default: + case 0x09: /* FMUL */ case 0x19: /* FMULX */ unallocated_encoding(s); return; @@ -13269,10 +13289,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) read_vec_element(s, tcg_res, rd, pass, MO_64); gen_helper_vfp_muladdd(tcg_res, tcg_op, tcg_idx, tcg_res, fpst); break; - case 0x09: /* FMUL */ - gen_helper_vfp_muld(tcg_res, tcg_op, tcg_idx, fpst); - break; default: + case 0x09: /* FMUL */ case 0x19: /* FMULX */ g_assert_not_reached(); } @@ -13368,24 +13386,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) g_assert_not_reached(); } break; - case 0x09: /* FMUL */ - switch (size) { - case 1: - if (is_scalar) { - gen_helper_advsimd_mulh(tcg_res, tcg_op, - tcg_idx, fpst); - } else { - gen_helper_advsimd_mul2h(tcg_res, tcg_op, - tcg_idx, fpst); - } - break; - case 2: - gen_helper_vfp_muls(tcg_res, tcg_op, tcg_idx, fpst); - break; - default: - g_assert_not_reached(); - } - break; case 0x0c: /* SQDMULH */ if (size == 1) { gen_helper_neon_qdmulh_s16(tcg_res, tcg_env, @@ -13427,6 +13427,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } break; default: + case 0x09: /* FMUL */ case 0x19: /* FMULX */ g_assert_not_reached(); } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 86845819236..41065363710 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1248,6 +1248,10 @@ DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16) DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32) #ifdef TARGET_AARCH64 +DO_3OP(gvec_fdiv_h, float16_div, float16) +DO_3OP(gvec_fdiv_s, float32_div, float32) +DO_3OP(gvec_fdiv_d, float64_div, float64) + DO_3OP(gvec_fmulx_h, helper_advsimd_mulxh, float16) DO_3OP(gvec_fmulx_s, helper_vfp_mulxs, float32) DO_3OP(gvec_fmulx_d, helper_vfp_mulxd, float64) From patchwork Tue May 28 14:07:37 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799464 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255785wrz; Tue, 28 May 2024 07:10:30 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXJookyGmaj4DRcZs/A7FzRuqNxPI3CNfdRyCUkszcxEPD6e/mo/9TZof8nu9Fi7zgFAOxM8v9GbFjAzqLDtKsr X-Google-Smtp-Source: AGHT+IHe1ygnSVnDDtU97cFQpDyg31sG+aJwxSfTvaaziApgEJDnEWIztBT5PetyqZRzWm9jYVzY X-Received: by 2002:a05:6214:3101:b0:6aa:7049:2895 with SMTP id 6a1803df08f44-6abbbc447admr160093256d6.16.1716905430577; Tue, 28 May 2024 07:10:30 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905430; cv=none; d=google.com; s=arc-20160816; b=GmYiXwO1O8JMsR7IgEsoeBt/Il8sVRFUAdCtBBWZlsbxpkQ1vWlPPzYe1DalT8ijFf zvUd4Dmkm4xzmP6hxvK2OD09wvxcfmG0QQbJ6uDXnxD6fx3pF6IYMu4XCcdhuX3hB8PD 59Pd0GaPw3bTpDKodWowXLmGMJ054uQKvHWG9a28LbZNzyQjs1QRVcvmUHSXgsCliyMq gspADMFcd4OJ7LcnqWNcFZvPkrWFas7WgibNmMGLNhoYX5C4HFw13Sg+Q56GpQKuw/NS Dsn1PqNbOyyI2LtPv1RgP4QdoJSHSI7wLBZjCTKb/iRcAwrb5fyogYT+lIdrwTklOf04 tY8A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=aHiht3qjK9nTz/BmiDNiUp/VCOepZ4hbiSkB0EhpyPY=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=aO1JBdjflCgCRaZ3AvlHB60+zur5ShxvpROxci9yy/SqDaXPZKtXt6DewNn02ztDeF niFwk3J9iE7yJCz5hO2vVliyiFLC9kVViq0hWH02qJmZS2AEoOGoYQscHzv3Qyjk02pL aij2w24NJ3WmAXfjHcQHRNUhmd1JeIyaodvwVFXNQ9AVPGt3bEL6jGN1TZwqtLMDoWYF 9/D+Zxwq6YKN20on1/9XpufSX1S1EBDZqm8wn2zHIylSKnQL/ZtHVoJXqL+EkMbFH8rk sL4IOFWUyNX/6sUy6vEVz7QLZl2n60j2hcqqvGKDMGvGcJAo4IxE6Unu2Y+tYuAPXhpk aS0g==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=fX77is8s; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ac1625f5fcsi105527006d6.349.2024.05.28.07.10.30 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:30 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=fX77is8s; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUx-0001h4-BT; Tue, 28 May 2024 10:08:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUu-0001eZ-GN for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: from mail-wm1-x332.google.com ([2a00:1450:4864:20::332]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUq-00075H-4Y for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: by mail-wm1-x332.google.com with SMTP id 5b1f17b1804b1-420180b58c5so6691415e9.3 for ; Tue, 28 May 2024 07:08:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905291; x=1717510091; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=aHiht3qjK9nTz/BmiDNiUp/VCOepZ4hbiSkB0EhpyPY=; b=fX77is8sQSXww2TGufqujIVc3IvdqeOvFpQJknp5mf6R5kgNdOWONJqCXZgfRwHh5i yUsVwC71ZZGCofZtlImlzw5nHKxmx19dr3BCE95p0CFDmuxsMDPVraaJ8XDVazP+0F5G 6LHMA63NIi3wz9WgOrEvLoXZb7bfikQtowz43dwJ6g5UJ7K1ggEU+p3vHlBu5E6wnv3D 4s264/2qKQ+JKOEdl+F9S6CYp6HjS3TMnX1qBRWO/PkBWn7+p0qdumHwrZvYGc+tdEnJ ztJFyl+wS4QhfJLenRQu+j8a06apaM2aedJxb40j6Ym/vmYaYvqofYAF0Jk4nk00Hgmx yQ8w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905291; x=1717510091; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=aHiht3qjK9nTz/BmiDNiUp/VCOepZ4hbiSkB0EhpyPY=; b=ev9kdpnnum6syr8jbsyD8McYxF3d3KbJFffa1oezMDU7HUuP5+NJwXSpBh2MiM8fMP RsLySTnHofljuEk2jXwKqeTiEFSAOVi+HKKgKtob+xYwcHLh7BNHLrU6NLH1Ymqv9dkC juKRmhKpFG1DTEglPmtbo4r+6q+963tmQxOkJskxcIXFk7x40+X6ozPNpckRa8mVN/Lo sKfu0Tw7UIg/sQVprSOiGSisu5SR+pBAF0NMObdNfkyncxOZzfO6+SY6e+fj/9hg5j1T I6ZQjE/BFsAMfGx06dOy51RpIisam+wEfNMWR4VLvS9QrDi9Qs2hM+Omntu905JvHM3s SlTA== X-Gm-Message-State: AOJu0YygQlLxx+kfIoF4Xn8IElkOThxEq9DAbbq0YY/kjbs39ZYR7c+G /Yq7Xa+3OITO7lH6v+V4v3Jr+dKHauHh139eD2dOBmxHJgD2X4qSZjvoB2wIGjxTg7JtDdMNHKt 6 X-Received: by 2002:a05:600c:4506:b0:421:205f:52de with SMTP id 5b1f17b1804b1-421205f543bmr13251625e9.26.1716905290756; Tue, 28 May 2024 07:08:10 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.10 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:10 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 26/42] target/arm: Convert FMAX, FMIN, FMAXNM, FMINNM to decodetree Date: Tue, 28 May 2024 15:07:37 +0100 Message-Id: <20240528140753.3620597-27-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::332; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x332.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 4 + target/arm/tcg/a64.decode | 17 ++++ target/arm/tcg/translate-a64.c | 168 +++++++++++++++++---------------- target/arm/tcg/vec_helper.c | 4 + 4 files changed, 113 insertions(+), 80 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 2b027333053..7ee15b96512 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -748,15 +748,19 @@ DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 82daafbef52..e2678d919e5 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -704,6 +704,11 @@ FSUB_s 0001 1110 ..1 ..... 0011 10 ..... ..... @rrr_hsd FDIV_s 0001 1110 ..1 ..... 0001 10 ..... ..... @rrr_hsd FMUL_s 0001 1110 ..1 ..... 0000 10 ..... ..... @rrr_hsd +FMAX_s 0001 1110 ..1 ..... 0100 10 ..... ..... @rrr_hsd +FMIN_s 0001 1110 ..1 ..... 0101 10 ..... ..... @rrr_hsd +FMAXNM_s 0001 1110 ..1 ..... 0110 10 ..... ..... @rrr_hsd +FMINNM_s 0001 1110 ..1 ..... 0111 10 ..... ..... @rrr_hsd + FMULX_s 0101 1110 010 ..... 00011 1 ..... ..... @rrr_h FMULX_s 0101 1110 0.1 ..... 11011 1 ..... ..... @rrr_sd @@ -721,6 +726,18 @@ FDIV_v 0.10 1110 0.1 ..... 11111 1 ..... ..... @qrrr_sd FMUL_v 0.10 1110 010 ..... 00011 1 ..... ..... @qrrr_h FMUL_v 0.10 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd +FMAX_v 0.00 1110 010 ..... 00110 1 ..... ..... @qrrr_h +FMAX_v 0.00 1110 0.1 ..... 11110 1 ..... ..... @qrrr_sd + +FMIN_v 0.00 1110 110 ..... 00110 1 ..... ..... @qrrr_h +FMIN_v 0.00 1110 1.1 ..... 11110 1 ..... ..... @qrrr_sd + +FMAXNM_v 0.00 1110 010 ..... 00000 1 ..... ..... @qrrr_h +FMAXNM_v 0.00 1110 0.1 ..... 11000 1 ..... ..... @qrrr_sd + +FMINNM_v 0.00 1110 110 ..... 00000 1 ..... ..... @qrrr_h +FMINNM_v 0.00 1110 1.1 ..... 11000 1 ..... ..... @qrrr_sd + FMULX_v 0.00 1110 010 ..... 00011 1 ..... ..... @qrrr_h FMULX_v 0.00 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 97c3d758d62..6f8207d842b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4915,6 +4915,34 @@ static const FPScalar f_scalar_fmul = { }; TRANS(FMUL_s, do_fp3_scalar, a, &f_scalar_fmul) +static const FPScalar f_scalar_fmax = { + gen_helper_advsimd_maxh, + gen_helper_vfp_maxs, + gen_helper_vfp_maxd, +}; +TRANS(FMAX_s, do_fp3_scalar, a, &f_scalar_fmax) + +static const FPScalar f_scalar_fmin = { + gen_helper_advsimd_minh, + gen_helper_vfp_mins, + gen_helper_vfp_mind, +}; +TRANS(FMIN_s, do_fp3_scalar, a, &f_scalar_fmin) + +static const FPScalar f_scalar_fmaxnm = { + gen_helper_advsimd_maxnumh, + gen_helper_vfp_maxnums, + gen_helper_vfp_maxnumd, +}; +TRANS(FMAXNM_s, do_fp3_scalar, a, &f_scalar_fmaxnm) + +static const FPScalar f_scalar_fminnm = { + gen_helper_advsimd_minnumh, + gen_helper_vfp_minnums, + gen_helper_vfp_minnumd, +}; +TRANS(FMINNM_s, do_fp3_scalar, a, &f_scalar_fminnm) + static const FPScalar f_scalar_fmulx = { gen_helper_advsimd_mulxh, gen_helper_vfp_mulxs, @@ -4978,6 +5006,34 @@ static gen_helper_gvec_3_ptr * const f_vector_fmul[3] = { }; TRANS(FMUL_v, do_fp3_vector, a, f_vector_fmul) +static gen_helper_gvec_3_ptr * const f_vector_fmax[3] = { + gen_helper_gvec_fmax_h, + gen_helper_gvec_fmax_s, + gen_helper_gvec_fmax_d, +}; +TRANS(FMAX_v, do_fp3_vector, a, f_vector_fmax) + +static gen_helper_gvec_3_ptr * const f_vector_fmin[3] = { + gen_helper_gvec_fmin_h, + gen_helper_gvec_fmin_s, + gen_helper_gvec_fmin_d, +}; +TRANS(FMIN_v, do_fp3_vector, a, f_vector_fmin) + +static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[3] = { + gen_helper_gvec_fmaxnum_h, + gen_helper_gvec_fmaxnum_s, + gen_helper_gvec_fmaxnum_d, +}; +TRANS(FMAXNM_v, do_fp3_vector, a, f_vector_fmaxnm) + +static gen_helper_gvec_3_ptr * const f_vector_fminnm[3] = { + gen_helper_gvec_fminnum_h, + gen_helper_gvec_fminnum_s, + gen_helper_gvec_fminnum_d, +}; +TRANS(FMINNM_v, do_fp3_vector, a, f_vector_fminnm) + static gen_helper_gvec_3_ptr * const f_vector_fmulx[3] = { gen_helper_gvec_fmulx_h, gen_helper_gvec_fmulx_s, @@ -6891,18 +6947,6 @@ static void handle_fp_2src_single(DisasContext *s, int opcode, tcg_op2 = read_fp_sreg(s, rm); switch (opcode) { - case 0x4: /* FMAX */ - gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x5: /* FMIN */ - gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x6: /* FMAXNM */ - gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7: /* FMINNM */ - gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x8: /* FNMUL */ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_negs(tcg_res, tcg_res); @@ -6912,6 +6956,10 @@ static void handle_fp_2src_single(DisasContext *s, int opcode, case 0x1: /* FDIV */ case 0x2: /* FADD */ case 0x3: /* FSUB */ + case 0x4: /* FMAX */ + case 0x5: /* FMIN */ + case 0x6: /* FMAXNM */ + case 0x7: /* FMINNM */ g_assert_not_reached(); } @@ -6933,18 +6981,6 @@ static void handle_fp_2src_double(DisasContext *s, int opcode, tcg_op2 = read_fp_dreg(s, rm); switch (opcode) { - case 0x4: /* FMAX */ - gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x5: /* FMIN */ - gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x6: /* FMAXNM */ - gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7: /* FMINNM */ - gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x8: /* FNMUL */ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_vfp_negd(tcg_res, tcg_res); @@ -6954,6 +6990,10 @@ static void handle_fp_2src_double(DisasContext *s, int opcode, case 0x1: /* FDIV */ case 0x2: /* FADD */ case 0x3: /* FSUB */ + case 0x4: /* FMAX */ + case 0x5: /* FMIN */ + case 0x6: /* FMAXNM */ + case 0x7: /* FMINNM */ g_assert_not_reached(); } @@ -6975,18 +7015,6 @@ static void handle_fp_2src_half(DisasContext *s, int opcode, tcg_op2 = read_fp_hreg(s, rm); switch (opcode) { - case 0x4: /* FMAX */ - gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x5: /* FMIN */ - gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x6: /* FMAXNM */ - gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7: /* FMINNM */ - gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x8: /* FNMUL */ gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_gen_xori_i32(tcg_res, tcg_res, 0x8000); @@ -6996,6 +7024,10 @@ static void handle_fp_2src_half(DisasContext *s, int opcode, case 0x1: /* FDIV */ case 0x2: /* FADD */ case 0x3: /* FSUB */ + case 0x4: /* FMAX */ + case 0x5: /* FMIN */ + case 0x6: /* FMAXNM */ + case 0x7: /* FMINNM */ g_assert_not_reached(); } @@ -9221,24 +9253,12 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, tcg_res, fpst); break; - case 0x18: /* FMAXNM */ - gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1e: /* FMAX */ - gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1f: /* FRECPS */ gen_helper_recpsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x38: /* FMINNM */ - gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3e: /* FMIN */ - gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9259,9 +9279,13 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x18: /* FMAXNM */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1e: /* FMAX */ + case 0x38: /* FMINNM */ case 0x3a: /* FSUB */ + case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ case 0x5f: /* FDIV */ g_assert_not_reached(); @@ -9290,21 +9314,9 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1e: /* FMAX */ - gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1f: /* FRECPS */ gen_helper_recpsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x18: /* FMAXNM */ - gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x38: /* FMINNM */ - gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3e: /* FMIN */ - gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9325,9 +9337,13 @@ static void handle_3same_float(DisasContext *s, int size, int elements, gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x18: /* FMAXNM */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1e: /* FMAX */ + case 0x38: /* FMINNM */ case 0x3a: /* FSUB */ + case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ case 0x5f: /* FDIV */ g_assert_not_reached(); @@ -11251,11 +11267,7 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x7d: /* FACGT */ case 0x19: /* FMLA */ case 0x39: /* FMLS */ - case 0x18: /* FMAXNM */ case 0x1c: /* FCMEQ */ - case 0x1e: /* FMAX */ - case 0x38: /* FMINNM */ - case 0x3e: /* FMIN */ case 0x5c: /* FCMGE */ case 0x7a: /* FABD */ case 0x7c: /* FCMGT */ @@ -11286,9 +11298,13 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) return; default: + case 0x18: /* FMAXNM */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1e: /* FMAX */ + case 0x38: /* FMINNM */ case 0x3a: /* FSUB */ + case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ case 0x5f: /* FDIV */ unallocated_encoding(s); @@ -11632,14 +11648,10 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) int pass; switch (fpopcode) { - case 0x0: /* FMAXNM */ case 0x1: /* FMLA */ case 0x4: /* FCMEQ */ - case 0x6: /* FMAX */ case 0x7: /* FRECPS */ - case 0x8: /* FMINNM */ case 0x9: /* FMLS */ - case 0xe: /* FMIN */ case 0xf: /* FRSQRTS */ case 0x14: /* FCMGE */ case 0x15: /* FACGE */ @@ -11656,9 +11668,13 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) pairwise = true; break; default: + case 0x0: /* FMAXNM */ case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0x6: /* FMAX */ + case 0x8: /* FMINNM */ case 0xa: /* FSUB */ + case 0xe: /* FMIN */ case 0x13: /* FMUL */ case 0x17: /* FDIV */ unallocated_encoding(s); @@ -11726,9 +11742,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); switch (fpopcode) { - case 0x0: /* FMAXNM */ - gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1: /* FMLA */ read_vec_element_i32(s, tcg_res, rd, pass, MO_16); gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, @@ -11737,15 +11750,9 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x4: /* FCMEQ */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x6: /* FMAX */ - gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7: /* FRECPS */ gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x8: /* FMINNM */ - gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x9: /* FMLS */ /* As usual for ARM, separate negation for fused multiply-add */ tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); @@ -11753,9 +11760,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, fpst); break; - case 0xe: /* FMIN */ - gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0xf: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -11776,9 +11780,13 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0x0: /* FMAXNM */ case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0x6: /* FMAX */ + case 0x8: /* FMINNM */ case 0xa: /* FSUB */ + case 0xe: /* FMIN */ case 0x13: /* FMUL */ case 0x17: /* FDIV */ g_assert_not_reached(); diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 41065363710..99ef6760719 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1231,15 +1231,19 @@ DO_3OP(gvec_facgt_s, float32_acgt, float32) DO_3OP(gvec_fmax_h, float16_max, float16) DO_3OP(gvec_fmax_s, float32_max, float32) +DO_3OP(gvec_fmax_d, float64_max, float64) DO_3OP(gvec_fmin_h, float16_min, float16) DO_3OP(gvec_fmin_s, float32_min, float32) +DO_3OP(gvec_fmin_d, float64_min, float64) DO_3OP(gvec_fmaxnum_h, float16_maxnum, float16) DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32) +DO_3OP(gvec_fmaxnum_d, float64_maxnum, float64) DO_3OP(gvec_fminnum_h, float16_minnum, float16) DO_3OP(gvec_fminnum_s, float32_minnum, float32) +DO_3OP(gvec_fminnum_d, float64_minnum, float64) DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) From patchwork Tue May 28 14:07:38 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799467 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256076wrz; Tue, 28 May 2024 07:10:54 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVOezoWWg0SclJxzxocsM8c6SuM6dGerHDk9jVyZEKqkgXkFmosoHVhzmrIER/mV7w1epb9+yjXAM9+oyopSNvm X-Google-Smtp-Source: AGHT+IGwH6DI/k0xCmPNI61XQlCPoxDhwOsClVy/kBvPpdwcrvNHf6O/pEj0qLG/9YIvwmHRV57E X-Received: by 2002:a05:6359:5083:b0:198:43cc:4e3b with SMTP id e5c5f4694b2df-19843cc4f32mr1042977355d.28.1716905454315; Tue, 28 May 2024 07:10:54 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905454; cv=none; d=google.com; s=arc-20160816; b=FA/RV3+3qPxn5PrvIFm0PbdiwBm73FU+yMf8VMzMOr1QUvF6b5paKg983LTpApeWWx AULV3maj+0KhzE7RPMOBzGAFFQdidJk1xvIjVOsN126XKu1mZgXj/1qsnYL8E31uNstu +aG1HDNDAU4W0E8UtjbNbiNfloVH3b2RBRx4Pt+VCx5EWu13WYcSlMU0TWSRzx2ze1Yo 3u9PfWd1pW3IYxftlHb9ANqVnmJAfBfgYVaFb0Q9xOLhNkqZbqy5eD0q7mVruo6JJJFs qFXzwSxBBRKbNZ5wenh05HHWZ5wdtDrnXabtGG++kP/gr3rV4itwfg13YEHiYdNKe/+7 BDfw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=h1buDJhz2wCtQFvBdtMaIdKQ5IOooPTw5OQ/DvPjbTs=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=mCIJ4DXhQ2GmcKpGZ6kZcmIhPPVutWcY82iL4AfmWndFkF+ohFsohhxgy6mjcpLpcl Q3MDFmeoyRWGKa+8xUyO2Fqq6wA5jwSLdoh6lkumuTvn9S8bO9JKP4qLlsMds2D2kac1 0SYtgOtj1Idw8Fer4I5psBKnihieVlQeRVBBxcaiyijxhDq9i5ZSlbpH1NUbsJiG6LqV kDLR9Ixy4HI2nGsOoMKtMSkFRRiPd529C976xjy98JCKW+PLJoIJ4mLdJwOTx2DVsgYY nXAguhRnlFmQ50A7a9dp8z2+TXXEmBE/XyXvl1U+Ug4vwdOHF/LxtocHyTtsrWE6nrZ+ Qgeg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=yJE17Fe0; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ac162b52e0si105504466d6.493.2024.05.28.07.10.54 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:54 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=yJE17Fe0; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUx-0001h0-1w; Tue, 28 May 2024 10:08:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUu-0001ex-Tn for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: from mail-wr1-x436.google.com ([2a00:1450:4864:20::436]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUq-00075Q-KH for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:16 -0400 Received: by mail-wr1-x436.google.com with SMTP id ffacd0b85a97d-357ec504fcdso579229f8f.3 for ; Tue, 28 May 2024 07:08:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905291; x=1717510091; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=h1buDJhz2wCtQFvBdtMaIdKQ5IOooPTw5OQ/DvPjbTs=; b=yJE17Fe0Ay6oqiJ9hZMM5qc0w84aKBtBEDiz6A2WpFE70d9EZI5PZLiVBg2Ul5cpi0 mwTdrH5VJ9oSwIz4z1UA4vRpzQlxtallj/bQIyu+zwgivEzJEbNOWUGuMlHhtF8e8S/3 QbM/LBbI0KpklrCYUEs9pKP3rCtaYNplC3SjhKClol9HsREmT5icyK3QwcJUwGrbZMKB J/zkR4xmRXy7UaTg0s/tJA3iU/F++GDqwmH1dPGfu3EFWP2cSviSXDbh81KZbhEh0rXA v29Wl24H/hGoCdy+FSHgbFoSVvs1lB/5f7PJVziTHXssHlo0xFpLVddNr68wUi5JY2gI Epfw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905291; x=1717510091; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=h1buDJhz2wCtQFvBdtMaIdKQ5IOooPTw5OQ/DvPjbTs=; b=f9Uxcyt/ZwdGJcKx1EyITIM5J3wM9T7Aqbuw4dWKAieT9oSaXHoYqlZcJUkpKbzXp5 ajmBHrwSIRjFxl8TqE9BDQqYxct18ZelBxwGBNj1E1WiWy3vsiXENeDgtE83EJkT0miK QuMJnzdstudTh/yRpQWl1LYWzzW4VnXeqFKodE1DHYFrrMF59PZVixBUvipWjVywI7MD Bj4hrjtUIvacS3byOyNitaQb83NHH7FcrkWjp1EVbNuVY6o9vfBUn5Z30WCC2QOyq8LO pVGfWcLgZnX4B4DOPoAErQ9KM5U5WPY62uD/AlcZzuDyV+ussqUjwJA+HI2HSyhP3jUu BQSg== X-Gm-Message-State: AOJu0YwWdkGVb/GPT5IYTAM5+37P9G01ZQaBlQnxmoUio0QrhXBlvTTW BjXNtwxbAZOB6KTLdg4r4Y5Jq6BX0qNnc3w6+/xn2P48LplMr8Ee0vqaRXc2IvWuab+hOdAWKP4 j X-Received: by 2002:a05:6000:401f:b0:354:fd51:45fe with SMTP id ffacd0b85a97d-3552fdf29a8mr9356995f8f.47.1716905291275; Tue, 28 May 2024 07:08:11 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.10 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:10 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 27/42] target/arm: Introduce vfp_load_reg16 Date: Tue, 28 May 2024 15:07:38 +0100 Message-Id: <20240528140753.3620597-28-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::436; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x436.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Load and zero-extend float16 into a TCGv_i32 before all scalar operations. Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20240524232121.284515-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-vfp.c | 39 +++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index b9af03b7c35..8e755fcde8a 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -48,6 +48,12 @@ static inline void vfp_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, tcg_env, vfp_reg_offset(false, reg)); } +static inline void vfp_load_reg16(TCGv_i32 var, int reg) +{ + tcg_gen_ld16u_i32(var, tcg_env, + vfp_reg_offset(false, reg) + HOST_BIG_ENDIAN * 2); +} + /* * The imm8 encodes the sign bit, enough bits to represent an exponent in * the range 01....1xx to 10....0xx, and the most significant 4 bits of @@ -902,8 +908,7 @@ static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - vfp_load_reg32(tmp, a->vn); - tcg_gen_andi_i32(tmp, tmp, 0xffff); + vfp_load_reg16(tmp, a->vn); store_reg(s, a->rt, tmp); } else { /* general purpose register to VFP */ @@ -1453,11 +1458,11 @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR_F16); - vfp_load_reg32(f0, vn); - vfp_load_reg32(f1, vm); + vfp_load_reg16(f0, vn); + vfp_load_reg16(f1, vm); if (reads_vd) { - vfp_load_reg32(fd, vd); + vfp_load_reg16(fd, vd); } fn(fd, f0, f1, fpst); vfp_store_reg32(fd, vd); @@ -1633,7 +1638,7 @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) } f0 = tcg_temp_new_i32(); - vfp_load_reg32(f0, vm); + vfp_load_reg16(f0, vm); fn(f0, f0); vfp_store_reg32(f0, vd); @@ -2106,13 +2111,13 @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - vfp_load_reg32(vn, a->vn); - vfp_load_reg32(vm, a->vm); + vfp_load_reg16(vn, a->vn); + vfp_load_reg16(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negh(vn, vn); } - vfp_load_reg32(vd, a->vd); + vfp_load_reg16(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negh(vd, vd); @@ -2456,11 +2461,11 @@ static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - vfp_load_reg32(vd, a->vd); + vfp_load_reg16(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - vfp_load_reg32(vm, a->vm); + vfp_load_reg16(vm, a->vm); } if (a->e) { @@ -2700,7 +2705,7 @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - vfp_load_reg32(tmp, a->vm); + vfp_load_reg16(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); @@ -2773,7 +2778,7 @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - vfp_load_reg32(tmp, a->vm); + vfp_load_reg16(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); tcg_rmode = gen_set_rmode(FPROUNDING_ZERO, fpst); gen_helper_rinth(tmp, tmp, fpst); @@ -2853,7 +2858,7 @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - vfp_load_reg32(tmp, a->vm); + vfp_load_reg16(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth_exact(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); @@ -3270,7 +3275,7 @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR_F16); vm = tcg_temp_new_i32(); - vfp_load_reg32(vm, a->vm); + vfp_load_reg16(vm, a->vm); if (a->s) { if (a->rz) { @@ -3383,8 +3388,8 @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) /* Insert low half of Vm into high half of Vd */ rm = tcg_temp_new_i32(); rd = tcg_temp_new_i32(); - vfp_load_reg32(rm, a->vm); - vfp_load_reg32(rd, a->vd); + vfp_load_reg16(rm, a->vm); + vfp_load_reg16(rd, a->vd); tcg_gen_deposit_i32(rd, rd, rm, 16, 16); vfp_store_reg32(rd, a->vd); return true; From patchwork Tue May 28 14:07:39 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799463 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255631wrz; Tue, 28 May 2024 07:10:17 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWjkL9mW4Ej7vqVnmhJHuD5K9kkgqxuHH2kK8faNtjUyK9r/XybWaUzkVEzVf/Wj8x/EkeHH0pwzORXupeaiFM3 X-Google-Smtp-Source: AGHT+IE7aiOzDWo1JPd4srOG+Gi8NEnEtNJ07DJCOcoaBq/oXyBkk4a81tUeZG5Z3veQCWSGBTaD X-Received: by 2002:a05:620a:8411:b0:792:bb19:9ca4 with SMTP id af79cd13be357-794ab07ba8emr1318150185a.27.1716905417549; Tue, 28 May 2024 07:10:17 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905417; cv=none; d=google.com; s=arc-20160816; b=EabTA4U0TOhVnKLZ+4ajl9jnTXSUf26nDx5Chp2ASvvrmyGd1OtioUwyNT1yWdV7zL CsgiAekyXc/KwiDcdARN7bTbffLyCnHZFhnxVLBr/DtKXpO0EglN2VZq2lf2Q9aFlAu5 aA0aammStakiRnNWPjrRCeOUTZfVZC2oyJ7ufWDMSc9jGsOoiXV6M/S1Z+twDL0FiG95 IRZzozVaRWCtVT2XjjgNyTbsiJc/Jj7IJ3fJhMRWtDwjguPzOJ4nuemQvr6rihSsRLHu NYT7MunK1fFyxmtPoFsO3jX6g84XpiynCTwbkljUweAkwhApZ8Irx8wEsWWnonpIUREH HBcQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=OwnlNbDMOmxfFj+GYcLImITZ7aufeXIDA8+CMbpckVU=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=ZsSjW6am9Qm4wlpArC8TvvBvdCrIb0vo2ZU7NcYh4L/7+/sxIfqtrOxKoaW8v0QKsU Gwj2vWbaNHDglusKP8HHkLnHAaWQIWhuGF6j5YgHhrUO8ksvnSIRbNTTcgZO7KeEG86z IVoIXxEbTU3N/IXuLPfFt7gA4HzM9pMKAsKPj1PzGfKUCt4PCQG/L8vznwe7+1WkOsLA d7KfT9oLl3wYc+0daiawk+qZHZ9fFHRUDsJNwnhbY+uU4lCRzRVjIDOZzeJhR2YhAXVO Mf97ERzs9jXPZKg8947xLxcXrs2y6mfxMGEntHn4fBsLRWRvaOdEoGXn5jDquBE2eUxO 7yFQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=U4rpnKSn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id af79cd13be357-794b60af1c6si789512985a.136.2024.05.28.07.10.17 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:17 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=U4rpnKSn; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV3-0001jQ-3e; Tue, 28 May 2024 10:08:25 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUw-0001gI-KE for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:18 -0400 Received: from mail-wr1-x42f.google.com ([2a00:1450:4864:20::42f]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUr-00075d-98 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:18 -0400 Received: by mail-wr1-x42f.google.com with SMTP id ffacd0b85a97d-3564a0bea19so826686f8f.2 for ; Tue, 28 May 2024 07:08:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905292; x=1717510092; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=OwnlNbDMOmxfFj+GYcLImITZ7aufeXIDA8+CMbpckVU=; b=U4rpnKSnPAIFNFtqWp9KSWxtci5uMW/vbV7A6WxGu8idcOhed0OwGb+E7jo9WAguiC pqFvpMZhuaWToWJa2oWyYPmvOllR9qWTPGlmtL7/eT+nt2iPN8MUCOgGgZXHB95/PJsu qa3TldKe2jJcQ6GA22B40M3Er62MO/+4KkUPpWzjR1KjtjvM0ackv2A0DlD280HfZDgR ek8UcXt7p9mikaLvaAvBI5GjkTsNZxnv8QTjSfAW7w4bltsSpAgqKeSyzR1XnPuSUF2g kw4+pUcRlgvEm0bFVmQUaL7DV8R262OBlfZZ2x8JwTEaVK6hW4ltanDI/ddlcRtzAXI9 JszQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905292; x=1717510092; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=OwnlNbDMOmxfFj+GYcLImITZ7aufeXIDA8+CMbpckVU=; b=Mm7t8vAYIqRFbsxkvrGcdZynCeibG/VCECllnJYf7qgDEuh51kHngv+E2C1xNYmhUy 68+B7x6jTcxSVhfuto+YX+EpQcNog/bWWxI/qqh7DYUIJcGdex69c67uHHWkVn5JWb2f jBG22PxuCkvlLazG+Mlg2KqFlGW4FXyRWx052ZqpZIo3/k671pdmeuIwMbPV9sMv7pHt ccDTOEpBRcFTdA4BX3hF/AhkkbkaoToXbVQ238TJlIPWYrh/4b5GvvrM5gcGlIRX5+HA hKZIAaE1t03wH3u+ZtecMokWI4TaSVH/MJcLN2V49pDbNRvDSz9ZTLL0/IexQv1jgyJD N5wA== X-Gm-Message-State: AOJu0YzU6QaiMCNdYuyhjKqkn5S+AI3fyea6uHxXHD8QYTYTEP46ZTKJ x3/ThEsgpi8k0jvH5ItzjawyB6sHSj0Wuxc3gyt80FQzHhhSsZs8+QvFln8txUwZgRDczcTUgPC s X-Received: by 2002:a5d:6da6:0:b0:358:ffe5:dce3 with SMTP id ffacd0b85a97d-358ffe5de00mr8829412f8f.49.1716905291887; Tue, 28 May 2024 07:08:11 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.11 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:11 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 28/42] target/arm: Expand vfp neg and abs inline Date: Tue, 28 May 2024 15:07:39 +0100 Message-Id: <20240528140753.3620597-29-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42f; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42f.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 6 ---- target/arm/tcg/translate.h | 30 +++++++++++++++++++ target/arm/tcg/translate-a64.c | 44 +++++++++++++-------------- target/arm/tcg/translate-vfp.c | 54 +++++++++++++++++----------------- target/arm/vfp_helper.c | 30 ------------------- 5 files changed, 79 insertions(+), 85 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 7ee15b96512..0fd01c9c52d 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -132,12 +132,6 @@ DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) -DEF_HELPER_1(vfp_negh, f16, f16) -DEF_HELPER_1(vfp_negs, f32, f32) -DEF_HELPER_1(vfp_negd, f64, f64) -DEF_HELPER_1(vfp_absh, f16, f16) -DEF_HELPER_1(vfp_abss, f32, f32) -DEF_HELPER_1(vfp_absd, f64, f64) DEF_HELPER_2(vfp_sqrth, f16, f16, env) DEF_HELPER_2(vfp_sqrts, f32, f32, env) DEF_HELPER_2(vfp_sqrtd, f64, f64, env) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index ecfa242eef3..b05a9eb6685 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -406,6 +406,36 @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) */ uint64_t vfp_expand_imm(int size, uint8_t imm8); +static inline void gen_vfp_absh(TCGv_i32 d, TCGv_i32 s) +{ + tcg_gen_andi_i32(d, s, INT16_MAX); +} + +static inline void gen_vfp_abss(TCGv_i32 d, TCGv_i32 s) +{ + tcg_gen_andi_i32(d, s, INT32_MAX); +} + +static inline void gen_vfp_absd(TCGv_i64 d, TCGv_i64 s) +{ + tcg_gen_andi_i64(d, s, INT64_MAX); +} + +static inline void gen_vfp_negh(TCGv_i32 d, TCGv_i32 s) +{ + tcg_gen_xori_i32(d, s, 1u << 15); +} + +static inline void gen_vfp_negs(TCGv_i32 d, TCGv_i32 s) +{ + tcg_gen_xori_i32(d, s, 1u << 31); +} + +static inline void gen_vfp_negd(TCGv_i64 d, TCGv_i64 s) +{ + tcg_gen_xori_i64(d, s, 1ull << 63); +} + /* Vector operations shared between ARM and AArch64. */ void gen_gvec_ceq0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 6f8207d842b..878f83298f5 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -6591,10 +6591,10 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) tcg_gen_mov_i32(tcg_res, tcg_op); break; case 0x1: /* FABS */ - tcg_gen_andi_i32(tcg_res, tcg_op, 0x7fff); + gen_vfp_absh(tcg_res, tcg_op); break; case 0x2: /* FNEG */ - tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); + gen_vfp_negh(tcg_res, tcg_op); break; case 0x3: /* FSQRT */ fpst = fpstatus_ptr(FPST_FPCR_F16); @@ -6645,10 +6645,10 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) tcg_gen_mov_i32(tcg_res, tcg_op); goto done; case 0x1: /* FABS */ - gen_helper_vfp_abss(tcg_res, tcg_op); + gen_vfp_abss(tcg_res, tcg_op); goto done; case 0x2: /* FNEG */ - gen_helper_vfp_negs(tcg_res, tcg_op); + gen_vfp_negs(tcg_res, tcg_op); goto done; case 0x3: /* FSQRT */ gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env); @@ -6720,10 +6720,10 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) switch (opcode) { case 0x1: /* FABS */ - gen_helper_vfp_absd(tcg_res, tcg_op); + gen_vfp_absd(tcg_res, tcg_op); goto done; case 0x2: /* FNEG */ - gen_helper_vfp_negd(tcg_res, tcg_op); + gen_vfp_negd(tcg_res, tcg_op); goto done; case 0x3: /* FSQRT */ gen_helper_vfp_sqrtd(tcg_res, tcg_op, tcg_env); @@ -6949,7 +6949,7 @@ static void handle_fp_2src_single(DisasContext *s, int opcode, switch (opcode) { case 0x8: /* FNMUL */ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); - gen_helper_vfp_negs(tcg_res, tcg_res); + gen_vfp_negs(tcg_res, tcg_res); break; default: case 0x0: /* FMUL */ @@ -6983,7 +6983,7 @@ static void handle_fp_2src_double(DisasContext *s, int opcode, switch (opcode) { case 0x8: /* FNMUL */ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); - gen_helper_vfp_negd(tcg_res, tcg_res); + gen_vfp_negd(tcg_res, tcg_res); break; default: case 0x0: /* FMUL */ @@ -7017,7 +7017,7 @@ static void handle_fp_2src_half(DisasContext *s, int opcode, switch (opcode) { case 0x8: /* FNMUL */ gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); - tcg_gen_xori_i32(tcg_res, tcg_res, 0x8000); + gen_vfp_negh(tcg_res, tcg_res); break; default: case 0x0: /* FMUL */ @@ -7102,11 +7102,11 @@ static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, * flipped if it is a negated-input. */ if (o1 == true) { - gen_helper_vfp_negs(tcg_op3, tcg_op3); + gen_vfp_negs(tcg_op3, tcg_op3); } if (o0 != o1) { - gen_helper_vfp_negs(tcg_op1, tcg_op1); + gen_vfp_negs(tcg_op1, tcg_op1); } gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); @@ -7134,11 +7134,11 @@ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, * flipped if it is a negated-input. */ if (o1 == true) { - gen_helper_vfp_negd(tcg_op3, tcg_op3); + gen_vfp_negd(tcg_op3, tcg_op3); } if (o0 != o1) { - gen_helper_vfp_negd(tcg_op1, tcg_op1); + gen_vfp_negd(tcg_op1, tcg_op1); } gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); @@ -9246,7 +9246,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, switch (fpopcode) { case 0x39: /* FMLS */ /* As usual for ARM, separate negation for fused multiply-add */ - gen_helper_vfp_negd(tcg_op1, tcg_op1); + gen_vfp_negd(tcg_op1, tcg_op1); /* fall through */ case 0x19: /* FMLA */ read_vec_element(s, tcg_res, rd, pass, MO_64); @@ -9270,7 +9270,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, break; case 0x7a: /* FABD */ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); - gen_helper_vfp_absd(tcg_res, tcg_res); + gen_vfp_absd(tcg_res, tcg_res); break; case 0x7c: /* FCMGT */ gen_helper_neon_cgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); @@ -9304,7 +9304,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, switch (fpopcode) { case 0x39: /* FMLS */ /* As usual for ARM, separate negation for fused multiply-add */ - gen_helper_vfp_negs(tcg_op1, tcg_op1); + gen_vfp_negs(tcg_op1, tcg_op1); /* fall through */ case 0x19: /* FMLA */ read_vec_element_i32(s, tcg_res, rd, pass, MO_32); @@ -9328,7 +9328,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, break; case 0x7a: /* FABD */ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); - gen_helper_vfp_abss(tcg_res, tcg_res); + gen_vfp_abss(tcg_res, tcg_res); break; case 0x7c: /* FCMGT */ gen_helper_neon_cgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); @@ -9741,10 +9741,10 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, } break; case 0x2f: /* FABS */ - gen_helper_vfp_absd(tcg_rd, tcg_rn); + gen_vfp_absd(tcg_rd, tcg_rn); break; case 0x6f: /* FNEG */ - gen_helper_vfp_negd(tcg_rd, tcg_rn); + gen_vfp_negd(tcg_rd, tcg_rn); break; case 0x7f: /* FSQRT */ gen_helper_vfp_sqrtd(tcg_rd, tcg_rn, tcg_env); @@ -12567,10 +12567,10 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } break; case 0x2f: /* FABS */ - gen_helper_vfp_abss(tcg_res, tcg_op); + gen_vfp_abss(tcg_res, tcg_op); break; case 0x6f: /* FNEG */ - gen_helper_vfp_negs(tcg_res, tcg_op); + gen_vfp_negs(tcg_res, tcg_op); break; case 0x7f: /* FSQRT */ gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env); @@ -13291,7 +13291,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x05: /* FMLS */ /* As usual for ARM, separate negation for fused multiply-add */ - gen_helper_vfp_negd(tcg_op, tcg_op); + gen_vfp_negd(tcg_op, tcg_op); /* fall through */ case 0x01: /* FMLA */ read_vec_element(s, tcg_res, rd, pass, MO_64); diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index 8e755fcde8a..39ec971ff70 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -1768,7 +1768,7 @@ static void gen_VMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_mulh(tmp, vn, vm, fpst); - gen_helper_vfp_negh(tmp, tmp); + gen_vfp_negh(tmp, tmp); gen_helper_vfp_addh(vd, vd, tmp, fpst); } @@ -1786,7 +1786,7 @@ static void gen_VMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_muls(tmp, vn, vm, fpst); - gen_helper_vfp_negs(tmp, tmp); + gen_vfp_negs(tmp, tmp); gen_helper_vfp_adds(vd, vd, tmp, fpst); } @@ -1804,7 +1804,7 @@ static void gen_VMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) TCGv_i64 tmp = tcg_temp_new_i64(); gen_helper_vfp_muld(tmp, vn, vm, fpst); - gen_helper_vfp_negd(tmp, tmp); + gen_vfp_negd(tmp, tmp); gen_helper_vfp_addd(vd, vd, tmp, fpst); } @@ -1824,7 +1824,7 @@ static void gen_VNMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_mulh(tmp, vn, vm, fpst); - gen_helper_vfp_negh(vd, vd); + gen_vfp_negh(vd, vd); gen_helper_vfp_addh(vd, vd, tmp, fpst); } @@ -1844,7 +1844,7 @@ static void gen_VNMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_muls(tmp, vn, vm, fpst); - gen_helper_vfp_negs(vd, vd); + gen_vfp_negs(vd, vd); gen_helper_vfp_adds(vd, vd, tmp, fpst); } @@ -1864,7 +1864,7 @@ static void gen_VNMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) TCGv_i64 tmp = tcg_temp_new_i64(); gen_helper_vfp_muld(tmp, vn, vm, fpst); - gen_helper_vfp_negd(vd, vd); + gen_vfp_negd(vd, vd); gen_helper_vfp_addd(vd, vd, tmp, fpst); } @@ -1879,8 +1879,8 @@ static void gen_VNMLA_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_mulh(tmp, vn, vm, fpst); - gen_helper_vfp_negh(tmp, tmp); - gen_helper_vfp_negh(vd, vd); + gen_vfp_negh(tmp, tmp); + gen_vfp_negh(vd, vd); gen_helper_vfp_addh(vd, vd, tmp, fpst); } @@ -1895,8 +1895,8 @@ static void gen_VNMLA_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_vfp_muls(tmp, vn, vm, fpst); - gen_helper_vfp_negs(tmp, tmp); - gen_helper_vfp_negs(vd, vd); + gen_vfp_negs(tmp, tmp); + gen_vfp_negs(vd, vd); gen_helper_vfp_adds(vd, vd, tmp, fpst); } @@ -1911,8 +1911,8 @@ static void gen_VNMLA_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) TCGv_i64 tmp = tcg_temp_new_i64(); gen_helper_vfp_muld(tmp, vn, vm, fpst); - gen_helper_vfp_negd(tmp, tmp); - gen_helper_vfp_negd(vd, vd); + gen_vfp_negd(tmp, tmp); + gen_vfp_negd(vd, vd); gen_helper_vfp_addd(vd, vd, tmp, fpst); } @@ -1940,7 +1940,7 @@ static void gen_VNMUL_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMUL: -(fn * fm) */ gen_helper_vfp_mulh(vd, vn, vm, fpst); - gen_helper_vfp_negh(vd, vd); + gen_vfp_negh(vd, vd); } static bool trans_VNMUL_hp(DisasContext *s, arg_VNMUL_sp *a) @@ -1952,7 +1952,7 @@ static void gen_VNMUL_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMUL: -(fn * fm) */ gen_helper_vfp_muls(vd, vn, vm, fpst); - gen_helper_vfp_negs(vd, vd); + gen_vfp_negs(vd, vd); } static bool trans_VNMUL_sp(DisasContext *s, arg_VNMUL_sp *a) @@ -1964,7 +1964,7 @@ static void gen_VNMUL_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) { /* VNMUL: -(fn * fm) */ gen_helper_vfp_muld(vd, vn, vm, fpst); - gen_helper_vfp_negd(vd, vd); + gen_vfp_negd(vd, vd); } static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_dp *a) @@ -2115,12 +2115,12 @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vfp_load_reg16(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ - gen_helper_vfp_negh(vn, vn); + gen_vfp_negh(vn, vn); } vfp_load_reg16(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ - gen_helper_vfp_negh(vd, vd); + gen_vfp_negh(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); @@ -2174,12 +2174,12 @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ - gen_helper_vfp_negs(vn, vn); + gen_vfp_negs(vn, vn); } vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ - gen_helper_vfp_negs(vd, vd); + gen_vfp_negs(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); @@ -2239,12 +2239,12 @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) vfp_load_reg64(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ - gen_helper_vfp_negd(vn, vn); + gen_vfp_negd(vn, vn); } vfp_load_reg64(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ - gen_helper_vfp_negd(vd, vd); + gen_vfp_negd(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); @@ -2414,13 +2414,13 @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) DO_VFP_VMOV(VMOV_reg, sp, tcg_gen_mov_i32) DO_VFP_VMOV(VMOV_reg, dp, tcg_gen_mov_i64) -DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh, aa32_fp16_arith) -DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss, aa32_fpsp_v2) -DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd, aa32_fpdp_v2) +DO_VFP_2OP(VABS, hp, gen_vfp_absh, aa32_fp16_arith) +DO_VFP_2OP(VABS, sp, gen_vfp_abss, aa32_fpsp_v2) +DO_VFP_2OP(VABS, dp, gen_vfp_absd, aa32_fpdp_v2) -DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh, aa32_fp16_arith) -DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs, aa32_fpsp_v2) -DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd, aa32_fpdp_v2) +DO_VFP_2OP(VNEG, hp, gen_vfp_negh, aa32_fp16_arith) +DO_VFP_2OP(VNEG, sp, gen_vfp_negs, aa32_fpsp_v2) +DO_VFP_2OP(VNEG, dp, gen_vfp_negd, aa32_fpdp_v2) static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) { diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index 3e5e37abbe8..ce26b8a71a1 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -281,36 +281,6 @@ VFP_BINOP(minnum) VFP_BINOP(maxnum) #undef VFP_BINOP -dh_ctype_f16 VFP_HELPER(neg, h)(dh_ctype_f16 a) -{ - return float16_chs(a); -} - -float32 VFP_HELPER(neg, s)(float32 a) -{ - return float32_chs(a); -} - -float64 VFP_HELPER(neg, d)(float64 a) -{ - return float64_chs(a); -} - -dh_ctype_f16 VFP_HELPER(abs, h)(dh_ctype_f16 a) -{ - return float16_abs(a); -} - -float32 VFP_HELPER(abs, s)(float32 a) -{ - return float32_abs(a); -} - -float64 VFP_HELPER(abs, d)(float64 a) -{ - return float64_abs(a); -} - dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env) { return float16_sqrt(a, &env->vfp.fp_status_f16); From patchwork Tue May 28 14:07:40 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799460 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255415wrz; Tue, 28 May 2024 07:09:57 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCW/p/7c31jjH41TXUqsChQTkSd3Mr9qZ95LVSz3XiPHHmSTHPGVDr3oML8UPVLKjG5s/Dp+A/vSSZxGdts9DO0P X-Google-Smtp-Source: AGHT+IEs/tBTxPCtysUgFgLvqlDjL60FkFbOdwXdpz4rRcbxOYycaQ8lmgvhzO0RIt4jCHKw8H// X-Received: by 2002:a05:622a:1b9e:b0:43e:3bc9:b5e9 with SMTP id d75a77b69052e-43fb0f1436fmr134822801cf.68.1716905397475; Tue, 28 May 2024 07:09:57 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905397; cv=none; d=google.com; s=arc-20160816; b=EnCxvQRYJr95I0iw4vW4vJQUcX/E6PrNv65KXCRm3LlOPUexh/vX1Il8dev9CkthMS TgMsbVgKgwWbdvTym1roB5OSDfTyPvf5JD95rhhilFoS7WXgCgRkf0/QN+JzKryZGq7D /HWvjoE/g6mPviFIAQoNU8zcsyogZB7IuejEp0wsmj6cxLwaSYDe8+kgieJB+J8kWYfS Wg30XkhJSxw7V9XwD5Gp1ivLLw7IA5Xedc77FKrbXjSqBwTuFvT5bAMi0GfVdpboNyjC otUYg+huSfcg+e+zBraI6MmkpOWcti4figwAXoDS52C7k3tYu5yVB803jJNXA8UEV5OF l3ww== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=3hft4bieprUBhQb/iCkHZaG8gsd1lziCQes6UVxdv4c=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=hCwD9oNK1Ywna27RtYzh0KgphomNwZwXFTD/RHXQI7KPBMj2JtOxCWG9EkszghG8J6 vHsohXaq18z9S9mcceANvxYe8fiAYDy1gDwz4pmhVSmvYhUwKDAKUPILCOyNfcH293wy kHuk4yjHchEuD2wKXCEKV5B6RUO1OWiO4OFY3wVIwspmNMC9sUzwQbOdvdT56ivg5Yal Km0XAPk3f6HusaC7jzGVe/zlvx1KDQCMS0xmbGB4yBMIH+Tpm0vNY2pd4Kd2KpwvpNyg ieKLep7m/Q2Z5HarWxyxgwLOhtZzA0CTW1ub2UkdU5gF5IAbzuEkezc5exTySKkHFUix fhsQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="neu/4Ybl"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18b324bsi103024521cf.432.2024.05.28.07.09.57 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:09:57 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="neu/4Ybl"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iB-Ly; Tue, 28 May 2024 10:08:23 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUw-0001fo-11 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:18 -0400 Received: from mail-wr1-x42f.google.com ([2a00:1450:4864:20::42f]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUs-000760-U1 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:17 -0400 Received: by mail-wr1-x42f.google.com with SMTP id ffacd0b85a97d-35b447d78f1so458240f8f.0 for ; Tue, 28 May 2024 07:08:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905293; x=1717510093; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=3hft4bieprUBhQb/iCkHZaG8gsd1lziCQes6UVxdv4c=; b=neu/4YblH9eAhYCg9TMLw413SRpyUD+DquQhmXlAcwhS/dd2gD3yzqG3zs0hIT8bEp bcTvuFhUdC0jKt4dyavn6cGlyXOstwLSnOQcHF2FgafAnIJ1oQmXXbGBo8AJK+U3Cl8G Z4nzpuwTnmJSVEUQiKyTby1wUi+2MXdGhLG/OEsrgD8m4flMzeYyrFR1KOTvnfItgLUK X6bjY56ZWz5grNaLhiNtLB7tmHdhIBZ1yzf+9Nxr8cQfcxmXIvgSdLNjPQ5BK+xnFZlZ /KAJ46C0LlStbOcqFDhVyZiPKcWdpdNfQKuixjC+u9aharSxAqwKD8JDpYdKrvknL7J+ XAdw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905293; x=1717510093; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=3hft4bieprUBhQb/iCkHZaG8gsd1lziCQes6UVxdv4c=; b=GQ5Zwjt2BUxrtOxS1E/Z442VYXYQd2odv5YhsM4SsoJd5RlWAfuJRIAkIgAdd2r5ci zMO5N9Vv8LEEuORrUwgTp740ZjCtccTVJc2+OyYBhO+tWAugmnFE+h0lszxQ/VeooLin 240x8j6/YOxF81CWk0knOIlFeA+3KIx7DTert1nYhOoGdA4KhxkoPowMEB5Ysm7+s7Ve SDnZ08MKgwnwHd5x8EAeBp5BO0mo4O+NELAoacVPIFJc6oBkueI+mcSvxihjpVwZuhh9 vCtCDgkyhtxMPqLqGBgWVun2OtlY4WMIB6zyMe/UoMDP2SSGaPCJy+9AzZ5BZBdY7/ej 6+LA== X-Gm-Message-State: AOJu0Yw4FwZgmKGLhQDFPyITkqBnU83r4fNh9A3VmBx8d6dRgjys0uQX DOy4bO+Yl+Qyxc7Lf928+kcQeNm6BAU/1Sen3yAlowKeRkNBN8xtS5TZbW6xt7tHg2AL1kt1Z+4 R X-Received: by 2002:adf:e507:0:b0:354:dd6a:a5cd with SMTP id ffacd0b85a97d-35506de26e4mr10020690f8f.33.1716905293562; Tue, 28 May 2024 07:08:13 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.12 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:12 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 29/42] target/arm: Convert FNMUL to decodetree Date: Tue, 28 May 2024 15:07:40 +0100 Message-Id: <20240528140753.3620597-30-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::42f; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x42f.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson This is the last instruction within disas_fp_2src, so remove that and its subroutines. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 1 + target/arm/tcg/translate-a64.c | 177 +++++---------------------------- 2 files changed, 27 insertions(+), 151 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index e2678d919e5..cde4b86303d 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -703,6 +703,7 @@ FADD_s 0001 1110 ..1 ..... 0010 10 ..... ..... @rrr_hsd FSUB_s 0001 1110 ..1 ..... 0011 10 ..... ..... @rrr_hsd FDIV_s 0001 1110 ..1 ..... 0001 10 ..... ..... @rrr_hsd FMUL_s 0001 1110 ..1 ..... 0000 10 ..... ..... @rrr_hsd +FNMUL_s 0001 1110 ..1 ..... 1000 10 ..... ..... @rrr_hsd FMAX_s 0001 1110 ..1 ..... 0100 10 ..... ..... @rrr_hsd FMIN_s 0001 1110 ..1 ..... 0101 10 ..... ..... @rrr_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 878f83298f5..5ba30ba7c86 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4950,6 +4950,31 @@ static const FPScalar f_scalar_fmulx = { }; TRANS(FMULX_s, do_fp3_scalar, a, &f_scalar_fmulx) +static void gen_fnmul_h(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_ptr s) +{ + gen_helper_vfp_mulh(d, n, m, s); + gen_vfp_negh(d, d); +} + +static void gen_fnmul_s(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_ptr s) +{ + gen_helper_vfp_muls(d, n, m, s); + gen_vfp_negs(d, d); +} + +static void gen_fnmul_d(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_ptr s) +{ + gen_helper_vfp_muld(d, n, m, s); + gen_vfp_negd(d, d); +} + +static const FPScalar f_scalar_fnmul = { + gen_fnmul_h, + gen_fnmul_s, + gen_fnmul_d, +}; +TRANS(FNMUL_s, do_fp3_scalar, a, &f_scalar_fnmul) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -6932,156 +6957,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) } } -/* Floating-point data-processing (2 source) - single precision */ -static void handle_fp_2src_single(DisasContext *s, int opcode, - int rd, int rn, int rm) -{ - TCGv_i32 tcg_op1; - TCGv_i32 tcg_op2; - TCGv_i32 tcg_res; - TCGv_ptr fpst; - - tcg_res = tcg_temp_new_i32(); - fpst = fpstatus_ptr(FPST_FPCR); - tcg_op1 = read_fp_sreg(s, rn); - tcg_op2 = read_fp_sreg(s, rm); - - switch (opcode) { - case 0x8: /* FNMUL */ - gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst); - gen_vfp_negs(tcg_res, tcg_res); - break; - default: - case 0x0: /* FMUL */ - case 0x1: /* FDIV */ - case 0x2: /* FADD */ - case 0x3: /* FSUB */ - case 0x4: /* FMAX */ - case 0x5: /* FMIN */ - case 0x6: /* FMAXNM */ - case 0x7: /* FMINNM */ - g_assert_not_reached(); - } - - write_fp_sreg(s, rd, tcg_res); -} - -/* Floating-point data-processing (2 source) - double precision */ -static void handle_fp_2src_double(DisasContext *s, int opcode, - int rd, int rn, int rm) -{ - TCGv_i64 tcg_op1; - TCGv_i64 tcg_op2; - TCGv_i64 tcg_res; - TCGv_ptr fpst; - - tcg_res = tcg_temp_new_i64(); - fpst = fpstatus_ptr(FPST_FPCR); - tcg_op1 = read_fp_dreg(s, rn); - tcg_op2 = read_fp_dreg(s, rm); - - switch (opcode) { - case 0x8: /* FNMUL */ - gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst); - gen_vfp_negd(tcg_res, tcg_res); - break; - default: - case 0x0: /* FMUL */ - case 0x1: /* FDIV */ - case 0x2: /* FADD */ - case 0x3: /* FSUB */ - case 0x4: /* FMAX */ - case 0x5: /* FMIN */ - case 0x6: /* FMAXNM */ - case 0x7: /* FMINNM */ - g_assert_not_reached(); - } - - write_fp_dreg(s, rd, tcg_res); -} - -/* Floating-point data-processing (2 source) - half precision */ -static void handle_fp_2src_half(DisasContext *s, int opcode, - int rd, int rn, int rm) -{ - TCGv_i32 tcg_op1; - TCGv_i32 tcg_op2; - TCGv_i32 tcg_res; - TCGv_ptr fpst; - - tcg_res = tcg_temp_new_i32(); - fpst = fpstatus_ptr(FPST_FPCR_F16); - tcg_op1 = read_fp_hreg(s, rn); - tcg_op2 = read_fp_hreg(s, rm); - - switch (opcode) { - case 0x8: /* FNMUL */ - gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); - gen_vfp_negh(tcg_res, tcg_res); - break; - default: - case 0x0: /* FMUL */ - case 0x1: /* FDIV */ - case 0x2: /* FADD */ - case 0x3: /* FSUB */ - case 0x4: /* FMAX */ - case 0x5: /* FMIN */ - case 0x6: /* FMAXNM */ - case 0x7: /* FMINNM */ - g_assert_not_reached(); - } - - write_fp_sreg(s, rd, tcg_res); -} - -/* Floating point data-processing (2 source) - * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 - * +---+---+---+-----------+------+---+------+--------+-----+------+------+ - * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | opcode | 1 0 | Rn | Rd | - * +---+---+---+-----------+------+---+------+--------+-----+------+------+ - */ -static void disas_fp_2src(DisasContext *s, uint32_t insn) -{ - int mos = extract32(insn, 29, 3); - int type = extract32(insn, 22, 2); - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rm = extract32(insn, 16, 5); - int opcode = extract32(insn, 12, 4); - - if (opcode > 8 || mos) { - unallocated_encoding(s); - return; - } - - switch (type) { - case 0: - if (!fp_access_check(s)) { - return; - } - handle_fp_2src_single(s, opcode, rd, rn, rm); - break; - case 1: - if (!fp_access_check(s)) { - return; - } - handle_fp_2src_double(s, opcode, rd, rn, rm); - break; - case 3: - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_fp_2src_half(s, opcode, rd, rn, rm); - break; - default: - unallocated_encoding(s); - } -} - /* Floating-point data-processing (3 source) - single precision */ static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, int rd, int rn, int rm, int ra) @@ -7685,7 +7560,7 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) break; case 2: /* Floating point data-processing (2 source) */ - disas_fp_2src(s, insn); + unallocated_encoding(s); /* in decodetree */ break; case 3: /* Floating point conditional select */ From patchwork Tue May 28 14:07:41 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799468 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256121wrz; Tue, 28 May 2024 07:10:59 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWqOSPpB4m5ihsOYq6h+DFhYF8ZikiFyFek/Fj2Lwv4Npxm3en9P7Ex+evrNo3lkIHdgYjDI9KyF0yJydiuDHKE X-Google-Smtp-Source: AGHT+IFGY2OfAi3gVCIoaKJkHX4l2txFsmP5udE4gBbCC1ClVtTKvJwfgN2ABrwy4DksuEnsQBJt X-Received: by 2002:a05:622a:406:b0:43d:f4e8:3b14 with SMTP id d75a77b69052e-43fb0e6feb2mr127374491cf.39.1716905458861; Tue, 28 May 2024 07:10:58 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905458; cv=none; d=google.com; s=arc-20160816; b=dXRQFcMPPHDYNHyvv62BXHQtwxSmUP0Db23cWAcqM37Oen/wOsECr9tpQDPMixEchv Wx2mz86CmvkIFm7jkr0SFoS70usxJYN/UlJnV3KfNcLDZhKTiH9dWcCTiAnqmnjBwDqW rqTe1o4VSndPhCJX1bBwMicXZNZhQ9p4LTR/h2GUCGtJIWEKBfUw+E/gZw6XVv/7/Yyh FqtCrei4S78Lg21GVUbv+8TMMSvm12/txfkqsSKORz9Jg+o4oZ5rIxYo+oEWIRXkRKLo sTr/VxEIe/y3UBPj0vtyPVyhSJqnb5QaU1Kl8suFV0VOOg4oLdXcAvNOSUiAgYjobbQW MdiQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=ghOm/pfXmE0yZHIRLQnjGK2uukPMYQRC8aInSR+fgXM=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=FKHPj/AnCZgFjk2jZssA+ufA5xeDzgCkkeylYNbwFfcXBfJGgGyNt8ocs+JGIZJz+l FncFKDyRR40m5g4x7fGO6xSVwwExKTjDtWdpVv15Uk3dDQCUla5Gt1WdcJuXIMEeWJZd rXzR4vXkLG80ixUPdUE2aDH1iZURJS7vE27UDXhbzFiE4xurLYF7vvGPneD128FaFvxB Ul8CgiPAYhdZrH7V/QsvNyIIrzgEqcwY8PL5XW96a5bvxGrzFMnovMN/WVKvE14jXHm3 95Od8M9khIvi6vdBACIf6uNdgSwxThZabyjm1X/Q3JFRPFFnc0PwemKhiVNXZDzVBb2/ 0rHQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ZrFaB7Bm; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18ca3b4si116996481cf.659.2024.05.28.07.10.58 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:58 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ZrFaB7Bm; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hV-PQ; Tue, 28 May 2024 10:08:20 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUw-0001gc-PN for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:18 -0400 Received: from mail-wr1-x436.google.com ([2a00:1450:4864:20::436]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUu-00076C-3n for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:18 -0400 Received: by mail-wr1-x436.google.com with SMTP id ffacd0b85a97d-35507dfe221so545258f8f.1 for ; Tue, 28 May 2024 07:08:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905294; x=1717510094; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=ghOm/pfXmE0yZHIRLQnjGK2uukPMYQRC8aInSR+fgXM=; b=ZrFaB7Bme0DF0ox0zDHYCyTF+MZfiJikxpWEUCsWGwsSJTwCvUiW9xkGCmY7w9VNQV DvfFQKJ5hLwKMlURVuNlpDSyTJTHF3l+UTbRf83q4BcNWr47tgFWl43yH5w3uJgdtruf tHnvFE2lW76BqG12KgcHrCrvAem8961q2/o73L4/dA9NQ8oLlU5K2hgAmwo9Y14kPDbb 8cL2ZKZjkwc/D7yXp1D/hrRvkWUL0rw6I+HKRAENcsKVm/OG/Jp9QN+kunT7bBp//1PA uSjbXaV5gaA8Z2eh1jVNzKgxRhp0WPkW1CPwABWzrh4Pu/M9bZidHUMJyh4i9W9H0m6M fzsw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905294; x=1717510094; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=ghOm/pfXmE0yZHIRLQnjGK2uukPMYQRC8aInSR+fgXM=; b=IGMeTtaLduyYFJbyfn42Dt1BClCo4zGhBegQCS4veLujCWTKWb0LfAINkFZW1GXVmS KRNTpcwcOUa8yjfjHoed7pER3TPiF95OgrJ6MwvL0p6h7MwKn+7aohwDKW3ZzNIsDGXt xJx9kOQw37Zk/vikPiP6y2Tsf3Hoeit2t9A20eR43Kq0oUPZ/QfwLVNG/m6EQdfMn7vn VPJRDz9DJZAZ0jHwFpTajuogZyfw6CUxtwPXP7hEtbIL0QBXMjkn5TjAOIPVnMYmYEgC 3p8fXuf7KyWpW8wksMMzpx0ZHNhopJ2zjSZTDH4XDRniqqOMOzYpKRrwouzBo7i2Spb7 WnaA== X-Gm-Message-State: AOJu0YyaQxq0lMNs4JdH26eWxNS19YuWkf+SXTDKlT513wmel3X2cEfX +FYWNXwn9jQgEERQs+wvLaMg+Mjv0cB/T6gPbVfiRBVxpeFnjkdb3fIdRa8n/O6BMbRhSUjZa+f L X-Received: by 2002:a5d:64ec:0:b0:358:8e1:1c30 with SMTP id ffacd0b85a97d-35808e11d39mr8454791f8f.4.1716905294522; Tue, 28 May 2024 07:08:14 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.13 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:14 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 30/42] target/arm: Convert FMLA, FMLS to decodetree Date: Tue, 28 May 2024 15:07:41 +0100 Message-Id: <20240528140753.3620597-31-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::436; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x436.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 2 + target/arm/tcg/a64.decode | 22 +++ target/arm/tcg/translate-a64.c | 241 +++++++++++++++++---------------- target/arm/tcg/vec_helper.c | 14 ++ 4 files changed, 163 insertions(+), 116 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 0fd01c9c52d..e021c185178 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -770,9 +770,11 @@ DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index cde4b86303d..11527bb5e5e 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -742,12 +742,26 @@ FMINNM_v 0.00 1110 1.1 ..... 11000 1 ..... ..... @qrrr_sd FMULX_v 0.00 1110 010 ..... 00011 1 ..... ..... @qrrr_h FMULX_v 0.00 1110 0.1 ..... 11011 1 ..... ..... @qrrr_sd +FMLA_v 0.00 1110 010 ..... 00001 1 ..... ..... @qrrr_h +FMLA_v 0.00 1110 0.1 ..... 11001 1 ..... ..... @qrrr_sd + +FMLS_v 0.00 1110 110 ..... 00001 1 ..... ..... @qrrr_h +FMLS_v 0.00 1110 1.1 ..... 11001 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h FMUL_si 0101 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s FMUL_si 0101 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d +FMLA_si 0101 1111 00 .. .... 0001 . 0 ..... ..... @rrx_h +FMLA_si 0101 1111 10 .. .... 0001 . 0 ..... ..... @rrx_s +FMLA_si 0101 1111 11 0. .... 0001 . 0 ..... ..... @rrx_d + +FMLS_si 0101 1111 00 .. .... 0101 . 0 ..... ..... @rrx_h +FMLS_si 0101 1111 10 .. .... 0101 . 0 ..... ..... @rrx_s +FMLS_si 0101 1111 11 0. .... 0101 . 0 ..... ..... @rrx_d + FMULX_si 0111 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h FMULX_si 0111 1111 10 . ..... 1001 . 0 ..... ..... @rrx_s FMULX_si 0111 1111 11 0 ..... 1001 . 0 ..... ..... @rrx_d @@ -758,6 +772,14 @@ FMUL_vi 0.00 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h FMUL_vi 0.00 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s FMUL_vi 0.00 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d +FMLA_vi 0.00 1111 00 .. .... 0001 . 0 ..... ..... @qrrx_h +FMLA_vi 0.00 1111 10 . ..... 0001 . 0 ..... ..... @qrrx_s +FMLA_vi 0.00 1111 11 0 ..... 0001 . 0 ..... ..... @qrrx_d + +FMLS_vi 0.00 1111 00 .. .... 0101 . 0 ..... ..... @qrrx_h +FMLS_vi 0.00 1111 10 . ..... 0101 . 0 ..... ..... @qrrx_s +FMLS_vi 0.00 1111 11 0 ..... 0101 . 0 ..... ..... @qrrx_d + FMULX_vi 0.10 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h FMULX_vi 0.10 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s FMULX_vi 0.10 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 5ba30ba7c86..f84c12378dc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5066,6 +5066,20 @@ static gen_helper_gvec_3_ptr * const f_vector_fmulx[3] = { }; TRANS(FMULX_v, do_fp3_vector, a, f_vector_fmulx) +static gen_helper_gvec_3_ptr * const f_vector_fmla[3] = { + gen_helper_gvec_vfma_h, + gen_helper_gvec_vfma_s, + gen_helper_gvec_vfma_d, +}; +TRANS(FMLA_v, do_fp3_vector, a, f_vector_fmla) + +static gen_helper_gvec_3_ptr * const f_vector_fmls[3] = { + gen_helper_gvec_vfms_h, + gen_helper_gvec_vfms_s, + gen_helper_gvec_vfms_d, +}; +TRANS(FMLS_v, do_fp3_vector, a, f_vector_fmls) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -5115,6 +5129,64 @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) TRANS(FMUL_si, do_fp3_scalar_idx, a, &f_scalar_fmul) TRANS(FMULX_si, do_fp3_scalar_idx, a, &f_scalar_fmulx) +static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t0 = read_fp_dreg(s, a->rd); + TCGv_i64 t1 = read_fp_dreg(s, a->rn); + TCGv_i64 t2 = tcg_temp_new_i64(); + + read_vec_element(s, t2, a->rm, a->idx, MO_64); + if (neg) { + gen_vfp_negd(t1, t1); + } + gen_helper_vfp_muladdd(t0, t1, t2, t0, fpstatus_ptr(FPST_FPCR)); + write_fp_dreg(s, a->rd, t0); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_sreg(s, a->rd); + TCGv_i32 t1 = read_fp_sreg(s, a->rn); + TCGv_i32 t2 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t2, a->rm, a->idx, MO_32); + if (neg) { + gen_vfp_negs(t1, t1); + } + gen_helper_vfp_muladds(t0, t1, t2, t0, fpstatus_ptr(FPST_FPCR)); + write_fp_sreg(s, a->rd, t0); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_hreg(s, a->rd); + TCGv_i32 t1 = read_fp_hreg(s, a->rn); + TCGv_i32 t2 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t2, a->rm, a->idx, MO_16); + if (neg) { + gen_vfp_negh(t1, t1); + } + gen_helper_advsimd_muladdh(t0, t1, t2, t0, + fpstatus_ptr(FPST_FPCR_F16)); + write_fp_sreg(s, a->rd, t0); + } + break; + default: + g_assert_not_reached(); + } + return true; +} + +TRANS(FMLA_si, do_fmla_scalar_idx, a, false) +TRANS(FMLS_si, do_fmla_scalar_idx, a, true) + static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -5157,6 +5229,42 @@ static gen_helper_gvec_3_ptr * const f_vector_idx_fmulx[3] = { }; TRANS(FMULX_vi, do_fp3_vector_idx, a, f_vector_idx_fmulx) +static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg) +{ + static gen_helper_gvec_4_ptr * const fns[3] = { + gen_helper_gvec_fmla_idx_h, + gen_helper_gvec_fmla_idx_s, + gen_helper_gvec_fmla_idx_d, + }; + MemOp esz = a->esz; + + switch (esz) { + case MO_64: + if (!a->q) { + return false; + } + break; + case MO_32: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + break; + default: + g_assert_not_reached(); + } + if (fp_access_check(s)) { + gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, + esz == MO_16, (a->idx << 1) | neg, + fns[esz - 1]); + } + return true; +} + +TRANS(FMLA_vi, do_fmla_vector_idx, a, false) +TRANS(FMLS_vi, do_fmla_vector_idx, a, true) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the @@ -9119,15 +9227,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element(s, tcg_op2, rm, pass, MO_64); switch (fpopcode) { - case 0x39: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - gen_vfp_negd(tcg_op1, tcg_op1); - /* fall through */ - case 0x19: /* FMLA */ - read_vec_element(s, tcg_res, rd, pass, MO_64); - gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, - tcg_res, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9155,10 +9254,12 @@ static void handle_3same_float(DisasContext *s, int size, int elements, break; default: case 0x18: /* FMAXNM */ + case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ + case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ @@ -9177,15 +9278,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); switch (fpopcode) { - case 0x39: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - gen_vfp_negs(tcg_op1, tcg_op1); - /* fall through */ - case 0x19: /* FMLA */ - read_vec_element_i32(s, tcg_res, rd, pass, MO_32); - gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, - tcg_res, fpst); - break; case 0x1c: /* FCMEQ */ gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -9213,10 +9305,12 @@ static void handle_3same_float(DisasContext *s, int size, int elements, break; default: case 0x18: /* FMAXNM */ + case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ + case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ @@ -11140,8 +11234,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x3f: /* FRSQRTS */ case 0x5d: /* FACGE */ case 0x7d: /* FACGT */ - case 0x19: /* FMLA */ - case 0x39: /* FMLS */ case 0x1c: /* FCMEQ */ case 0x5c: /* FCMGE */ case 0x7a: /* FABD */ @@ -11174,10 +11266,12 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) default: case 0x18: /* FMAXNM */ + case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ + case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ @@ -11523,10 +11617,8 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) int pass; switch (fpopcode) { - case 0x1: /* FMLA */ case 0x4: /* FCMEQ */ case 0x7: /* FRECPS */ - case 0x9: /* FMLS */ case 0xf: /* FRSQRTS */ case 0x14: /* FCMGE */ case 0x15: /* FACGE */ @@ -11544,10 +11636,12 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) break; default: case 0x0: /* FMAXNM */ + case 0x1: /* FMLA */ case 0x2: /* FADD */ case 0x3: /* FMULX */ case 0x6: /* FMAX */ case 0x8: /* FMINNM */ + case 0x9: /* FMLS */ case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0x13: /* FMUL */ @@ -11617,24 +11711,12 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); switch (fpopcode) { - case 0x1: /* FMLA */ - read_vec_element_i32(s, tcg_res, rd, pass, MO_16); - gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, - fpst); - break; case 0x4: /* FCMEQ */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x7: /* FRECPS */ gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x9: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); - read_vec_element_i32(s, tcg_res, rd, pass, MO_16); - gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, - fpst); - break; case 0xf: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -11656,10 +11738,12 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) break; default: case 0x0: /* FMAXNM */ + case 0x1: /* FMLA */ case 0x2: /* FADD */ case 0x3: /* FMULX */ case 0x6: /* FMAX */ case 0x8: /* FMINNM */ + case 0x9: /* FMLS */ case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0x13: /* FMUL */ @@ -12880,10 +12964,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0c: /* SQDMULH */ case 0x0d: /* SQRDMULH */ break; - case 0x01: /* FMLA */ - case 0x05: /* FMLS */ - is_fp = 1; - break; case 0x1d: /* SQRDMLAH */ case 0x1f: /* SQRDMLSH */ if (!dc_isar_feature(aa64_rdm, s)) { @@ -12950,6 +13030,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) /* is_fp, but we pass tcg_env not fp_status. */ break; default: + case 0x01: /* FMLA */ + case 0x05: /* FMLS */ case 0x09: /* FMUL */ case 0x19: /* FMULX */ unallocated_encoding(s); @@ -12958,20 +13040,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (is_fp) { case 1: /* normal fp */ - /* convert insn encoded size to MemOp size */ - switch (size) { - case 0: /* half-precision */ - size = MO_16; - is_fp16 = true; - break; - case MO_32: /* single precision */ - case MO_64: /* double precision */ - break; - default: - unallocated_encoding(s); - return; - } - break; + unallocated_encoding(s); /* in decodetree */ + return; case 2: /* complex fp */ /* Each indexable element is a complex pair. */ @@ -13150,38 +13220,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } if (size == 3) { - TCGv_i64 tcg_idx = tcg_temp_new_i64(); - int pass; - - assert(is_fp && is_q && !is_long); - - read_vec_element(s, tcg_idx, rm, index, MO_64); - - for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op, rn, pass, MO_64); - - switch (16 * u + opcode) { - case 0x05: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - gen_vfp_negd(tcg_op, tcg_op); - /* fall through */ - case 0x01: /* FMLA */ - read_vec_element(s, tcg_res, rd, pass, MO_64); - gen_helper_vfp_muladdd(tcg_res, tcg_op, tcg_idx, tcg_res, fpst); - break; - default: - case 0x09: /* FMUL */ - case 0x19: /* FMULX */ - g_assert_not_reached(); - } - - write_vec_element(s, tcg_res, rd, pass, MO_64); - } - - clear_vec_high(s, !is_scalar, rd); + g_assert_not_reached(); } else if (!is_long) { /* 32 bit floating point, or 16 or 32 bit integer. * For the 16 bit scalar case we use the usual Neon helpers and @@ -13237,38 +13276,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) genfn(tcg_res, tcg_op, tcg_res); break; } - case 0x05: /* FMLS */ - case 0x01: /* FMLA */ - read_vec_element_i32(s, tcg_res, rd, pass, - is_scalar ? size : MO_32); - switch (size) { - case 1: - if (opcode == 0x5) { - /* As usual for ARM, separate negation for fused - * multiply-add */ - tcg_gen_xori_i32(tcg_op, tcg_op, 0x80008000); - } - if (is_scalar) { - gen_helper_advsimd_muladdh(tcg_res, tcg_op, tcg_idx, - tcg_res, fpst); - } else { - gen_helper_advsimd_muladd2h(tcg_res, tcg_op, tcg_idx, - tcg_res, fpst); - } - break; - case 2: - if (opcode == 0x5) { - /* As usual for ARM, separate negation for - * fused multiply-add */ - tcg_gen_xori_i32(tcg_op, tcg_op, 0x80000000); - } - gen_helper_vfp_muladds(tcg_res, tcg_op, tcg_idx, - tcg_res, fpst); - break; - default: - g_assert_not_reached(); - } - break; case 0x0c: /* SQDMULH */ if (size == 1) { gen_helper_neon_qdmulh_s16(tcg_res, tcg_env, @@ -13310,6 +13317,8 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } break; default: + case 0x01: /* FMLA */ + case 0x05: /* FMLS */ case 0x09: /* FMUL */ case 0x19: /* FMULX */ g_assert_not_reached(); diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 99ef6760719..b925b9f21be 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1309,6 +1309,12 @@ static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2, return float32_muladd(op1, op2, dest, 0, stat); } +static float64 float64_muladd_f(float64 dest, float64 op1, float64 op2, + float_status *stat) +{ + return float64_muladd(op1, op2, dest, 0, stat); +} + static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2, float_status *stat) { @@ -1321,6 +1327,12 @@ static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2, return float32_muladd(float32_chs(op1), op2, dest, 0, stat); } +static float64 float64_mulsub_f(float64 dest, float64 op1, float64 op2, + float_status *stat) +{ + return float64_muladd(float64_chs(op1), op2, dest, 0, stat); +} + #define DO_MULADD(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ @@ -1340,9 +1352,11 @@ DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) +DO_MULADD(gvec_vfma_d, float64_muladd_f, float64) DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16) DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) +DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64) /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. From patchwork Tue May 28 14:07:42 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799458 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255339wrz; Tue, 28 May 2024 07:09:51 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXGMa1dreZnvYlgesBL+qK3OQrJxaEDeuSwbwRZcvpYWUvQ/8ZcMo7TYsfISEatXBTRaVxQkGhQlEhHdnZvUF3O X-Google-Smtp-Source: AGHT+IFHX/pkkuQhBB98g9Z+BYI8bO4OTQmHKmOraw/5mR0MKsJKTynkkTdU0Bge7U/qZkdVEMsT X-Received: by 2002:a05:622a:251:b0:43d:faac:56fa with SMTP id d75a77b69052e-43fb0e03d2fmr131681141cf.31.1716905390804; Tue, 28 May 2024 07:09:50 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905390; cv=none; d=google.com; s=arc-20160816; b=dyUesRqGD9uIwLDrcJRHHJlo7N6BVrG074gn4+PtnLKAIzv8kKBusqp2B1DWNGNc/5 MTq66c0P6hDBIiEcbqTbiXnF8Tp2F/S2+C7+lwN+aD0W/oGSTPUbqYu7pIpMprXv9s/U Yp//vlr0dJQ2ggtP2uRvvdMGEdDyO7yfy9IsdOjSPnWBcFJ85SytwurDsHNTNr4bw6I2 sJ/yQnBQC1R+lpiPWJ93D/Txti8rbT/U4hcBwblPOVsNj0kp7SuDjWL/sR8G/S776HgS D22mRW33XdONITO65Cz4uvU6zfCNV4gavS8MI+XArf0Ww3WQzXs5oOMd/Xg5AltoR+cB LzSw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=Ilxot+ayKDPXMmcmCPmQZrNMbEMh27HpTfIFIB0QgVc=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=l9sqldOfHEJDlQHTPw0q18/ghYQCgPgT4IvGE1Ra/aQKH+GCecftYE0G3EPZyEQzJz IgPpy3AqQeFM2pSJ6jIjJfQ2Eee3dnyVPbN1Ls2o6UglzlJFTSSTwCniiEpuhhQYgG0/ ESA0ttEIg27jjzt1J/UtV6zJWcCxQDirqv2zUGrd9tkawrYwkB66enH0dbiCcme7S7BJ zCT/LSm2CkoMc4MEo3a4zh7GYMRO2UIUU8F5M6Nt/cCqW5ztN03Q3glDAV9w4M1Lu5M6 qey/aTrb5Cj4LLIf2nJ0ct9dN33JddM2xsC/fKHL6q4EP7JpcLTkYdSGdkWKyjoFWPXj KZVg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=dNkBDAnK; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18b3d5asi104042341cf.450.2024.05.28.07.09.50 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:09:50 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=dNkBDAnK; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVD-0001ou-J8; Tue, 28 May 2024 10:08:35 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hF-E7 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: from mail-wr1-x434.google.com ([2a00:1450:4864:20::434]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUv-00076K-Oh for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: by mail-wr1-x434.google.com with SMTP id ffacd0b85a97d-35b6467754cso376426f8f.3 for ; Tue, 28 May 2024 07:08:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905295; x=1717510095; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=Ilxot+ayKDPXMmcmCPmQZrNMbEMh27HpTfIFIB0QgVc=; b=dNkBDAnKmNUnhEnpsDFMTPrFVYPO+AvT3GOtN+jZFn7Et0If9CnU38In7x7iyK+RGa DVGmQsMxc3cczuBX4rY1Z0vKWXiqzrLsqXZqVmR77QaK2DUXrxPz03BgBGNgaTsWnMfT mV3who1GKEL09sAFsmmqylvMKCxmKIS3Vb3nXUSS5emKybSntfI0fHgZN4gOWYg1XS+K JVymYiQRf86zsdHCCzE5kBIvVF9p6Nv1Xn2PfnoMTUSfKnjw8hMgRJewaEtjUNQFndo3 5Gt/9E3J5uhvqQVv8EsZtpci3a9FOgkG/cE8boUPAMCBLlz4MhFfkSnqaL2feQy3xhsl muVQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905295; x=1717510095; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Ilxot+ayKDPXMmcmCPmQZrNMbEMh27HpTfIFIB0QgVc=; b=CQaZBwvGeBhhmgYGW6XQ5vVj7sMLij97qxJHybLcLrCI8zaQsqrmosm28n5o7uMUmC LLR+aa+9ItlmttDm6mdB0TtHvhvxdua4A8ysAlBYKSdsZ/On3msX+oKW0qLCTQ4mWPKQ jRg/loDkAsLL50J9OsLqzzVDCh0qhGoI+wMQPSrIWfju6YCamA/z9HbMhWTUhd6e5gey F5/p5hPpbQb+bFCmQPkSKn6is/zX5GPQEHA7yBSv9hb8Pi/61OopOY991zAU4Ut4t/LK Cl/TF/yAf4Cm+uR4N1dPc/vxG+PLee8LKrF/zpPT1SQLPFeqXpCVdfcVNze1DVMYT905 Cwew== X-Gm-Message-State: AOJu0YwMnBcxCEEzRBEAyyCiCOqtp+F34z7iB+oQQtes1zDu8XxCgvfO Nlnr+juHc5xeXVVl8x/b+ZYQj9go0CE8EAqWO6XBg4Le815vezIvbiHzMN8ONXBW40DhTNl6TId S X-Received: by 2002:a5d:60c9:0:b0:355:2ee:9f09 with SMTP id ffacd0b85a97d-35527047af4mr8641708f8f.41.1716905295014; Tue, 28 May 2024 07:08:15 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.14 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:14 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 31/42] target/arm: Convert FCMEQ, FCMGE, FCMGT, FACGE, FACGT to decodetree Date: Tue, 28 May 2024 15:07:42 +0100 Message-Id: <20240528140753.3620597-32-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::434; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x434.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 5 + target/arm/tcg/a64.decode | 30 ++++++ target/arm/tcg/translate-a64.c | 188 +++++++++++++++++++-------------- target/arm/tcg/vec_helper.c | 30 ++++++ 4 files changed, 174 insertions(+), 79 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index e021c185178..8d076011c18 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -727,18 +727,23 @@ DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 11527bb5e5e..7fc3277be67 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -713,6 +713,21 @@ FMINNM_s 0001 1110 ..1 ..... 0111 10 ..... ..... @rrr_hsd FMULX_s 0101 1110 010 ..... 00011 1 ..... ..... @rrr_h FMULX_s 0101 1110 0.1 ..... 11011 1 ..... ..... @rrr_sd +FCMEQ_s 0101 1110 010 ..... 00100 1 ..... ..... @rrr_h +FCMEQ_s 0101 1110 0.1 ..... 11100 1 ..... ..... @rrr_sd + +FCMGE_s 0111 1110 010 ..... 00100 1 ..... ..... @rrr_h +FCMGE_s 0111 1110 0.1 ..... 11100 1 ..... ..... @rrr_sd + +FCMGT_s 0111 1110 110 ..... 00100 1 ..... ..... @rrr_h +FCMGT_s 0111 1110 1.1 ..... 11100 1 ..... ..... @rrr_sd + +FACGE_s 0111 1110 010 ..... 00101 1 ..... ..... @rrr_h +FACGE_s 0111 1110 0.1 ..... 11101 1 ..... ..... @rrr_sd + +FACGT_s 0111 1110 110 ..... 00101 1 ..... ..... @rrr_h +FACGT_s 0111 1110 1.1 ..... 11101 1 ..... ..... @rrr_sd + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -748,6 +763,21 @@ FMLA_v 0.00 1110 0.1 ..... 11001 1 ..... ..... @qrrr_sd FMLS_v 0.00 1110 110 ..... 00001 1 ..... ..... @qrrr_h FMLS_v 0.00 1110 1.1 ..... 11001 1 ..... ..... @qrrr_sd +FCMEQ_v 0.00 1110 010 ..... 00100 1 ..... ..... @qrrr_h +FCMEQ_v 0.00 1110 0.1 ..... 11100 1 ..... ..... @qrrr_sd + +FCMGE_v 0.10 1110 010 ..... 00100 1 ..... ..... @qrrr_h +FCMGE_v 0.10 1110 0.1 ..... 11100 1 ..... ..... @qrrr_sd + +FCMGT_v 0.10 1110 110 ..... 00100 1 ..... ..... @qrrr_h +FCMGT_v 0.10 1110 1.1 ..... 11100 1 ..... ..... @qrrr_sd + +FACGE_v 0.10 1110 010 ..... 00101 1 ..... ..... @qrrr_h +FACGE_v 0.10 1110 0.1 ..... 11101 1 ..... ..... @qrrr_sd + +FACGT_v 0.10 1110 110 ..... 00101 1 ..... ..... @qrrr_h +FACGT_v 0.10 1110 1.1 ..... 11101 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index f84c12378dc..75b0c1a005e 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -4975,6 +4975,41 @@ static const FPScalar f_scalar_fnmul = { }; TRANS(FNMUL_s, do_fp3_scalar, a, &f_scalar_fnmul) +static const FPScalar f_scalar_fcmeq = { + gen_helper_advsimd_ceq_f16, + gen_helper_neon_ceq_f32, + gen_helper_neon_ceq_f64, +}; +TRANS(FCMEQ_s, do_fp3_scalar, a, &f_scalar_fcmeq) + +static const FPScalar f_scalar_fcmge = { + gen_helper_advsimd_cge_f16, + gen_helper_neon_cge_f32, + gen_helper_neon_cge_f64, +}; +TRANS(FCMGE_s, do_fp3_scalar, a, &f_scalar_fcmge) + +static const FPScalar f_scalar_fcmgt = { + gen_helper_advsimd_cgt_f16, + gen_helper_neon_cgt_f32, + gen_helper_neon_cgt_f64, +}; +TRANS(FCMGT_s, do_fp3_scalar, a, &f_scalar_fcmgt) + +static const FPScalar f_scalar_facge = { + gen_helper_advsimd_acge_f16, + gen_helper_neon_acge_f32, + gen_helper_neon_acge_f64, +}; +TRANS(FACGE_s, do_fp3_scalar, a, &f_scalar_facge) + +static const FPScalar f_scalar_facgt = { + gen_helper_advsimd_acgt_f16, + gen_helper_neon_acgt_f32, + gen_helper_neon_acgt_f64, +}; +TRANS(FACGT_s, do_fp3_scalar, a, &f_scalar_facgt) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -5080,6 +5115,41 @@ static gen_helper_gvec_3_ptr * const f_vector_fmls[3] = { }; TRANS(FMLS_v, do_fp3_vector, a, f_vector_fmls) +static gen_helper_gvec_3_ptr * const f_vector_fcmeq[3] = { + gen_helper_gvec_fceq_h, + gen_helper_gvec_fceq_s, + gen_helper_gvec_fceq_d, +}; +TRANS(FCMEQ_v, do_fp3_vector, a, f_vector_fcmeq) + +static gen_helper_gvec_3_ptr * const f_vector_fcmge[3] = { + gen_helper_gvec_fcge_h, + gen_helper_gvec_fcge_s, + gen_helper_gvec_fcge_d, +}; +TRANS(FCMGE_v, do_fp3_vector, a, f_vector_fcmge) + +static gen_helper_gvec_3_ptr * const f_vector_fcmgt[3] = { + gen_helper_gvec_fcgt_h, + gen_helper_gvec_fcgt_s, + gen_helper_gvec_fcgt_d, +}; +TRANS(FCMGT_v, do_fp3_vector, a, f_vector_fcmgt) + +static gen_helper_gvec_3_ptr * const f_vector_facge[3] = { + gen_helper_gvec_facge_h, + gen_helper_gvec_facge_s, + gen_helper_gvec_facge_d, +}; +TRANS(FACGE_v, do_fp3_vector, a, f_vector_facge) + +static gen_helper_gvec_3_ptr * const f_vector_facgt[3] = { + gen_helper_gvec_facgt_h, + gen_helper_gvec_facgt_s, + gen_helper_gvec_facgt_d, +}; +TRANS(FACGT_v, do_fp3_vector, a, f_vector_facgt) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -9227,43 +9297,33 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element(s, tcg_op2, rm, pass, MO_64); switch (fpopcode) { - case 0x1c: /* FCMEQ */ - gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1f: /* FRECPS */ gen_helper_recpsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5c: /* FCMGE */ - gen_helper_neon_cge_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x5d: /* FACGE */ - gen_helper_neon_acge_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7a: /* FABD */ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); gen_vfp_absd(tcg_res, tcg_res); break; - case 0x7c: /* FCMGT */ - gen_helper_neon_cgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7d: /* FACGT */ - gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; default: case 0x18: /* FMAXNM */ case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ + case 0x5c: /* FCMGE */ + case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7c: /* FCMGT */ + case 0x7d: /* FACGT */ g_assert_not_reached(); } @@ -9278,43 +9338,33 @@ static void handle_3same_float(DisasContext *s, int size, int elements, read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); switch (fpopcode) { - case 0x1c: /* FCMEQ */ - gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1f: /* FRECPS */ gen_helper_recpsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x5c: /* FCMGE */ - gen_helper_neon_cge_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x5d: /* FACGE */ - gen_helper_neon_acge_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7a: /* FABD */ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); gen_vfp_abss(tcg_res, tcg_res); break; - case 0x7c: /* FCMGT */ - gen_helper_neon_cgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7d: /* FACGT */ - gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; default: case 0x18: /* FMAXNM */ case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ + case 0x5c: /* FCMGE */ + case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7c: /* FCMGT */ + case 0x7d: /* FACGT */ g_assert_not_reached(); } @@ -9355,15 +9405,15 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ + case 0x7a: /* FABD */ + break; + default: + case 0x1b: /* FMULX */ case 0x5d: /* FACGE */ case 0x7d: /* FACGT */ case 0x1c: /* FCMEQ */ case 0x5c: /* FCMGE */ case 0x7c: /* FCMGT */ - case 0x7a: /* FABD */ - break; - default: - case 0x1b: /* FMULX */ unallocated_encoding(s); return; } @@ -9516,17 +9566,17 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, TCGv_i32 tcg_res; switch (fpopcode) { - case 0x04: /* FCMEQ (reg) */ case 0x07: /* FRECPS */ case 0x0f: /* FRSQRTS */ - case 0x14: /* FCMGE (reg) */ - case 0x15: /* FACGE */ case 0x1a: /* FABD */ - case 0x1c: /* FCMGT (reg) */ - case 0x1d: /* FACGT */ break; default: case 0x03: /* FMULX */ + case 0x04: /* FCMEQ (reg) */ + case 0x14: /* FCMGE (reg) */ + case 0x15: /* FACGE */ + case 0x1c: /* FCMGT (reg) */ + case 0x1d: /* FACGT */ unallocated_encoding(s); return; } @@ -9546,33 +9596,23 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, tcg_res = tcg_temp_new_i32(); switch (fpopcode) { - case 0x04: /* FCMEQ (reg) */ - gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x07: /* FRECPS */ gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0x0f: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x14: /* FCMGE (reg) */ - gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x15: /* FACGE */ - gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1a: /* FABD */ gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); break; - case 0x1c: /* FCMGT (reg) */ - gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1d: /* FACGT */ - gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; default: case 0x03: /* FMULX */ + case 0x04: /* FCMEQ (reg) */ + case 0x14: /* FCMGE (reg) */ + case 0x15: /* FACGE */ + case 0x1c: /* FCMGT (reg) */ + case 0x1d: /* FACGT */ g_assert_not_reached(); } @@ -11232,12 +11272,7 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) return; case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ - case 0x5d: /* FACGE */ - case 0x7d: /* FACGT */ - case 0x1c: /* FCMEQ */ - case 0x5c: /* FCMGE */ case 0x7a: /* FABD */ - case 0x7c: /* FCMGT */ if (!fp_access_check(s)) { return; } @@ -11269,13 +11304,18 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x19: /* FMLA */ case 0x1a: /* FADD */ case 0x1b: /* FMULX */ + case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ case 0x38: /* FMINNM */ case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x5b: /* FMUL */ + case 0x5c: /* FCMGE */ + case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7d: /* FACGT */ + case 0x7c: /* FCMGT */ unallocated_encoding(s); return; } @@ -11617,14 +11657,9 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) int pass; switch (fpopcode) { - case 0x4: /* FCMEQ */ case 0x7: /* FRECPS */ case 0xf: /* FRSQRTS */ - case 0x14: /* FCMGE */ - case 0x15: /* FACGE */ case 0x1a: /* FABD */ - case 0x1c: /* FCMGT */ - case 0x1d: /* FACGT */ pairwise = false; break; case 0x10: /* FMAXNMP */ @@ -11639,13 +11674,18 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x1: /* FMLA */ case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0x4: /* FCMEQ */ case 0x6: /* FMAX */ case 0x8: /* FMINNM */ case 0x9: /* FMLS */ case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0x13: /* FMUL */ + case 0x14: /* FCMGE */ + case 0x15: /* FACGE */ case 0x17: /* FDIV */ + case 0x1c: /* FCMGT */ + case 0x1d: /* FACGT */ unallocated_encoding(s); return; } @@ -11711,43 +11751,33 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); switch (fpopcode) { - case 0x4: /* FCMEQ */ - gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x7: /* FRECPS */ gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; case 0xf: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x14: /* FCMGE */ - gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x15: /* FACGE */ - gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0x1a: /* FABD */ gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); break; - case 0x1c: /* FCMGT */ - gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1d: /* FACGT */ - gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; default: case 0x0: /* FMAXNM */ case 0x1: /* FMLA */ case 0x2: /* FADD */ case 0x3: /* FMULX */ + case 0x4: /* FCMEQ */ case 0x6: /* FMAX */ case 0x8: /* FMINNM */ case 0x9: /* FMLS */ case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0x13: /* FMUL */ + case 0x14: /* FCMGE */ + case 0x15: /* FACGE */ case 0x17: /* FDIV */ + case 0x1c: /* FCMGT */ + case 0x1d: /* FACGT */ g_assert_not_reached(); } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index b925b9f21be..dabefa3526d 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -971,6 +971,11 @@ static uint32_t float32_ceq(float32 op1, float32 op2, float_status *stat) return -float32_eq_quiet(op1, op2, stat); } +static uint64_t float64_ceq(float64 op1, float64 op2, float_status *stat) +{ + return -float64_eq_quiet(op1, op2, stat); +} + static uint16_t float16_cge(float16 op1, float16 op2, float_status *stat) { return -float16_le(op2, op1, stat); @@ -981,6 +986,11 @@ static uint32_t float32_cge(float32 op1, float32 op2, float_status *stat) return -float32_le(op2, op1, stat); } +static uint64_t float64_cge(float64 op1, float64 op2, float_status *stat) +{ + return -float64_le(op2, op1, stat); +} + static uint16_t float16_cgt(float16 op1, float16 op2, float_status *stat) { return -float16_lt(op2, op1, stat); @@ -991,6 +1001,11 @@ static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(op2, op1, stat); } +static uint64_t float64_cgt(float64 op1, float64 op2, float_status *stat) +{ + return -float64_lt(op2, op1, stat); +} + static uint16_t float16_acge(float16 op1, float16 op2, float_status *stat) { return -float16_le(float16_abs(op2), float16_abs(op1), stat); @@ -1001,6 +1016,11 @@ static uint32_t float32_acge(float32 op1, float32 op2, float_status *stat) return -float32_le(float32_abs(op2), float32_abs(op1), stat); } +static uint64_t float64_acge(float64 op1, float64 op2, float_status *stat) +{ + return -float64_le(float64_abs(op2), float64_abs(op1), stat); +} + static uint16_t float16_acgt(float16 op1, float16 op2, float_status *stat) { return -float16_lt(float16_abs(op2), float16_abs(op1), stat); @@ -1011,6 +1031,11 @@ static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(float32_abs(op2), float32_abs(op1), stat); } +static uint64_t float64_acgt(float64 op1, float64 op2, float_status *stat) +{ + return -float64_lt(float64_abs(op2), float64_abs(op1), stat); +} + static int16_t vfp_tosszh(float16 x, void *fpstp) { float_status *fpst = fpstp; @@ -1216,18 +1241,23 @@ DO_3OP(gvec_fabd_s, float32_abd, float32) DO_3OP(gvec_fceq_h, float16_ceq, float16) DO_3OP(gvec_fceq_s, float32_ceq, float32) +DO_3OP(gvec_fceq_d, float64_ceq, float64) DO_3OP(gvec_fcge_h, float16_cge, float16) DO_3OP(gvec_fcge_s, float32_cge, float32) +DO_3OP(gvec_fcge_d, float64_cge, float64) DO_3OP(gvec_fcgt_h, float16_cgt, float16) DO_3OP(gvec_fcgt_s, float32_cgt, float32) +DO_3OP(gvec_fcgt_d, float64_cgt, float64) DO_3OP(gvec_facge_h, float16_acge, float16) DO_3OP(gvec_facge_s, float32_acge, float32) +DO_3OP(gvec_facge_d, float64_acge, float64) DO_3OP(gvec_facgt_h, float16_acgt, float16) DO_3OP(gvec_facgt_s, float32_acgt, float32) +DO_3OP(gvec_facgt_d, float64_acgt, float64) DO_3OP(gvec_fmax_h, float16_max, float16) DO_3OP(gvec_fmax_s, float32_max, float32) From patchwork Tue May 28 14:07:43 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799469 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256152wrz; Tue, 28 May 2024 07:11:02 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCURvAiCSIh88+1BFKL6kT8wiHw0uEwmSYlyeIcAhuCvKHMmRuxWRreiS+bWfnnUTjbOxd5pLzE8/Ws+6uRha/Cp X-Google-Smtp-Source: AGHT+IGL/5ToVSmCmM/EIDnR3YzT5coJaoprhDxtiPWTkZR9C18G9ATMl+wneGW+lAUvdUWFMjhy X-Received: by 2002:a05:6e02:1746:b0:36d:b51c:4b87 with SMTP id e9e14a558f8ab-3737b2ebffamr143631255ab.18.1716905462609; Tue, 28 May 2024 07:11:02 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905462; cv=none; d=google.com; s=arc-20160816; b=rJmoGpUlggOdhwLB+9cVA+q7iXwI6MgkfTJY4+py9xNqXKsvIYE6q3fj4387pyLwwa eZkD0pJd7mrh0pk+K99uMjrYHaylvNHvZADSEBS4/StTf5QYtK8iRqJQ3QkY3kdvSbqD zhxzVMNA2M/YYlanYWJBy4bJe2zgB4BVGEilKkAfRrbhXt8eUxFUjLj3iXQtJHgdjJrw g50pGx6Mdn1GiEne/8M/EqYnG3nVyEwKmypHO4qoTX1+H0ZlDlk9Bo09CpDnowIEkrji 8Xm+OkK+0xC0ukh++uqjbf/YdACdcYcslqQ1v+qdFSpL0b7SZCcUOwYmzO6t6lyukfma 5/AQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=hVAsp/c4hHolhFaVa/tFc/Uvy2bSit7O3UHJnbszYUg=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=hPvg6tfNq3TAozq08zIYYmInwGLBsxgCjxd/cg5h6w4Sn+IfoKV2VSrGX7rE2OKJTD raXXchrBKwnCSBSrkHBAvL2+sCcpWB4QEx6BnFASI6xBpQaqsDs6jIMQhGceJr4bqiYK srZv1wf5Iczl5MyYmjrUuPCmJARAD8j76Q9E5dAgjAopiAkHzrOJNuEjeULagZ0iqax5 9ZN0vwNi57inT6aHFuS6OkhSqUeLWMkRStAZLxolJdLdSIUq54S4sbW00fvTej4F73Dy ozCwUWaF6FutkIS+JOzNDOjYTY5Ah96aDnM/ztog398EwVTn90wzkdgHmm6WU+ACxvao FLdw==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ujNaXet5; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb18a6deasi104645791cf.296.2024.05.28.07.11.02 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:11:02 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ujNaXet5; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVa-0002UM-97; Tue, 28 May 2024 10:08:58 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV2-0001jR-PM for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:24 -0400 Received: from mail-lj1-x236.google.com ([2a00:1450:4864:20::236]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUv-00076R-HB for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:24 -0400 Received: by mail-lj1-x236.google.com with SMTP id 38308e7fff4ca-2e724bc466fso8970381fa.3 for ; Tue, 28 May 2024 07:08:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905295; x=1717510095; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=hVAsp/c4hHolhFaVa/tFc/Uvy2bSit7O3UHJnbszYUg=; b=ujNaXet5SV8bI0jVppJEzMejqHDMko/1gzn1Sbjdxpap7GRd9IOfJsEpaCcOkDVXAc ghDyfSaQYu5mFs6EW1msrm7/DAPW4q8rElF8X/Gnr/RwxtEGEairtQDg9/i324LHXsXn tfjI10OKVkBl7fDm8CCpdzrxZaJQgIgL5tjrIB2MFbP4rRZapKTbtxEo+Tp/6EfcpoLV /hT67x2/IaBmXCCFEiBkq10MUkgNxgbcizTMbxTwwHE/lHO5NFSVd3IrU8TG2k14rE2g 7VdFDvM52zjYYoy+J67fcAKMWlOxw1fjDetBC03o3W6aZdBkOh3rVMi3/kO3kvbIxBrn UeLg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905295; x=1717510095; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=hVAsp/c4hHolhFaVa/tFc/Uvy2bSit7O3UHJnbszYUg=; b=IjetVOMGROASqUgJMvFqAs1HkSuW7ArPkNdUn3Olrkrn7E3pCgtoPKOzfZhIVMZHal gGYjifo85ovl7apvpJYwixbMHYHn2JWz3mud+3+R3Q+vdwnlNszfrlVth8bPFEpIHMKc wPi/NNQvZDURzUutyLW/YgF29r35fsZihGVSWf8Q9dNCFlpUfqw1JEPR2xcaQo379Fzd 5lZvdQQu2w5oGKnOLDmpxiFiQBmtk0YlkWaQrzQoNJpIYKvqkaWkc8VZJl/awwlSBB7d 1MNirSHaTH7v9DmKpC62Wf+C3wq52+yDDLYcRujUXI9a41B0Zq+Ev1jZm+EzGg/Fsqvo V6lQ== X-Gm-Message-State: AOJu0Yz5EukfPEtuHT5tyRuQypRw+EzL5je1wGkk5FNnXWxlly5m7Uwt kP3pr+ZmRDHG7eeWcQg6zjM2V18mFe+n5oR2PjKC8i1utXmpEd276ziGFVKPjOHOdNYld51WqY3 3 X-Received: by 2002:a2e:7216:0:b0:2df:ffc6:1a0c with SMTP id 38308e7fff4ca-2e95b042bebmr117565121fa.2.1716905295596; Tue, 28 May 2024 07:08:15 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.15 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:15 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 32/42] target/arm: Convert FABD to decodetree Date: Tue, 28 May 2024 15:07:43 +0100 Message-Id: <20240528140753.3620597-33-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::236; envelope-from=peter.maydell@linaro.org; helo=mail-lj1-x236.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 1 + target/arm/tcg/a64.decode | 6 ++++ target/arm/tcg/translate-a64.c | 60 ++++++++++++++++++++++------------ target/arm/tcg/vec_helper.c | 6 ++++ 4 files changed, 53 insertions(+), 20 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 8d076011c18..ff6e3094f41 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -724,6 +724,7 @@ DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7fc3277be67..a852b5f06f0 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -728,6 +728,9 @@ FACGE_s 0111 1110 0.1 ..... 11101 1 ..... ..... @rrr_sd FACGT_s 0111 1110 110 ..... 00101 1 ..... ..... @rrr_h FACGT_s 0111 1110 1.1 ..... 11101 1 ..... ..... @rrr_sd +FABD_s 0111 1110 110 ..... 00010 1 ..... ..... @rrr_h +FABD_s 0111 1110 1.1 ..... 11010 1 ..... ..... @rrr_sd + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -778,6 +781,9 @@ FACGE_v 0.10 1110 0.1 ..... 11101 1 ..... ..... @qrrr_sd FACGT_v 0.10 1110 110 ..... 00101 1 ..... ..... @qrrr_h FACGT_v 0.10 1110 1.1 ..... 11101 1 ..... ..... @qrrr_sd +FABD_v 0.10 1110 110 ..... 00010 1 ..... ..... @qrrr_h +FABD_v 0.10 1110 1.1 ..... 11010 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 75b0c1a005e..633384d2a56 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5010,6 +5010,31 @@ static const FPScalar f_scalar_facgt = { }; TRANS(FACGT_s, do_fp3_scalar, a, &f_scalar_facgt) +static void gen_fabd_h(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_ptr s) +{ + gen_helper_vfp_subh(d, n, m, s); + gen_vfp_absh(d, d); +} + +static void gen_fabd_s(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_ptr s) +{ + gen_helper_vfp_subs(d, n, m, s); + gen_vfp_abss(d, d); +} + +static void gen_fabd_d(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_ptr s) +{ + gen_helper_vfp_subd(d, n, m, s); + gen_vfp_absd(d, d); +} + +static const FPScalar f_scalar_fabd = { + gen_fabd_h, + gen_fabd_s, + gen_fabd_d, +}; +TRANS(FABD_s, do_fp3_scalar, a, &f_scalar_fabd) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -5150,6 +5175,13 @@ static gen_helper_gvec_3_ptr * const f_vector_facgt[3] = { }; TRANS(FACGT_v, do_fp3_vector, a, f_vector_facgt) +static gen_helper_gvec_3_ptr * const f_vector_fabd[3] = { + gen_helper_gvec_fabd_h, + gen_helper_gvec_fabd_s, + gen_helper_gvec_fabd_d, +}; +TRANS(FABD_v, do_fp3_vector, a, f_vector_fabd) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -9303,10 +9335,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x7a: /* FABD */ - gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst); - gen_vfp_absd(tcg_res, tcg_res); - break; default: case 0x18: /* FMAXNM */ case 0x19: /* FMLA */ @@ -9322,6 +9350,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7a: /* FABD */ case 0x7c: /* FCMGT */ case 0x7d: /* FACGT */ g_assert_not_reached(); @@ -9344,10 +9373,6 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x3f: /* FRSQRTS */ gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x7a: /* FABD */ - gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst); - gen_vfp_abss(tcg_res, tcg_res); - break; default: case 0x18: /* FMAXNM */ case 0x19: /* FMLA */ @@ -9363,6 +9388,7 @@ static void handle_3same_float(DisasContext *s, int size, int elements, case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7a: /* FABD */ case 0x7c: /* FCMGT */ case 0x7d: /* FACGT */ g_assert_not_reached(); @@ -9405,7 +9431,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ - case 0x7a: /* FABD */ break; default: case 0x1b: /* FMULX */ @@ -9413,6 +9438,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) case 0x7d: /* FACGT */ case 0x1c: /* FCMEQ */ case 0x5c: /* FCMGE */ + case 0x7a: /* FABD */ case 0x7c: /* FCMGT */ unallocated_encoding(s); return; @@ -9568,13 +9594,13 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, switch (fpopcode) { case 0x07: /* FRECPS */ case 0x0f: /* FRSQRTS */ - case 0x1a: /* FABD */ break; default: case 0x03: /* FMULX */ case 0x04: /* FCMEQ (reg) */ case 0x14: /* FCMGE (reg) */ case 0x15: /* FACGE */ + case 0x1a: /* FABD */ case 0x1c: /* FCMGT (reg) */ case 0x1d: /* FACGT */ unallocated_encoding(s); @@ -9602,15 +9628,12 @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, case 0x0f: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1a: /* FABD */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); - break; default: case 0x03: /* FMULX */ case 0x04: /* FCMEQ (reg) */ case 0x14: /* FCMGE (reg) */ case 0x15: /* FACGE */ + case 0x1a: /* FABD */ case 0x1c: /* FCMGT (reg) */ case 0x1d: /* FACGT */ g_assert_not_reached(); @@ -11272,7 +11295,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) return; case 0x1f: /* FRECPS */ case 0x3f: /* FRSQRTS */ - case 0x7a: /* FABD */ if (!fp_access_check(s)) { return; } @@ -11314,6 +11336,7 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ case 0x5f: /* FDIV */ + case 0x7a: /* FABD */ case 0x7d: /* FACGT */ case 0x7c: /* FCMGT */ unallocated_encoding(s); @@ -11659,7 +11682,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x7: /* FRECPS */ case 0xf: /* FRSQRTS */ - case 0x1a: /* FABD */ pairwise = false; break; case 0x10: /* FMAXNMP */ @@ -11684,6 +11706,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x14: /* FCMGE */ case 0x15: /* FACGE */ case 0x17: /* FDIV */ + case 0x1a: /* FABD */ case 0x1c: /* FCMGT */ case 0x1d: /* FACGT */ unallocated_encoding(s); @@ -11757,10 +11780,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0xf: /* FRSQRTS */ gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0x1a: /* FABD */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); - break; default: case 0x0: /* FMAXNM */ case 0x1: /* FMLA */ @@ -11776,6 +11795,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x14: /* FCMGE */ case 0x15: /* FACGE */ case 0x17: /* FDIV */ + case 0x1a: /* FABD */ case 0x1c: /* FCMGT */ case 0x1d: /* FACGT */ g_assert_not_reached(); diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index dabefa3526d..e9d7922f303 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1154,6 +1154,11 @@ static float32 float32_abd(float32 op1, float32 op2, float_status *stat) return float32_abs(float32_sub(op1, op2, stat)); } +static float64 float64_abd(float64 op1, float64 op2, float_status *stat) +{ + return float64_abs(float64_sub(op1, op2, stat)); +} + /* * Reciprocal step. These are the AArch32 version which uses a * non-fused multiply-and-subtract. @@ -1238,6 +1243,7 @@ DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) DO_3OP(gvec_fabd_h, float16_abd, float16) DO_3OP(gvec_fabd_s, float32_abd, float32) +DO_3OP(gvec_fabd_d, float64_abd, float64) DO_3OP(gvec_fceq_h, float16_ceq, float16) DO_3OP(gvec_fceq_s, float32_ceq, float32) From patchwork Tue May 28 14:07:44 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799457 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255337wrz; Tue, 28 May 2024 07:09:50 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCU7cdKfmleSZEdmF8s6boPgf2yS2siFP/JemTj2oSut/tmToIGq+XdvslUjZZeHqG1GvvCe1zhEq/oONr7blFxC X-Google-Smtp-Source: AGHT+IEbV3sOfSiz30lXckHYVYzlwasl3ysaVFFXCJlpSinctDneJewoRKH8zTm6VLRVOWKmpv9q X-Received: by 2002:a05:6359:6386:b0:183:4d1d:dcae with SMTP id e5c5f4694b2df-197e567966cmr1183520755d.28.1716905390264; Tue, 28 May 2024 07:09:50 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905390; cv=none; d=google.com; s=arc-20160816; b=qUI/l1gA9ziXEEii9rpr/TTd2E7vPhh8f5+EHTBCcga9GOCwue5i/6YzvCGl9lmNg/ RdWwUFuh1d+JqBACqtfFG7zpnVHasKnwJH6LSxjJ2YCF+WGE8a0Z2XurkgSOMgPdx6vf SPdNIvJ89sJMa1nRw5opavnJ37PbGVSpK6d7iwlNssCI1ezLYDegRqXyzdO065T5V+OZ 5ZhyhLz+t6MSi9hEo4cMm/s0huCZcFV0ewKo/jg3zvHn1y3OGG4PA9H2uazNj/i1Liov wCNJCTsnJSXvwZL71b0KABb8t4GqC6TIlrve7Dvc4ITK7fa/+HTvC8KNMt/dT8kw1a5K 1+iA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=ZkmlHFSwMemNc/pbjcOY9sbB9XVxOQ2MJdXbYI8TzRA=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=q+/sa91y5ex6mJoIBXH4msoPQRh6N+e8mMSsH7GE2EvMPCDW+jLV0KtoLWy4/lT6jC T+idibHKsRzRCWFtRT4gMQCyCU2zTbNB3SVJxdDKR1sZSXkdkeDbmkZkBdpODxYZ0Ar+ i0kFlChQ3TW70rQx+RkP2sLh7+UsW9IINE/MdHSr/D7CvlWhSe1B4jh8mS9s/zNEwpsv nlr6U1SmyZJRlJk0WN5BH5kVNiFX5sGo8lHqPVKgqITovDUF5/xDwyxaE+ryJ9sXf1WZ xfPJXVhdjHGTcfnh9mInMdjv405/AVW1tcqWsWgOfaFjm4FEY//I9zkjkNCw9PNAu/NC CYMA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=TohsECFa; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ad7a2b4269si60182596d6.604.2024.05.28.07.09.50 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:09:50 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=TohsECFa; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iF-Ql; Tue, 28 May 2024 10:08:23 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hE-DX for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: from mail-wm1-x32f.google.com ([2a00:1450:4864:20::32f]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUv-00076h-Q4 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: by mail-wm1-x32f.google.com with SMTP id 5b1f17b1804b1-42120fc8cbfso3301025e9.2 for ; Tue, 28 May 2024 07:08:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905296; x=1717510096; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=ZkmlHFSwMemNc/pbjcOY9sbB9XVxOQ2MJdXbYI8TzRA=; b=TohsECFa4CITS19Irf5Q1wvDLeXktKnrk11uzNvARI84oyMCNbabMmLh6Y/7U252H7 UCDKAdJFrh3y2xyicUu1aT/Ujpa4/2ZfHKAME77kqzSMPGlTQ33AO5Kb37uWUiJMMiLr KliWHuZpgdltwF2yC9Ub21q2Lif3lvx5kUcaJxBBDZgeDBxgZ0R/hnG9oLDSvd2tdPWY YQ7nqTevRr1fMESUaYkcrNzTz0JeYLU2GzPtIKXlIvvJOYwXESEgDo1lUn5jqKCgtWOu Nmd8IvQWs0moqg87UJxLPBkV7l+9gWLEVZ/6FPxHXxdwp4Q5EH1qkUnCkkdFziLKNOwI BlcQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905296; x=1717510096; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=ZkmlHFSwMemNc/pbjcOY9sbB9XVxOQ2MJdXbYI8TzRA=; b=hmiGQBif5QnToc3aEgmndHhpNpK6tYNHPm9r5k9M9lCtxfwf1pNvKRyEWYjc6SgoR8 5p9CaDRDdyXUwj9AkImL+ow3OCYdlY8TAWwRHKTAdBQ1iwQ1S+Yo3J8oGhXMw4jOna5Y BjyZDIcIwNO7RUrPX8xFWCCM0jyMSVsY+lWcj0Nbk8A8vr2wujY9GMyMEV3XnNG6PjUH xy7kLY4D+YoerXPc0FRa9u17vjnU9gpQLbL7WjEbZ8wlxRR/uf+9zSy07sf8Uu3Ql8Yu T+8U3LrPXc+P2d4xXu3INdkKpF9b2IPaEiebMdRu2IfwQ9Fd5PXyPIZl9KztBqIqLVgh QNTQ== X-Gm-Message-State: AOJu0YxwOIxm2zlBYU9RGwmvnOdyMXxkTpsLk1zN+mP5HSPGI6K17FAk PO63ZNqMkkmkc4KkIrloIj2hOZOIJQWhAc+Ko4EaWC9Ym1d5ll75zhLTHCb7kcDSunb9eYEx8C/ g X-Received: by 2002:adf:ce06:0:b0:34d:96ca:8c24 with SMTP id ffacd0b85a97d-35526c6d60emr8442316f8f.37.1716905296093; Tue, 28 May 2024 07:08:16 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.15 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:15 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 33/42] target/arm: Convert FRECPS, FRSQRTS to decodetree Date: Tue, 28 May 2024 15:07:44 +0100 Message-Id: <20240528140753.3620597-34-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::32f; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x32f.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson These are the last instructions within handle_3same_float and disas_simd_scalar_three_reg_same_fp16 so remove them. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 12 ++ target/arm/tcg/translate-a64.c | 293 ++++----------------------------- 2 files changed, 46 insertions(+), 259 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index a852b5f06f0..84cb38f1dd0 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -731,6 +731,12 @@ FACGT_s 0111 1110 1.1 ..... 11101 1 ..... ..... @rrr_sd FABD_s 0111 1110 110 ..... 00010 1 ..... ..... @rrr_h FABD_s 0111 1110 1.1 ..... 11010 1 ..... ..... @rrr_sd +FRECPS_s 0101 1110 010 ..... 00111 1 ..... ..... @rrr_h +FRECPS_s 0101 1110 0.1 ..... 11111 1 ..... ..... @rrr_sd + +FRSQRTS_s 0101 1110 110 ..... 00111 1 ..... ..... @rrr_h +FRSQRTS_s 0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -784,6 +790,12 @@ FACGT_v 0.10 1110 1.1 ..... 11101 1 ..... ..... @qrrr_sd FABD_v 0.10 1110 110 ..... 00010 1 ..... ..... @qrrr_h FABD_v 0.10 1110 1.1 ..... 11010 1 ..... ..... @qrrr_sd +FRECPS_v 0.00 1110 010 ..... 00111 1 ..... ..... @qrrr_h +FRECPS_v 0.00 1110 0.1 ..... 11111 1 ..... ..... @qrrr_sd + +FRSQRTS_v 0.00 1110 110 ..... 00111 1 ..... ..... @qrrr_h +FRSQRTS_v 0.00 1110 1.1 ..... 11111 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 633384d2a56..a7537a5104f 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5035,6 +5035,20 @@ static const FPScalar f_scalar_fabd = { }; TRANS(FABD_s, do_fp3_scalar, a, &f_scalar_fabd) +static const FPScalar f_scalar_frecps = { + gen_helper_recpsf_f16, + gen_helper_recpsf_f32, + gen_helper_recpsf_f64, +}; +TRANS(FRECPS_s, do_fp3_scalar, a, &f_scalar_frecps) + +static const FPScalar f_scalar_frsqrts = { + gen_helper_rsqrtsf_f16, + gen_helper_rsqrtsf_f32, + gen_helper_rsqrtsf_f64, +}; +TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts) + static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -5182,6 +5196,20 @@ static gen_helper_gvec_3_ptr * const f_vector_fabd[3] = { }; TRANS(FABD_v, do_fp3_vector, a, f_vector_fabd) +static gen_helper_gvec_3_ptr * const f_vector_frecps[3] = { + gen_helper_gvec_recps_h, + gen_helper_gvec_recps_s, + gen_helper_gvec_recps_d, +}; +TRANS(FRECPS_v, do_fp3_vector, a, f_vector_frecps) + +static gen_helper_gvec_3_ptr * const f_vector_frsqrts[3] = { + gen_helper_gvec_rsqrts_h, + gen_helper_gvec_rsqrts_s, + gen_helper_gvec_rsqrts_d, +}; +TRANS(FRSQRTS_v, do_fp3_vector, a, f_vector_frsqrts) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -9308,107 +9336,6 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, } } -/* Handle the 3-same-operands float operations; shared by the scalar - * and vector encodings. The caller must filter out any encodings - * not allocated for the encoding it is dealing with. - */ -static void handle_3same_float(DisasContext *s, int size, int elements, - int fpopcode, int rd, int rn, int rm) -{ - int pass; - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - - for (pass = 0; pass < elements; pass++) { - if (size) { - /* Double */ - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - switch (fpopcode) { - case 0x1f: /* FRECPS */ - gen_helper_recpsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3f: /* FRSQRTS */ - gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0x18: /* FMAXNM */ - case 0x19: /* FMLA */ - case 0x1a: /* FADD */ - case 0x1b: /* FMULX */ - case 0x1c: /* FCMEQ */ - case 0x1e: /* FMAX */ - case 0x38: /* FMINNM */ - case 0x39: /* FMLS */ - case 0x3a: /* FSUB */ - case 0x3e: /* FMIN */ - case 0x5b: /* FMUL */ - case 0x5c: /* FCMGE */ - case 0x5d: /* FACGE */ - case 0x5f: /* FDIV */ - case 0x7a: /* FABD */ - case 0x7c: /* FCMGT */ - case 0x7d: /* FACGT */ - g_assert_not_reached(); - } - - write_vec_element(s, tcg_res, rd, pass, MO_64); - } else { - /* Single */ - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op1, rn, pass, MO_32); - read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); - - switch (fpopcode) { - case 0x1f: /* FRECPS */ - gen_helper_recpsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3f: /* FRSQRTS */ - gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0x18: /* FMAXNM */ - case 0x19: /* FMLA */ - case 0x1a: /* FADD */ - case 0x1b: /* FMULX */ - case 0x1c: /* FCMEQ */ - case 0x1e: /* FMAX */ - case 0x38: /* FMINNM */ - case 0x39: /* FMLS */ - case 0x3a: /* FSUB */ - case 0x3e: /* FMIN */ - case 0x5b: /* FMUL */ - case 0x5c: /* FCMGE */ - case 0x5d: /* FACGE */ - case 0x5f: /* FDIV */ - case 0x7a: /* FABD */ - case 0x7c: /* FCMGT */ - case 0x7d: /* FACGT */ - g_assert_not_reached(); - } - - if (elements == 1) { - /* scalar single so clear high part */ - TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - - tcg_gen_extu_i32_i64(tcg_tmp, tcg_res); - write_vec_element(s, tcg_tmp, rd, pass, MO_64); - } else { - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - } - - clear_vec_high(s, elements * (size ? 8 : 4) > 8, rd); -} - /* AdvSIMD scalar three same * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+--------+---+------+------+ @@ -9425,33 +9352,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) bool u = extract32(insn, 29, 1); TCGv_i64 tcg_rd; - if (opcode >= 0x18) { - /* Floating point: U, size[1] and opcode indicate operation */ - int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6); - switch (fpopcode) { - case 0x1f: /* FRECPS */ - case 0x3f: /* FRSQRTS */ - break; - default: - case 0x1b: /* FMULX */ - case 0x5d: /* FACGE */ - case 0x7d: /* FACGT */ - case 0x1c: /* FCMEQ */ - case 0x5c: /* FCMGE */ - case 0x7a: /* FABD */ - case 0x7c: /* FCMGT */ - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - handle_3same_float(s, extract32(size, 0, 1), 1, fpopcode, rd, rn, rm); - return; - } - switch (opcode) { case 0x1: /* SQADD, UQADD */ case 0x5: /* SQSUB, UQSUB */ @@ -9568,80 +9468,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn) write_fp_dreg(s, rd, tcg_rd); } -/* AdvSIMD scalar three same FP16 - * 31 30 29 28 24 23 22 21 20 16 15 14 13 11 10 9 5 4 0 - * +-----+---+-----------+---+-----+------+-----+--------+---+----+----+ - * | 0 1 | U | 1 1 1 1 0 | a | 1 0 | Rm | 0 0 | opcode | 1 | Rn | Rd | - * +-----+---+-----------+---+-----+------+-----+--------+---+----+----+ - * v: 0101 1110 0100 0000 0000 0100 0000 0000 => 5e400400 - * m: 1101 1111 0110 0000 1100 0100 0000 0000 => df60c400 - */ -static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, - uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 3); - int rm = extract32(insn, 16, 5); - bool u = extract32(insn, 29, 1); - bool a = extract32(insn, 23, 1); - int fpopcode = opcode | (a << 3) | (u << 4); - TCGv_ptr fpst; - TCGv_i32 tcg_op1; - TCGv_i32 tcg_op2; - TCGv_i32 tcg_res; - - switch (fpopcode) { - case 0x07: /* FRECPS */ - case 0x0f: /* FRSQRTS */ - break; - default: - case 0x03: /* FMULX */ - case 0x04: /* FCMEQ (reg) */ - case 0x14: /* FCMGE (reg) */ - case 0x15: /* FACGE */ - case 0x1a: /* FABD */ - case 0x1c: /* FCMGT (reg) */ - case 0x1d: /* FACGT */ - unallocated_encoding(s); - return; - } - - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - } - - if (!fp_access_check(s)) { - return; - } - - fpst = fpstatus_ptr(FPST_FPCR_F16); - - tcg_op1 = read_fp_hreg(s, rn); - tcg_op2 = read_fp_hreg(s, rm); - tcg_res = tcg_temp_new_i32(); - - switch (fpopcode) { - case 0x07: /* FRECPS */ - gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x0f: /* FRSQRTS */ - gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0x03: /* FMULX */ - case 0x04: /* FCMEQ (reg) */ - case 0x14: /* FCMGE (reg) */ - case 0x15: /* FACGE */ - case 0x1a: /* FABD */ - case 0x1c: /* FCMGT (reg) */ - case 0x1d: /* FACGT */ - g_assert_not_reached(); - } - - write_fp_sreg(s, rd, tcg_res); -} - /* AdvSIMD scalar three same extra * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 * +-----+---+-----------+------+---+------+---+--------+---+----+----+ @@ -11114,7 +10940,7 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) /* Pairwise op subgroup of C3.6.16. * - * This is called directly or via the handle_3same_float for float pairwise + * This is called directly for float pairwise * operations where the opcode and size are calculated differently. */ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, @@ -11271,10 +11097,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int datasize = is_q ? 128 : 64; - int esize = 32 << size; - int elements = datasize / esize; - if (size == 1 && !is_q) { unallocated_encoding(s); return; @@ -11293,13 +11115,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) handle_simd_3same_pair(s, is_q, 0, fpopcode, size ? MO_64 : MO_32, rn, rm, rd); return; - case 0x1f: /* FRECPS */ - case 0x3f: /* FRSQRTS */ - if (!fp_access_check(s)) { - return; - } - handle_3same_float(s, size, elements, fpopcode, rd, rn, rm); - return; case 0x1d: /* FMLAL */ case 0x3d: /* FMLSL */ @@ -11328,10 +11143,12 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x1b: /* FMULX */ case 0x1c: /* FCMEQ */ case 0x1e: /* FMAX */ + case 0x1f: /* FRECPS */ case 0x38: /* FMINNM */ case 0x39: /* FMLS */ case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ + case 0x3f: /* FRSQRTS */ case 0x5b: /* FMUL */ case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ @@ -11673,17 +11490,11 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) * together indicate the operation. */ int fpopcode = opcode | (a << 3) | (u << 4); - int datasize = is_q ? 128 : 64; - int elements = datasize / 16; bool pairwise; TCGv_ptr fpst; int pass; switch (fpopcode) { - case 0x7: /* FRECPS */ - case 0xf: /* FRSQRTS */ - pairwise = false; - break; case 0x10: /* FMAXNMP */ case 0x12: /* FADDP */ case 0x16: /* FMAXP */ @@ -11698,10 +11509,12 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x3: /* FMULX */ case 0x4: /* FCMEQ */ case 0x6: /* FMAX */ + case 0x7: /* FRECPS */ case 0x8: /* FMINNM */ case 0x9: /* FMLS */ case 0xa: /* FSUB */ case 0xe: /* FMIN */ + case 0xf: /* FRSQRTS */ case 0x13: /* FMUL */ case 0x14: /* FCMGE */ case 0x15: /* FACGE */ @@ -11765,44 +11578,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_16); } } else { - for (pass = 0; pass < elements; pass++) { - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op1, rn, pass, MO_16); - read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); - - switch (fpopcode) { - case 0x7: /* FRECPS */ - gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FRSQRTS */ - gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0x0: /* FMAXNM */ - case 0x1: /* FMLA */ - case 0x2: /* FADD */ - case 0x3: /* FMULX */ - case 0x4: /* FCMEQ */ - case 0x6: /* FMAX */ - case 0x8: /* FMINNM */ - case 0x9: /* FMLS */ - case 0xa: /* FSUB */ - case 0xe: /* FMIN */ - case 0x13: /* FMUL */ - case 0x14: /* FCMGE */ - case 0x15: /* FACGE */ - case 0x17: /* FDIV */ - case 0x1a: /* FABD */ - case 0x1c: /* FCMGT */ - case 0x1d: /* FACGT */ - g_assert_not_reached(); - } - - write_vec_element_i32(s, tcg_res, rd, pass, MO_16); - } + g_assert_not_reached(); } clear_vec_high(s, is_q, rd); @@ -13572,7 +13348,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, - { 0x5e400400, 0xdf60c400, disas_simd_scalar_three_reg_same_fp16 }, { 0x00000000, 0x00000000, NULL } }; From patchwork Tue May 28 14:07:45 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799479 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257106wrz; Tue, 28 May 2024 07:12:32 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVAs7Ie5AkkJaaXiVV42UyHJq9p5XxcqWh1Olo1CXP6aD9SerwRlvvWQM0/uT94xZFSVMEO21thj2vkY3/u+zG3 X-Google-Smtp-Source: AGHT+IEh081j1oJvJ40ePBfNVKP5PBZVc19/LYi+Tw4a2wIQQD5T2Y1hUB7Q+K13jT92rlEvs85Z X-Received: by 2002:a05:6808:490:b0:3c6:e8d:3ef0 with SMTP id 5614622812f47-3d1a7b30770mr11801745b6e.49.1716905552340; Tue, 28 May 2024 07:12:32 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905552; cv=none; d=google.com; s=arc-20160816; b=zo+inqZh6Rh2W+oyia8UBXwqMGFl/cGV0ndKds9e2+jWNIDyEAYQ40w9e4qlSYozBT bUax8GsykechVYAid+aYoWnYoZaQtr7i9JXinzntuqoxmMH5iCCXq0FLHWMUgsVHyJDc v7X2iq6TleH/ob5WATiHExr0HRgPbkg96YTG5LYCS98TvEy2xFWvalLSI5B1ER9cnF51 NQFYF/neybXwSDHU4WJXoWu4AY3CFa50jwxpcyXtgjd6AYtcFY4KSxZj5DEc8Rew7/la wZpIT8vIeDnRyApeuDbK5CoKuW49cgr6T8J4PTOObw0bEmzuUejhDpY2tOWxW4xqm3F0 mrIA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=QVn7klxYDRWP5wXnyK/zURPRlSgpvw4yuDXzD1F0KkA=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=p/5lNKmDJ1jPHJOEzWpwKW5ewvSoH7T3kNEbHHs6UcqWzkgbfSr7Iq9bWNd/20HqMP dzMxh1r/VMOfXzfLQdzeTYr8QZ4L3Ur2rzv1bvDPh+cv8OahJ/eKlbhnR0rOFlMpIOAu TOS6B8d62o0V3tA7TdME2kEMAL0evu6tkUrmOSHux5kBBS/8+LI4tIZorwsjnWSOcrIY PJao65MMnA3o59JO2uerbJrRWL3QEk/wijL2dVb/l1ENt8z36KrjcJxrug0tscCaHdXV fKxJpDd/CgZ9X49TOXy/vEsLbwHM/Vn98yS6HFrJMqW3nGFM/M+4sihiK1Gn90dAxB2S /adQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=z61LhPXe; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb80a0b3dsi96768661cf.335.2024.05.28.07.12.32 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:32 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=z61LhPXe; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV6-0001le-HP; Tue, 28 May 2024 10:08:28 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hL-K5 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: from mail-wm1-x336.google.com ([2a00:1450:4864:20::336]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUw-00076x-2t for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: by mail-wm1-x336.google.com with SMTP id 5b1f17b1804b1-4211249fbafso7088205e9.3 for ; Tue, 28 May 2024 07:08:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905296; x=1717510096; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=QVn7klxYDRWP5wXnyK/zURPRlSgpvw4yuDXzD1F0KkA=; b=z61LhPXebNdaYJsAwoW0J7SHWNu1NSYvvO2FUUk+Biqb6ntghLEa5pwThEOJdiTXk3 y0FKA0k6qVAqPbzwBVGZRsaTSdvtRGCiSPyqDe184x7DAuzuEn8j6GwJTAz0Rzb2c4ed jPB/M83n6OelSAxGwetHFORcaG2ta/sVeXNIzPYgWv00z1ZI495jhfs5sndzqQ2tiGDr Nk27lwJeent+TN+EtUNk982/btU6ptINEbKnBmOKWvrEOKVo18TbwX33YoDZy2Vh3xeJ VbM5PKLg83LAm5zTKnjLiNeVuGVFq/SySrrAmEAgWlFs5Jlh5oC0E5iIQJ/O1MpTRK1q WaFw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905296; x=1717510096; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=QVn7klxYDRWP5wXnyK/zURPRlSgpvw4yuDXzD1F0KkA=; b=ZMXUblZuqyn7uNdXRTPnwXOZdQ68ve8ZOqx0HEOkcLzrxAvzOhlZPU1sPqJA3fCscU iI1zqr5MYekZKlhiIGoUhXLH+laLc0PAFLcasAwDPdv6dH7jqObts++tXJ6d1hBcLwp1 c1U88lsQeExlY7ueP3MPg0Xpu0bprmyN56ZxTT40L6bNt7txu3UMvS90QCZAtFC1Gn2m OtRM3h6fwQQIsUm4BHzNGAIbSopsmjgqtoEVSu/CymoHiTIjUfMeDO1zJjUA1gCfOHGU 0nZlzpUaqHAJg7FGEeT2QaMhzXfqyWggb9+Uk8SjX5oYgC7j9vxTPIv+dZ5DAxTJL7m0 tNXg== X-Gm-Message-State: AOJu0YzmyQQjR5AzeYxIYgzto341qa1Q+g28aSTZCVWsSGEjxhAgMsQo QU0Ncaq56X9b35bTRlH47FawJSO+CGMbxVVeYtDr8qZxaMYk7tYoljGxWSme6+XaQ1ytnqRnvnB + X-Received: by 2002:a7b:ce10:0:b0:41e:454b:2f7 with SMTP id 5b1f17b1804b1-421089fa056mr95012515e9.23.1716905296573; Tue, 28 May 2024 07:08:16 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.16 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:16 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 34/42] target/arm: Convert FADDP to decodetree Date: Tue, 28 May 2024 15:07:45 +0100 Message-Id: <20240528140753.3620597-35-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::336; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x336.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 4 ++ target/arm/tcg/a64.decode | 12 +++++ target/arm/tcg/translate-a64.c | 87 ++++++++++++++++++++++++++-------- target/arm/tcg/vec_helper.c | 23 +++++++++ 4 files changed, 105 insertions(+), 21 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index ff6e3094f41..8441b49d1f0 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -1048,6 +1048,10 @@ DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "tcg/helper-a64.h" #include "tcg/helper-sve.h" diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 84cb38f1dd0..d2a02365e15 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -29,6 +29,7 @@ &ri rd imm &rri_sf rd rn imm sf &i imm +&rr_e rd rn esz &rrr_e rd rn rm esz &rrx_e rd rn rm idx esz &qrr_e q rd rn esz @@ -36,6 +37,9 @@ &qrrx_e q rd rn rm idx esz &qrrrr_e q rd rn rm ra esz +@rr_h ........ ... ..... ...... rn:5 rd:5 &rr_e esz=1 +@rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd + @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @@ -737,6 +741,11 @@ FRECPS_s 0101 1110 0.1 ..... 11111 1 ..... ..... @rrr_sd FRSQRTS_s 0101 1110 110 ..... 00111 1 ..... ..... @rrr_h FRSQRTS_s 0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd +### Advanced SIMD scalar pairwise + +FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h +FADDP_s 0111 1110 0.11 0000 1101 10 ..... ..... @rr_sd + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -796,6 +805,9 @@ FRECPS_v 0.00 1110 0.1 ..... 11111 1 ..... ..... @qrrr_sd FRSQRTS_v 0.00 1110 110 ..... 00111 1 ..... ..... @qrrr_h FRSQRTS_v 0.00 1110 1.1 ..... 11111 1 ..... ..... @qrrr_sd +FADDP_v 0.10 1110 010 ..... 00010 1 ..... ..... @qrrr_h +FADDP_v 0.10 1110 0.1 ..... 11010 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index a7537a5104f..78949ab34f0 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5210,6 +5210,13 @@ static gen_helper_gvec_3_ptr * const f_vector_frsqrts[3] = { }; TRANS(FRSQRTS_v, do_fp3_vector, a, f_vector_frsqrts) +static gen_helper_gvec_3_ptr * const f_vector_faddp[3] = { + gen_helper_gvec_faddp_h, + gen_helper_gvec_faddp_s, + gen_helper_gvec_faddp_d, +}; +TRANS(FADDP_v, do_fp3_vector, a, f_vector_faddp) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -5395,6 +5402,56 @@ static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg) TRANS(FMLA_vi, do_fmla_vector_idx, a, false) TRANS(FMLS_vi, do_fmla_vector_idx, a, true) +/* + * Advanced SIMD scalar pairwise + */ + +static bool do_fp3_scalar_pair(DisasContext *s, arg_rr_e *a, const FPScalar *f) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + + read_vec_element(s, t0, a->rn, 0, MO_64); + read_vec_element(s, t1, a->rn, 1, MO_64); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_dreg(s, a->rd, t0); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t0, a->rn, 0, MO_32); + read_vec_element_i32(s, t1, a->rn, 1, MO_32); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + write_fp_sreg(s, a->rd, t0); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t0, a->rn, 0, MO_16); + read_vec_element_i32(s, t1, a->rn, 1, MO_16); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + write_fp_sreg(s, a->rd, t0); + } + break; + default: + g_assert_not_reached(); + } + return true; +} + +TRANS(FADDP_s, do_fp3_scalar_pair, a, &f_scalar_fadd) /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the @@ -8357,7 +8414,6 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) fpst = NULL; break; case 0xc: /* FMAXNMP */ - case 0xd: /* FADDP */ case 0xf: /* FMAXP */ case 0x2c: /* FMINNMP */ case 0x2f: /* FMINP */ @@ -8380,6 +8436,7 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); break; default: + case 0xd: /* FADDP */ unallocated_encoding(s); return; } @@ -8399,9 +8456,6 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0xc: /* FMAXNMP */ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0xd: /* FADDP */ - gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0xf: /* FMAXP */ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -8412,6 +8466,7 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0xd: /* FADDP */ g_assert_not_reached(); } @@ -8429,9 +8484,6 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0xc: /* FMAXNMP */ gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0xd: /* FADDP */ - gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0xf: /* FMAXP */ gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -8442,6 +8494,7 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0xd: /* FADDP */ g_assert_not_reached(); } } else { @@ -8449,9 +8502,6 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0xc: /* FMAXNMP */ gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); break; - case 0xd: /* FADDP */ - gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); - break; case 0xf: /* FMAXP */ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -8462,6 +8512,7 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); break; default: + case 0xd: /* FADDP */ g_assert_not_reached(); } } @@ -10982,9 +11033,6 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, case 0x58: /* FMAXNMP */ gen_helper_vfp_maxnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; - case 0x5a: /* FADDP */ - gen_helper_vfp_addd(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; case 0x5e: /* FMAXP */ gen_helper_vfp_maxd(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; @@ -10995,6 +11043,7 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, gen_helper_vfp_mind(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; default: + case 0x5a: /* FADDP */ g_assert_not_reached(); } } @@ -11052,9 +11101,6 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, case 0x58: /* FMAXNMP */ gen_helper_vfp_maxnums(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; - case 0x5a: /* FADDP */ - gen_helper_vfp_adds(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; case 0x5e: /* FMAXP */ gen_helper_vfp_maxs(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; @@ -11065,6 +11111,7 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, gen_helper_vfp_mins(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; default: + case 0x5a: /* FADDP */ g_assert_not_reached(); } @@ -11104,7 +11151,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x58: /* FMAXNMP */ - case 0x5a: /* FADDP */ case 0x5e: /* FMAXP */ case 0x78: /* FMINNMP */ case 0x7e: /* FMINP */ @@ -11149,6 +11195,7 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x3f: /* FRSQRTS */ + case 0x5a: /* FADDP */ case 0x5b: /* FMUL */ case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ @@ -11496,7 +11543,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) switch (fpopcode) { case 0x10: /* FMAXNMP */ - case 0x12: /* FADDP */ case 0x16: /* FMAXP */ case 0x18: /* FMINNMP */ case 0x1e: /* FMINP */ @@ -11515,6 +11561,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0xa: /* FSUB */ case 0xe: /* FMIN */ case 0xf: /* FRSQRTS */ + case 0x12: /* FADDP */ case 0x13: /* FMUL */ case 0x14: /* FCMGE */ case 0x15: /* FACGE */ @@ -11556,9 +11603,6 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_maxnumh(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; - case 0x12: /* FADDP */ - gen_helper_advsimd_addh(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; case 0x16: /* FMAXP */ gen_helper_advsimd_maxh(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; @@ -11570,6 +11614,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_minh(tcg_res[pass], tcg_op1, tcg_op2, fpst); break; default: + case 0x12: /* FADDP */ g_assert_not_reached(); } } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index e9d7922f303..28989c7d7a7 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2237,6 +2237,29 @@ DO_NEON_PAIRWISE(neon_pmin, min) #undef DO_NEON_PAIRWISE +#define DO_3OP_PAIR(NAME, FUNC, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + intptr_t oprsz = simd_oprsz(desc); \ + intptr_t half = oprsz / sizeof(TYPE) / 2; \ + TYPE *d = vd, *n = vn, *m = vm; \ + if (unlikely(d == m)) { \ + m = memcpy(&scratch, m, oprsz); \ + } \ + for (intptr_t i = 0; i < half; ++i) { \ + d[H(i)] = FUNC(n[H(i * 2)], n[H(i * 2 + 1)], stat); \ + } \ + for (intptr_t i = 0; i < half; ++i) { \ + d[H(i + half)] = FUNC(m[H(i * 2)], m[H(i * 2 + 1)], stat); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_3OP_PAIR(gvec_faddp_h, float16_add, float16, H2) +DO_3OP_PAIR(gvec_faddp_s, float32_add, float32, H4) +DO_3OP_PAIR(gvec_faddp_d, float64_add, float64, ) + #define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ From patchwork Tue May 28 14:07:46 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799472 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256495wrz; Tue, 28 May 2024 07:11:37 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVnqB9x77Y/AVlb2xesAc5+rHKci6A/iZArcpxnkHcYGcedqhEjFr+ojuxm5kZjGjj60/ZszJ6RD2l3AzD2ES51 X-Google-Smtp-Source: AGHT+IFU2jXbs0bvOtVBqoUQ1RlEegz3aF50/xKtSZN9yByWX6I2tilcL+Vod6iYO+OZZbQkqSdb X-Received: by 2002:a05:6808:1784:b0:3d1:c62a:3e0d with SMTP id 5614622812f47-3d1c62a40f2mr5744465b6e.58.1716905496753; Tue, 28 May 2024 07:11:36 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905496; cv=none; d=google.com; s=arc-20160816; b=UQonKKthXmbz1JvufvSMwcBALvcr3IDf/7osoh+OydaxJjAzAKSibvFJHM4lEEfmc6 ZG9d9WjoXO63K5RwVYKMzHF2PBRVezJHi0f0oIGRGMlT/XIXxqyWQ/MwwrBO7yY+R/UY Ck1AiX0oU6q7UqifutWadegb0++F9A2L3j7wt3OIi0rbB4ZgwkatiWxGHDFXisA0tShV RvqklASFnwo1NPfkHVQveF7mmZEB3uh+6i3/UvJPKt3WnAbJOEWJA4f01VtNag0NxRB9 sURJKR83c/D32jsARMFS0emWdfulMY4AL+XRp9sHH6O4v2mp1rll2c2nLBLd8LXvZwD9 3Yaw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=xQBOanUfnqfGmG/4cZPgLsJd77zq7zpJBHt0ftyxVho=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=Tgfp+vatsyjrYuuuAPyW4CdOzyvQMzCPRy4Uy5IKUU6JMMEBVTiWRP5Xrryhz2N7tA PfF277O+JxvLDaKYbaJJaTnUIgPfJayoaKiUWFDJEbErw06VI/s6t+i4jbu3JqGSZcFa lf5vqW/ZDvmW0uFDofBKXhbRZMfylpSLv6Y/yNxSiDhooGOJHiJWYrCDI32Z3L7H9BKK to1nez/dGwwGTgB23ry5aQgSHxKWE0+ySwVdG4OJc1V7rUZiMyQ/QiWcUeSgJ6eP0Enb H9bGFDL7qh2og8jofoHgYwlJzkle/gmw1RPKuo3hgjvPJd3mc3Y1AIxsfBSezZoJclza /fDQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=PnK5Kdax; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 71dfb90a1353d-4e4f07b78e3si1821898e0c.129.2024.05.28.07.11.36 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:11:36 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=PnK5Kdax; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV6-0001lI-1W; Tue, 28 May 2024 10:08:28 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iE-Na for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:23 -0400 Received: from mail-wr1-x433.google.com ([2a00:1450:4864:20::433]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUx-000779-Op for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:22 -0400 Received: by mail-wr1-x433.google.com with SMTP id ffacd0b85a97d-3564a0bea19so826776f8f.2 for ; Tue, 28 May 2024 07:08:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905297; x=1717510097; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=xQBOanUfnqfGmG/4cZPgLsJd77zq7zpJBHt0ftyxVho=; b=PnK5KdaxGIxkVcvbNbq/A9HF85K/jvFcIkpIMoEV9guPlxJi/50USvqX2yctYJge8T CJyZB4JkdPMIy08KuYybfByXyrrdqkt5QB/0GbKpYKhUYhDcvG9vooohH8ll8aYmhf5/ qqoOISbDCwPxtB+E9vm/Qax7qNKxW5lw/P6QIp+qiXlxEr5rDe7faUyXpcNBoKEZuqfo E2C2c0DkTu68U/E6w4EnJw57eYknec4NRVBArXckTfnCG5vT8nmHHCBeT6VTOLYTC+lG DusnOZrY/ognKXXPwMlufWzqGd6XvnqnTUKwFe28WfCnZuAPGroie7ow7qzvLmVxzBkJ FfBg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905297; x=1717510097; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=xQBOanUfnqfGmG/4cZPgLsJd77zq7zpJBHt0ftyxVho=; b=q6JAsUnm1Mc1mTGSvncqT2ru0Bgi8aUm09HofxitT3pGwPt6XyPHigJKbf1lpUJ0D6 HcZfga7Vu5XeP2tSCpBzICav6Nlzr1qXLGIlAxSCAWlfQ80vFci4WtvtLuMTI3X30DCG f14L5sXnFF8hvT9fOCF7kfPhbbDAWvXJ/Y9guhh9brCFyWW/dqwJxGvLSEnxlkQEgURA QvySXe11nSM0CdJYuiBNt/l+Ea3+IFRko2STTXgilXn6Y4khPsLPTwBTO6zO7B+UdVbz nvpP5oOG7Gi9bj9Q21k0zoyZF2/GKeVJVCI/zv6doIUySYF+URYl/fAZwSViDBNuNqEq jGRw== X-Gm-Message-State: AOJu0YzA2AJ3FHrJaRxdditbPd2p0JGSXMwMcMv3dWPe4o3NpEgVGIOY CeJlH1iBW/RKKTYImUFYjKja5YauY6WPwsDVeV+lBopSsUX0U3iJdvuwMah74y35AxhWfxrXTrL 3 X-Received: by 2002:adf:ee10:0:b0:355:12c:2733 with SMTP id ffacd0b85a97d-35526c38a52mr12439114f8f.31.1716905297117; Tue, 28 May 2024 07:08:17 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.16 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:16 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 35/42] target/arm: Convert FMAXP, FMINP, FMAXNMP, FMINNMP to decodetree Date: Tue, 28 May 2024 15:07:46 +0100 Message-Id: <20240528140753.3620597-36-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::433; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x433.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson These are the last instructions within disas_simd_three_reg_same_fp16, so remove it. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 16 ++ target/arm/tcg/a64.decode | 24 +++ target/arm/tcg/translate-a64.c | 296 ++++++--------------------------- target/arm/tcg/vec_helper.c | 16 ++ 4 files changed, 107 insertions(+), 245 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 8441b49d1f0..32684773299 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -1052,6 +1052,22 @@ DEF_HELPER_FLAGS_5(gvec_faddp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_faddp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_faddp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmaxnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fminnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "tcg/helper-a64.h" #include "tcg/helper-sve.h" diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index d2a02365e15..43557fdccc6 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -746,6 +746,18 @@ FRSQRTS_s 0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h FADDP_s 0111 1110 0.11 0000 1101 10 ..... ..... @rr_sd +FMAXP_s 0101 1110 0011 0000 1111 10 ..... ..... @rr_h +FMAXP_s 0111 1110 0.11 0000 1111 10 ..... ..... @rr_sd + +FMINP_s 0101 1110 1011 0000 1111 10 ..... ..... @rr_h +FMINP_s 0111 1110 1.11 0000 1111 10 ..... ..... @rr_sd + +FMAXNMP_s 0101 1110 0011 0000 1100 10 ..... ..... @rr_h +FMAXNMP_s 0111 1110 0.11 0000 1100 10 ..... ..... @rr_sd + +FMINNMP_s 0101 1110 1011 0000 1100 10 ..... ..... @rr_h +FMINNMP_s 0111 1110 1.11 0000 1100 10 ..... ..... @rr_sd + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -808,6 +820,18 @@ FRSQRTS_v 0.00 1110 1.1 ..... 11111 1 ..... ..... @qrrr_sd FADDP_v 0.10 1110 010 ..... 00010 1 ..... ..... @qrrr_h FADDP_v 0.10 1110 0.1 ..... 11010 1 ..... ..... @qrrr_sd +FMAXP_v 0.10 1110 010 ..... 00110 1 ..... ..... @qrrr_h +FMAXP_v 0.10 1110 0.1 ..... 11110 1 ..... ..... @qrrr_sd + +FMINP_v 0.10 1110 110 ..... 00110 1 ..... ..... @qrrr_h +FMINP_v 0.10 1110 1.1 ..... 11110 1 ..... ..... @qrrr_sd + +FMAXNMP_v 0.10 1110 010 ..... 00000 1 ..... ..... @qrrr_h +FMAXNMP_v 0.10 1110 0.1 ..... 11000 1 ..... ..... @qrrr_sd + +FMINNMP_v 0.10 1110 110 ..... 00000 1 ..... ..... @qrrr_h +FMINNMP_v 0.10 1110 1.1 ..... 11000 1 ..... ..... @qrrr_sd + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 78949ab34f0..07415bd2855 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5217,6 +5217,34 @@ static gen_helper_gvec_3_ptr * const f_vector_faddp[3] = { }; TRANS(FADDP_v, do_fp3_vector, a, f_vector_faddp) +static gen_helper_gvec_3_ptr * const f_vector_fmaxp[3] = { + gen_helper_gvec_fmaxp_h, + gen_helper_gvec_fmaxp_s, + gen_helper_gvec_fmaxp_d, +}; +TRANS(FMAXP_v, do_fp3_vector, a, f_vector_fmaxp) + +static gen_helper_gvec_3_ptr * const f_vector_fminp[3] = { + gen_helper_gvec_fminp_h, + gen_helper_gvec_fminp_s, + gen_helper_gvec_fminp_d, +}; +TRANS(FMINP_v, do_fp3_vector, a, f_vector_fminp) + +static gen_helper_gvec_3_ptr * const f_vector_fmaxnmp[3] = { + gen_helper_gvec_fmaxnump_h, + gen_helper_gvec_fmaxnump_s, + gen_helper_gvec_fmaxnump_d, +}; +TRANS(FMAXNMP_v, do_fp3_vector, a, f_vector_fmaxnmp) + +static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = { + gen_helper_gvec_fminnump_h, + gen_helper_gvec_fminnump_s, + gen_helper_gvec_fminnump_d, +}; +TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -5452,6 +5480,10 @@ static bool do_fp3_scalar_pair(DisasContext *s, arg_rr_e *a, const FPScalar *f) } TRANS(FADDP_s, do_fp3_scalar_pair, a, &f_scalar_fadd) +TRANS(FMAXP_s, do_fp3_scalar_pair, a, &f_scalar_fmax) +TRANS(FMINP_s, do_fp3_scalar_pair, a, &f_scalar_fmin) +TRANS(FMAXNMP_s, do_fp3_scalar_pair, a, &f_scalar_fmaxnm) +TRANS(FMINNMP_s, do_fp3_scalar_pair, a, &f_scalar_fminnm) /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the @@ -8393,7 +8425,6 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 12, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_ptr fpst; /* For some ops (the FP ones), size[1] is part of the encoding. * For ADDP strictly it is not but size[1] is always 1 for valid @@ -8410,33 +8441,13 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - fpst = NULL; break; + default: case 0xc: /* FMAXNMP */ + case 0xd: /* FADDP */ case 0xf: /* FMAXP */ case 0x2c: /* FMINNMP */ case 0x2f: /* FMINP */ - /* FP op, size[0] is 32 or 64 bit*/ - if (!u) { - if ((size & 1) || !dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } else { - size = MO_16; - } - } else { - size = extract32(size, 0, 1) ? MO_64 : MO_32; - } - - if (!fp_access_check(s)) { - return; - } - - fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - break; - default: - case 0xd: /* FADDP */ unallocated_encoding(s); return; } @@ -8453,71 +8464,18 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0x3b: /* ADDP */ tcg_gen_add_i64(tcg_res, tcg_op1, tcg_op2); break; - case 0xc: /* FMAXNMP */ - gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FMAXP */ - gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2c: /* FMINNMP */ - gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2f: /* FMINP */ - gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst); - break; default: + case 0xc: /* FMAXNMP */ case 0xd: /* FADDP */ + case 0xf: /* FMAXP */ + case 0x2c: /* FMINNMP */ + case 0x2f: /* FMINP */ g_assert_not_reached(); } write_fp_dreg(s, rd, tcg_res); } else { - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op1, rn, 0, size); - read_vec_element_i32(s, tcg_op2, rn, 1, size); - - if (size == MO_16) { - switch (opcode) { - case 0xc: /* FMAXNMP */ - gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FMAXP */ - gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2c: /* FMINNMP */ - gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2f: /* FMINP */ - gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0xd: /* FADDP */ - g_assert_not_reached(); - } - } else { - switch (opcode) { - case 0xc: /* FMAXNMP */ - gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FMAXP */ - gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2c: /* FMINNMP */ - gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2f: /* FMINP */ - gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - case 0xd: /* FADDP */ - g_assert_not_reached(); - } - } - - write_fp_sreg(s, rd, tcg_res); + g_assert_not_reached(); } } @@ -10997,16 +10955,8 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, int size, int rn, int rm, int rd) { - TCGv_ptr fpst; int pass; - /* Floating point operations need fpst */ - if (opcode >= 0x58) { - fpst = fpstatus_ptr(FPST_FPCR); - } else { - fpst = NULL; - } - if (!fp_access_check(s)) { return; } @@ -11030,20 +10980,12 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, case 0x17: /* ADDP */ tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2); break; - case 0x58: /* FMAXNMP */ - gen_helper_vfp_maxnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x5e: /* FMAXP */ - gen_helper_vfp_maxd(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x78: /* FMINNMP */ - gen_helper_vfp_minnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x7e: /* FMINP */ - gen_helper_vfp_mind(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; default: + case 0x58: /* FMAXNMP */ case 0x5a: /* FADDP */ + case 0x5e: /* FMAXP */ + case 0x78: /* FMINNMP */ + case 0x7e: /* FMINP */ g_assert_not_reached(); } } @@ -11097,21 +11039,12 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, genfn = fns[size][u]; break; } - /* The FP operations are all on single floats (32 bit) */ - case 0x58: /* FMAXNMP */ - gen_helper_vfp_maxnums(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x5e: /* FMAXP */ - gen_helper_vfp_maxs(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x78: /* FMINNMP */ - gen_helper_vfp_minnums(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x7e: /* FMINP */ - gen_helper_vfp_mins(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; default: + case 0x58: /* FMAXNMP */ case 0x5a: /* FADDP */ + case 0x5e: /* FMAXP */ + case 0x78: /* FMINNMP */ + case 0x7e: /* FMINP */ g_assert_not_reached(); } @@ -11150,18 +11083,6 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) } switch (fpopcode) { - case 0x58: /* FMAXNMP */ - case 0x5e: /* FMAXP */ - case 0x78: /* FMINNMP */ - case 0x7e: /* FMINP */ - if (size && !is_q) { - unallocated_encoding(s); - return; - } - handle_simd_3same_pair(s, is_q, 0, fpopcode, size ? MO_64 : MO_32, - rn, rm, rd); - return; - case 0x1d: /* FMLAL */ case 0x3d: /* FMLSL */ case 0x59: /* FMLAL2 */ @@ -11195,14 +11116,18 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) case 0x3a: /* FSUB */ case 0x3e: /* FMIN */ case 0x3f: /* FRSQRTS */ + case 0x58: /* FMAXNMP */ case 0x5a: /* FADDP */ case 0x5b: /* FMUL */ case 0x5c: /* FCMGE */ case 0x5d: /* FACGE */ + case 0x5e: /* FMAXP */ case 0x5f: /* FDIV */ + case 0x78: /* FMINNMP */ case 0x7a: /* FABD */ case 0x7d: /* FACGT */ case 0x7c: /* FCMGT */ + case 0x7e: /* FMINP */ unallocated_encoding(s); return; } @@ -11511,124 +11436,6 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) } } -/* - * Advanced SIMD three same (ARMv8.2 FP16 variants) - * - * 31 30 29 28 24 23 22 21 20 16 15 14 13 11 10 9 5 4 0 - * +---+---+---+-----------+---------+------+-----+--------+---+------+------+ - * | 0 | Q | U | 0 1 1 1 0 | a | 1 0 | Rm | 0 0 | opcode | 1 | Rn | Rd | - * +---+---+---+-----------+---------+------+-----+--------+---+------+------+ - * - * This includes FMULX, FCMEQ (register), FRECPS, FRSQRTS, FCMGE - * (register), FACGE, FABD, FCMGT (register) and FACGT. - * - */ -static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) -{ - int opcode = extract32(insn, 11, 3); - int u = extract32(insn, 29, 1); - int a = extract32(insn, 23, 1); - int is_q = extract32(insn, 30, 1); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - /* - * For these floating point ops, the U, a and opcode bits - * together indicate the operation. - */ - int fpopcode = opcode | (a << 3) | (u << 4); - bool pairwise; - TCGv_ptr fpst; - int pass; - - switch (fpopcode) { - case 0x10: /* FMAXNMP */ - case 0x16: /* FMAXP */ - case 0x18: /* FMINNMP */ - case 0x1e: /* FMINP */ - pairwise = true; - break; - default: - case 0x0: /* FMAXNM */ - case 0x1: /* FMLA */ - case 0x2: /* FADD */ - case 0x3: /* FMULX */ - case 0x4: /* FCMEQ */ - case 0x6: /* FMAX */ - case 0x7: /* FRECPS */ - case 0x8: /* FMINNM */ - case 0x9: /* FMLS */ - case 0xa: /* FSUB */ - case 0xe: /* FMIN */ - case 0xf: /* FRSQRTS */ - case 0x12: /* FADDP */ - case 0x13: /* FMUL */ - case 0x14: /* FCMGE */ - case 0x15: /* FACGE */ - case 0x17: /* FDIV */ - case 0x1a: /* FABD */ - case 0x1c: /* FCMGT */ - case 0x1d: /* FACGT */ - unallocated_encoding(s); - return; - } - - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - fpst = fpstatus_ptr(FPST_FPCR_F16); - - if (pairwise) { - int maxpass = is_q ? 8 : 4; - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res[8]; - - for (pass = 0; pass < maxpass; pass++) { - int passreg = pass < (maxpass / 2) ? rn : rm; - int passelt = (pass << 1) & (maxpass - 1); - - read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_16); - read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_16); - tcg_res[pass] = tcg_temp_new_i32(); - - switch (fpopcode) { - case 0x10: /* FMAXNMP */ - gen_helper_advsimd_maxnumh(tcg_res[pass], tcg_op1, tcg_op2, - fpst); - break; - case 0x16: /* FMAXP */ - gen_helper_advsimd_maxh(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - case 0x18: /* FMINNMP */ - gen_helper_advsimd_minnumh(tcg_res[pass], tcg_op1, tcg_op2, - fpst); - break; - case 0x1e: /* FMINP */ - gen_helper_advsimd_minh(tcg_res[pass], tcg_op1, tcg_op2, fpst); - break; - default: - case 0x12: /* FADDP */ - g_assert_not_reached(); - } - } - - for (pass = 0; pass < maxpass; pass++) { - write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_16); - } - } else { - g_assert_not_reached(); - } - - clear_vec_high(s, is_q, rd); -} - /* AdvSIMD three same extra * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+---+--------+---+----+----+ @@ -13391,7 +13198,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, - { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x00000000, 0x00000000, NULL } }; diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 28989c7d7a7..79e1fdcaa9f 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2260,6 +2260,22 @@ DO_3OP_PAIR(gvec_faddp_h, float16_add, float16, H2) DO_3OP_PAIR(gvec_faddp_s, float32_add, float32, H4) DO_3OP_PAIR(gvec_faddp_d, float64_add, float64, ) +DO_3OP_PAIR(gvec_fmaxp_h, float16_max, float16, H2) +DO_3OP_PAIR(gvec_fmaxp_s, float32_max, float32, H4) +DO_3OP_PAIR(gvec_fmaxp_d, float64_max, float64, ) + +DO_3OP_PAIR(gvec_fminp_h, float16_min, float16, H2) +DO_3OP_PAIR(gvec_fminp_s, float32_min, float32, H4) +DO_3OP_PAIR(gvec_fminp_d, float64_min, float64, ) + +DO_3OP_PAIR(gvec_fmaxnump_h, float16_maxnum, float16, H2) +DO_3OP_PAIR(gvec_fmaxnump_s, float32_maxnum, float32, H4) +DO_3OP_PAIR(gvec_fmaxnump_d, float64_maxnum, float64, ) + +DO_3OP_PAIR(gvec_fminnump_h, float16_minnum, float16, H2) +DO_3OP_PAIR(gvec_fminnump_s, float32_minnum, float32, H4) +DO_3OP_PAIR(gvec_fminnump_d, float64_minnum, float64, ) + #define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ From patchwork Tue May 28 14:07:47 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799462 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255507wrz; Tue, 28 May 2024 07:10:05 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVIC33wlhT5LVKq7dQG4G51ag8Z1kBK5AEuE1tckZjJOumrGEsbdkXJ3zT+yik88UE/q/CVaihg84m3wbrXy42p X-Google-Smtp-Source: AGHT+IHa4THOnAr9enEsApCwMdRplMGZHgIB4zp0nSmXLL7RVyuPSOhs+8sp4FQgxKbCuprg8ivV X-Received: by 2002:ac8:5794:0:b0:43e:3b8e:6713 with SMTP id d75a77b69052e-43fb0e51708mr127453611cf.2.1716905405719; Tue, 28 May 2024 07:10:05 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905405; cv=none; d=google.com; s=arc-20160816; b=HkMypa4fBO5ucbPRor1Wbw0IlVUipFnNOPI1FqND4RUQwyZ7I4BLLfTY+lVcqoHWTa 8jhWiy9p4y/Ug9f13JQDcb0g9SJN2FZZPVGJwZVqlfBTGwFBf0v62IfZKIR16UoqP3jz CZVJ94ZOEJ2sT1tcRabPxBuDE63z9hts5BNjwMl7XRbjA3t65wEjNv1MO0qNRkkFXBDu W4T3wzLKb6wZjpEux8hnwjB6LXEZk/982gAzWTeK8msMTZv0+/YTL6ofg3fqTR8nr+eH MFzLUIk4rvgitC3/h0i7iqc1ZeWnmp32Xc5fujFUYlAT7cxFzH8sPXHJO80Geg9pDUh6 yDqQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=V17D18da50ugL32JODWz478hrlXAz3Sw738V6ZYSXkw=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=A/iYYs8N/t6GmgrQ5PiJt+JTkGmaQ9tcZQpL1kg604S5A2J79Evrt5Mvn1/+BCFkPM eulVolWTT1oS/qvq8FVvyIHFd6a10g5Qcv4xN+bP1yGyP6pMGicTCyXnmZhux8jNp/gz 87BXQ2tLPoJ0HyIWp4Pp2jVgtkT3EQhZakQa4u7lCOe4tt+McoTgVb2Bm5LkeSOY9fdD VheVXox5u50uZGTyEQDYf+3ZIGpcA1+QDUEe8PZXkq1bSN3CUHuSTmg86zeKBubCfni5 eO1na6f6uDxN/clWXigQ9gALffEo+vnv/0xjyjZacMbbia2wyC5+AmWIs+pEs4eqKHwf QdYA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=Dvveghok; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id d75a77b69052e-43fb17b9757si113327501cf.19.2024.05.28.07.10.05 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:05 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=Dvveghok; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVL-0001sr-Bj; Tue, 28 May 2024 10:08:43 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxUy-0001hh-Ul for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:21 -0400 Received: from mail-wr1-x431.google.com ([2a00:1450:4864:20::431]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUw-00077J-VQ for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:20 -0400 Received: by mail-wr1-x431.google.com with SMTP id ffacd0b85a97d-35a264cb831so648811f8f.2 for ; Tue, 28 May 2024 07:08:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905297; x=1717510097; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=V17D18da50ugL32JODWz478hrlXAz3Sw738V6ZYSXkw=; b=DvveghokU/LMqTg74zr+BYp4Lhm/XtR9VnmrYVxrVs2zAeKgVgjlYTeEnmtdarzya7 ytHksUtJUqEawpUHYOMI4ZjXAeFYWSdtSwivbwJjWQlLDjSVA3FuGHj83SDsxNyd1h2c ghStGp0OygzC9NvGXTe4I12dQ0Q/lynjfRCpKjUUw0A1xBXkN95hPnoA/Hnh+f8jxKmJ 47jSKqrBa0wt3ynQ0Vngy4SB9VEA1y7iKOWUxB7suNcvHnLGduR/kyel5GKYUFNxNg0l HUU3Bws/DQPl9rLmDR63PIZYU49q5NrtLvkc6H6S+VsBQOrDsrDKoXsXQtMMC8vby3Ez lQ6A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905297; x=1717510097; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=V17D18da50ugL32JODWz478hrlXAz3Sw738V6ZYSXkw=; b=Fh3HhquqcUDDIkFxLQ12VGixXL2ijQKVpoGLtMwtKY6ob7GqpAeFAsVyNCnXGm79wQ oyqIwZMuzMuGgGIx6xj59sG6Zs6BseudjqVLF+sePApDoOMpCHyETYMMPnjzKwejwHAN RZxuNyEUhayhuO8PYSOum4Gs2+eFpU2heaH5f4bBaMZZLYx+byDk27+PALFgr7Sb++06 nnyQzJj00XWB1YkjRPw70dLbbWA6uJR8hOQLo5HT0fw8kHuZqjWP6tNf6LoqXZ7myNC6 +6GF/KKWTY8fSA1IQBakj84nxrQEMiNSwCvZeuxRowhCUSDIZdEqEv61qu6EN+FQCPm5 UNjQ== X-Gm-Message-State: AOJu0YzpgUbG4B9ndIFGRsv/R+wWt1uF/TkEtxkg2XyJjtUDAeZbskIO +IAmGSuC93fMKBc10hwMYiJSXb6s4NOdRsANS4H6Nsl8UL0/QCKBmMcYn4AFrSMaqfe8OxzGU/U U X-Received: by 2002:a5d:44ca:0:b0:354:f142:65b0 with SMTP id ffacd0b85a97d-35527051464mr8607232f8f.37.1716905297640; Tue, 28 May 2024 07:08:17 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.17 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:17 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 36/42] target/arm: Use gvec for neon faddp, fmaxp, fminp Date: Tue, 28 May 2024 15:07:47 +0100 Message-Id: <20240528140753.3620597-37-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::431; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x431.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 7 ----- target/arm/tcg/translate-neon.c | 55 ++------------------------------- target/arm/tcg/vec_helper.c | 45 --------------------------- 3 files changed, 3 insertions(+), 104 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 32684773299..065460ea80e 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -650,13 +650,6 @@ DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) - DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 144f18ba22e..2326a05a0aa 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -1144,6 +1144,9 @@ DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) DO_3S_FP_GVEC(VRSQRTS, gen_helper_gvec_rsqrts_nf_s, gen_helper_gvec_rsqrts_nf_h) +DO_3S_FP_GVEC(VPADD, gen_helper_gvec_faddp_s, gen_helper_gvec_faddp_h) +DO_3S_FP_GVEC(VPMAX, gen_helper_gvec_fmaxp_s, gen_helper_gvec_fmaxp_h) +DO_3S_FP_GVEC(VPMIN, gen_helper_gvec_fminp_s, gen_helper_gvec_fminp_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -1180,58 +1183,6 @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, - gen_helper_gvec_3_ptr *fn) -{ - /* FP pairwise operations */ - TCGv_ptr fpstatus; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - assert(a->q == 0); /* enforced by decode patterns */ - - - fpstatus = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), - vfp_reg_offset(1, a->vn), - vfp_reg_offset(1, a->vm), - fpstatus, 8, 8, 0, fn); - - return true; -} - -/* - * For all the functions using this macro, size == 1 means fp16, - * which is an architecture extension we don't implement yet. - */ -#define DO_3S_FP_PAIR(INSN,FUNC) \ - static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size == MO_16) { \ - if (!dc_isar_feature(aa32_fp16_arith, s)) { \ - return false; \ - } \ - return do_3same_fp_pair(s, a, FUNC##h); \ - } \ - return do_3same_fp_pair(s, a, FUNC##s); \ - } - -DO_3S_FP_PAIR(VPADD, gen_helper_neon_padd) -DO_3S_FP_PAIR(VPMAX, gen_helper_neon_pmax) -DO_3S_FP_PAIR(VPMIN, gen_helper_neon_pmin) - static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { /* Handle a 2-reg-shift insn which can be vectorized. */ diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 79e1fdcaa9f..26a9ca9c14a 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2192,51 +2192,6 @@ DO_ABA(gvec_uaba_d, uint64_t) #undef DO_ABA -#define DO_NEON_PAIRWISE(NAME, OP) \ - void HELPER(NAME##s)(void *vd, void *vn, void *vm, \ - void *stat, uint32_t oprsz) \ - { \ - float_status *fpst = stat; \ - float32 *d = vd; \ - float32 *n = vn; \ - float32 *m = vm; \ - float32 r0, r1; \ - \ - /* Read all inputs before writing outputs in case vm == vd */ \ - r0 = float32_##OP(n[H4(0)], n[H4(1)], fpst); \ - r1 = float32_##OP(m[H4(0)], m[H4(1)], fpst); \ - \ - d[H4(0)] = r0; \ - d[H4(1)] = r1; \ - } \ - \ - void HELPER(NAME##h)(void *vd, void *vn, void *vm, \ - void *stat, uint32_t oprsz) \ - { \ - float_status *fpst = stat; \ - float16 *d = vd; \ - float16 *n = vn; \ - float16 *m = vm; \ - float16 r0, r1, r2, r3; \ - \ - /* Read all inputs before writing outputs in case vm == vd */ \ - r0 = float16_##OP(n[H2(0)], n[H2(1)], fpst); \ - r1 = float16_##OP(n[H2(2)], n[H2(3)], fpst); \ - r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ - r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ - \ - d[H2(0)] = r0; \ - d[H2(1)] = r1; \ - d[H2(2)] = r2; \ - d[H2(3)] = r3; \ - } - -DO_NEON_PAIRWISE(neon_padd, add) -DO_NEON_PAIRWISE(neon_pmax, max) -DO_NEON_PAIRWISE(neon_pmin, min) - -#undef DO_NEON_PAIRWISE - #define DO_3OP_PAIR(NAME, FUNC, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ From patchwork Tue May 28 14:07:48 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799461 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255465wrz; Tue, 28 May 2024 07:10:01 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCUKmMfsgpLCkJ86tDmgoLIUk0Znyuln6qxqXwUNtddWgrL2QYp0cTCjG4Dl78tAknIjKWu9+SjOH2jnTd7uHbj6 X-Google-Smtp-Source: AGHT+IGdgMaqdTSaVc4Z5mhpitf8HEAGjHMGyP38wm6qw5DK/s/W3WOlFAeLt6l2jwt3KJQ6DSVB X-Received: by 2002:ae9:c01a:0:b0:790:f2dc:8b73 with SMTP id af79cd13be357-794ab110c2cmr1345706385a.55.1716905401513; Tue, 28 May 2024 07:10:01 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905401; cv=none; d=google.com; s=arc-20160816; b=LZ01HuylDvClqAgYCK9sMJKEqLnOYZImfI9yWQWTaDDRtDmYq6a8ww/cxLwUDCsf+3 CaZ3O5Us3M8RhD4nmLaGQuy2pylKLmWUiFlSjQTHsOkMTCB2CrhUV65eKGtbv2T4a0qe JF3pLoLs0pour08Dxw29IIL3Mm7b5fhulAlSz9guBcAewMMM+c5ozJnqIeVD4+wmGvq2 bPZYisDmhHz4Y/eRhBBcIwPt1cUlif2R47vDekfTwOHrKo+pZSgDl32oQ/wV58vznwhC GJM2CKXFsajr3Vs0tuz8VRa64kcjRb95VvebiV7pkq20xs0+XIhBMy6DUZejl5vmBuNp 9xTQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=+Q84CTXM19IVDYjWje//MGb/GIXnxXHoqK8YpmK1ovQ=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=wGquoJtwa6yrLUzlnpJ0Y66zgnSnlwe7TGsuz56W1u0U7LV2akg6bP7O7WUwbj/qo4 j07m8C3/H3cSsdslmfuhMeOYK4NTkaeHchw5fYLcHmETWDHpkDG/XfO4TFjjDkQo0Sy4 8wlNS+4MPhYnqbJYc8iymCJvxanktu/9uPBn2U27oVHcF6MdHOgYv8CX+lh7y33kixvI 7EQt8azWjLpdzf1SAOfblOrSp74ssJRxeSqbwBRNRdv7kfVJLSRqhbR0d3BKLbUvl7k5 cR7uUqXjbY0//IQVos+aJeRYvvz69beMAJatZ7OqfCRq3788x9QDCd0l8Ttf5o1CbLOE bK5Q==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=U3WDYD7F; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id af79cd13be357-794abd608d2si1021796285a.757.2024.05.28.07.10.01 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:10:01 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=U3WDYD7F; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV4-0001ki-I1; Tue, 28 May 2024 10:08:26 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iG-OT for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:23 -0400 Received: from mail-wr1-x432.google.com ([2a00:1450:4864:20::432]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUx-00077U-Ow for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:22 -0400 Received: by mail-wr1-x432.google.com with SMTP id ffacd0b85a97d-35bf77ba8fbso244492f8f.2 for ; Tue, 28 May 2024 07:08:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905298; x=1717510098; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=+Q84CTXM19IVDYjWje//MGb/GIXnxXHoqK8YpmK1ovQ=; b=U3WDYD7FqaJ+y0VvYpJI9d4o8YMxNMhJMl8SGEfK+LY/bdb8zzTj0bF0jFkVYVIlRK ovuEGyk3+5MO42l4aER5uGuU4O050j/IsIEVOSFVWR3EI9U53otsusLHotqWBWqS5KUZ QmNIRiLOg53mJtc67/AqFh249FWf3oTHcID5gAWLRZGwwJgS3zGbgkj/5r0hasffRWdW 7jUIFZOx2FjzDSBaw+PeZZJBamcHsYQi0xUjdg3w4TDMw6BjfbyyCDt48VVyJ9STPIHi kZDgef+bNbGk3i5WD7Ea4X2HEUDzBYOmAmcO1wEAstpEsllfDRT8kFgMFWdVDCSX61AW uyQw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905298; x=1717510098; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=+Q84CTXM19IVDYjWje//MGb/GIXnxXHoqK8YpmK1ovQ=; b=qZBX5mMzfPCJmpGMt/SVp/hUAdNS2VMFEKd2prp8fH9205xmhg3kCf5NnbLbM5TZ6S yrxljlshVeXzcVXh8Uyu2H3FV8n5dUwxCRcAdYmo3fQAh0IuyPGiWtt0dXrgwbTLYC/8 9Z4oDe2wuizcAc18GVx+Wz79kAxAapZRMosijkNMXQSSn6u7CynrwTHSeWTMimoKAFR/ K3Hi7t/+R1fAt9SqjbLoZIGEEvfpxjBQsXXBb+r2f+jDuS7uEWtd70H3kLvovilY0OrG 1dL2yYuzsF7H5iEBHRZ3Kv15OiF48bbZ/dXIzlpkXzpkyzJ4aDbz8bNdd20KOKGwy78+ uToQ== X-Gm-Message-State: AOJu0YyinHpmqFfrQqqSRbXiAs99qRovgIyPfcDMfh1YEz133GwlvF/C NkvAfoaJhXu8yW31g10OERYoUixyYL3amkh9D+ZdrlfNt7kflMDmFkDbdNk09a5+IX+fBhn1uox F X-Received: by 2002:a5d:5221:0:b0:351:b56e:8bc3 with SMTP id ffacd0b85a97d-3552fe02a52mr10742832f8f.53.1716905298228; Tue, 28 May 2024 07:08:18 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.17 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:17 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 37/42] target/arm: Convert ADDP to decodetree Date: Tue, 28 May 2024 15:07:48 +0100 Message-Id: <20240528140753.3620597-38-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::432; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x432.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 5 ++ target/arm/tcg/translate.h | 3 + target/arm/tcg/a64.decode | 6 ++ target/arm/tcg/gengvec.c | 12 ++++ target/arm/tcg/translate-a64.c | 128 ++++++--------------------------- target/arm/tcg/vec_helper.c | 30 ++++++++ 6 files changed, 77 insertions(+), 107 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 065460ea80e..d3579a101f4 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -1061,6 +1061,11 @@ DEF_HELPER_FLAGS_5(gvec_fminnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i DEF_HELPER_FLAGS_5(gvec_fminnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_addp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_addp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_addp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_addp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "tcg/helper-a64.h" #include "tcg/helper-sve.h" diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index b05a9eb6685..04771f483b6 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -514,6 +514,9 @@ void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_addp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 43557fdccc6..84f5bcc0e08 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -38,6 +38,7 @@ &qrrrr_e q rd rn rm ra esz @rr_h ........ ... ..... ...... rn:5 rd:5 &rr_e esz=1 +@rr_d ........ ... ..... ...... rn:5 rd:5 &rr_e esz=3 @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 @@ -56,6 +57,7 @@ @qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 @qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd +@qrrr_e . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5 &qrrr_e @qrrx_h . q:1 .. .... .. .. rm:4 .... . . rn:5 rd:5 \ &qrrx_e esz=1 idx=%hlm @@ -758,6 +760,8 @@ FMAXNMP_s 0111 1110 0.11 0000 1100 10 ..... ..... @rr_sd FMINNMP_s 0101 1110 1011 0000 1100 10 ..... ..... @rr_h FMINNMP_s 0111 1110 1.11 0000 1100 10 ..... ..... @rr_sd +ADDP_s 0101 1110 1111 0001 1011 10 ..... ..... @rr_d + ### Advanced SIMD three same FADD_v 0.00 1110 010 ..... 00010 1 ..... ..... @qrrr_h @@ -832,6 +836,8 @@ FMAXNMP_v 0.10 1110 0.1 ..... 11000 1 ..... ..... @qrrr_sd FMINNMP_v 0.10 1110 110 ..... 00000 1 ..... ..... @qrrr_h FMINNMP_v 0.10 1110 1.1 ..... 11000 1 ..... ..... @qrrr_sd +ADDP_v 0.00 1110 ..1 ..... 10111 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 7a1856253ff..f010dd5a0e8 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -1610,3 +1610,15 @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, }; tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } + +void gen_gvec_addp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_addp_b, + gen_helper_gvec_addp_h, + gen_helper_gvec_addp_s, + gen_helper_gvec_addp_d, + }; + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 07415bd2855..b8add91112d 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5245,6 +5245,8 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = { }; TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp) +TRANS(ADDP_v, do_gvec_fn3, a, gen_gvec_addp) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -5485,6 +5487,20 @@ TRANS(FMINP_s, do_fp3_scalar_pair, a, &f_scalar_fmin) TRANS(FMAXNMP_s, do_fp3_scalar_pair, a, &f_scalar_fmaxnm) TRANS(FMINNMP_s, do_fp3_scalar_pair, a, &f_scalar_fminnm) +static bool trans_ADDP_s(DisasContext *s, arg_rr_e *a) +{ + if (fp_access_check(s)) { + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + + read_vec_element(s, t0, a->rn, 0, MO_64); + read_vec_element(s, t1, a->rn, 1, MO_64); + tcg_gen_add_i64(t0, t0, t1); + write_fp_dreg(s, a->rd, t0); + } + return true; +} + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -8412,73 +8428,6 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) } } -/* AdvSIMD scalar pairwise - * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +-----+---+-----------+------+-----------+--------+-----+------+------+ - * | 0 1 | U | 1 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 | Rn | Rd | - * +-----+---+-----------+------+-----------+--------+-----+------+------+ - */ -static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) -{ - int u = extract32(insn, 29, 1); - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 12, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - /* For some ops (the FP ones), size[1] is part of the encoding. - * For ADDP strictly it is not but size[1] is always 1 for valid - * encodings. - */ - opcode |= (extract32(size, 1, 1) << 5); - - switch (opcode) { - case 0x3b: /* ADDP */ - if (u || size != 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - break; - default: - case 0xc: /* FMAXNMP */ - case 0xd: /* FADDP */ - case 0xf: /* FMAXP */ - case 0x2c: /* FMINNMP */ - case 0x2f: /* FMINP */ - unallocated_encoding(s); - return; - } - - if (size == MO_64) { - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op1, rn, 0, MO_64); - read_vec_element(s, tcg_op2, rn, 1, MO_64); - - switch (opcode) { - case 0x3b: /* ADDP */ - tcg_gen_add_i64(tcg_res, tcg_op1, tcg_op2); - break; - default: - case 0xc: /* FMAXNMP */ - case 0xd: /* FADDP */ - case 0xf: /* FMAXP */ - case 0x2c: /* FMINNMP */ - case 0x2f: /* FMINP */ - g_assert_not_reached(); - } - - write_fp_dreg(s, rd, tcg_res); - } else { - g_assert_not_reached(); - } -} - /* * Common SSHR[RA]/USHR[RA] - Shift right (optional rounding/accumulate) * @@ -10965,34 +10914,7 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, * adjacent elements being operated on to produce an element in the result. */ if (size == 3) { - TCGv_i64 tcg_res[2]; - - for (pass = 0; pass < 2; pass++) { - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - int passreg = (pass == 0) ? rn : rm; - - read_vec_element(s, tcg_op1, passreg, 0, MO_64); - read_vec_element(s, tcg_op2, passreg, 1, MO_64); - tcg_res[pass] = tcg_temp_new_i64(); - - switch (opcode) { - case 0x17: /* ADDP */ - tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2); - break; - default: - case 0x58: /* FMAXNMP */ - case 0x5a: /* FADDP */ - case 0x5e: /* FMAXP */ - case 0x78: /* FMINNMP */ - case 0x7e: /* FMINP */ - g_assert_not_reached(); - } - } - - for (pass = 0; pass < 2; pass++) { - write_vec_element(s, tcg_res[pass], rd, pass, MO_64); - } + g_assert_not_reached(); } else { int maxpass = is_q ? 4 : 2; TCGv_i32 tcg_res[4]; @@ -11009,16 +10931,6 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, tcg_res[pass] = tcg_temp_new_i32(); switch (opcode) { - case 0x17: /* ADDP */ - { - static NeonGenTwoOpFn * const fns[3] = { - gen_helper_neon_padd_u8, - gen_helper_neon_padd_u16, - tcg_gen_add_i32, - }; - genfn = fns[size]; - break; - } case 0x14: /* SMAXP, UMAXP */ { static NeonGenTwoOpFn * const fns[3][2] = { @@ -11040,6 +10952,7 @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, break; } default: + case 0x17: /* ADDP */ case 0x58: /* FMAXNMP */ case 0x5a: /* FADDP */ case 0x5e: /* FMAXP */ @@ -11401,7 +11314,6 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) case 0x3: /* logic ops */ disas_simd_3same_logic(s, insn); break; - case 0x17: /* ADDP */ case 0x14: /* SMAXP, UMAXP */ case 0x15: /* SMINP, UMINP */ { @@ -11433,6 +11345,9 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) default: disas_simd_3same_int(s, insn); break; + case 0x17: /* ADDP */ + unallocated_encoding(s); + break; } } @@ -13195,7 +13110,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x5e008400, 0xdf208400, disas_simd_scalar_three_reg_same_extra }, { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, - { 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 26a9ca9c14a..5069899415c 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2231,6 +2231,36 @@ DO_3OP_PAIR(gvec_fminnump_h, float16_minnum, float16, H2) DO_3OP_PAIR(gvec_fminnump_s, float32_minnum, float32, H4) DO_3OP_PAIR(gvec_fminnump_d, float64_minnum, float64, ) +#undef DO_3OP_PAIR + +#define DO_3OP_PAIR(NAME, FUNC, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + intptr_t oprsz = simd_oprsz(desc); \ + intptr_t half = oprsz / sizeof(TYPE) / 2; \ + TYPE *d = vd, *n = vn, *m = vm; \ + if (unlikely(d == m)) { \ + m = memcpy(&scratch, m, oprsz); \ + } \ + for (intptr_t i = 0; i < half; ++i) { \ + d[H(i)] = FUNC(n[H(i * 2)], n[H(i * 2 + 1)]); \ + } \ + for (intptr_t i = 0; i < half; ++i) { \ + d[H(i + half)] = FUNC(m[H(i * 2)], m[H(i * 2 + 1)]); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +#define ADD(A, B) (A + B) +DO_3OP_PAIR(gvec_addp_b, ADD, uint8_t, H1) +DO_3OP_PAIR(gvec_addp_h, ADD, uint16_t, H2) +DO_3OP_PAIR(gvec_addp_s, ADD, uint32_t, H4) +DO_3OP_PAIR(gvec_addp_d, ADD, uint64_t, ) +#undef ADD + +#undef DO_3OP_PAIR + #define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ From patchwork Tue May 28 14:07:49 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799474 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp256865wrz; Tue, 28 May 2024 07:12:09 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVGcftEqSXW9AQxuxc9f5LYxQ/jVMWsBDm3m8IXRzKLGMR8+fyh4rIPEVY1CoxwrhzpwyiynIHitcjJS2G1jEvc X-Google-Smtp-Source: AGHT+IHMI2wJrEOZKIBzhIGxpzULhIqqAsPVrLHbUUEEpv6a5anZgTfJMKyDjgn5Jj7cCuvmTrPj X-Received: by 2002:a05:6808:3d0:b0:3c9:a968:d0b2 with SMTP id 5614622812f47-3d1a61138a5mr11304651b6e.32.1716905529486; Tue, 28 May 2024 07:12:09 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905529; cv=none; d=google.com; s=arc-20160816; b=IN/JQbmTfUQrXjJcVdXRt+B2LYj+VaTj0CbjMIOhVI5JUTEhlx32KtMXZQoxPHt0xh iVaJkslAe3rJUGVnAJ7etGyC/c4IG/cEn+FJtSoqJ30yej0R6bNcVBzWdH4f0KvwY1Yz rvurC80LQ0gq6JZzfp+LtJBI9AI2OVHFFXjAQgowAyrjbcGdDLMgKgfIYC/qKq1mvuxa gxNyAUfvPUTQdzAoC3eknKYS6eO2yltGDrgjSbSvG/bMvki/mUMdJwL0RRhCUSMuPY9Z hJEMLmD4XUxHewPoLhtafjkcWyEEdcz001YXnKrbz4z9l6gsTgDpQhWensW0o+Z3rfTe e2cg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=8FAqlHwdIGYJ/Fo9nu8qvPKK59RKx8O/bWyYtfutAkU=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=Nw+phG/7DfjWhGpG77DIhXdXov/dqrIWSlYwyRz7NQ7LRm7a+lS1mOIkxGlvaKals9 Bt/G9awtC1sVjn6Z724BTCLZOczjVN/t/DbHLfuYfJh7eBOZ+ntSYDzXWM7MhAp2S61M vHIpTjg0cIRdBoVilGphHOxu7NfQWpN0afmlLwrq9lbFKPSOb8KzIv1No9V6W8ab3sKK MjyGMMvP83bs1DCBN2VqNpC8k4znocr/bdiIINy7O+vv+lwF/qgN2dZckM4rzqSoRmdH 7bok/95xKLS2Ew/vx10VGybC2/yZSGBwi5b4Pq6IE77NmgA6LvCDviK7TopANAbhfF8+ e8UA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=Va5hDNDD; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48b8ca321a6si617418137.221.2024.05.28.07.12.09 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:09 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=Va5hDNDD; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVO-0001xw-Ag; Tue, 28 May 2024 10:08:51 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iI-Ou for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:23 -0400 Received: from mail-wr1-x434.google.com ([2a00:1450:4864:20::434]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUx-00077c-Ve for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:21 -0400 Received: by mail-wr1-x434.google.com with SMTP id ffacd0b85a97d-35bf77ba8fbso244504f8f.2 for ; Tue, 28 May 2024 07:08:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905298; x=1717510098; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=8FAqlHwdIGYJ/Fo9nu8qvPKK59RKx8O/bWyYtfutAkU=; b=Va5hDNDDzlHR5eo3oq6WaQYjZuuaAB8NHylagGN3JVZy0xmV4pr+JP/nw2DkE/NTC8 wcqthsJqotGtf+PDaKrLy8nvEB75ftTKqZqhgAvNdxJ1h1z7BfZp8NDbvFmpKkR0lKn6 rBLnzxxJIs2LoJoPaEN0EcTD9Jo31JlUWm6KiDKW6W5/uxer+8X0Q27n+n9aJancimF2 WeJV+tutMaSSHr5uwC0sU/JzwOlOraQVl5k/rw24k3/r5caQbUhkjx1525uS7WoQU4R+ FXMVyhFKoeR+OiAucvMV4jlWb+lp7ITB7arccKVbq9TWegvHZlND8F6vwUhf1BJvdvJf Ty/w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905298; x=1717510098; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=8FAqlHwdIGYJ/Fo9nu8qvPKK59RKx8O/bWyYtfutAkU=; b=qiY4jHHVOuxAY9pk2xryPVyRkAwZPrpImF2pEJ4/09VKSPMM2Bu+zbMp2ROYwITQD4 r9ClstEUFa2ulP2IoSWldYvKbppq/3s9egIw+/Fn6fZfEhYQFJJXoN1tdCu2DCU+3arB me0vph+zJlVwTL2UxyB6TA2AJiIdIYYhZgV1+Ew8tj7p2SUkuwuMj9uaICXWbBZslPrV QQy54zYYVkXd9vzCHlmVcBrAMjHHF4IdpKNkibGGhE61RBklQatnPCcYbA47VhwoKXLg 7AmVACbFPKlyAf7PuizkIX1Ca7iMWoccw+m1sUCpT69+H5Z8mKrdj98l7X23WVI8crmc X6kg== X-Gm-Message-State: AOJu0YzeBIqSETynqGVw1KrJ5hgJ9bbku3BzXDo4pKbNneQw25yLQdvC utR4kEvjsHbjJN0L9/5B4DdlRgRC00SWqC4VT+5plkKhc8RUX4bKCEchLtwLQQVWHZv5fMtzosZ a X-Received: by 2002:a05:6000:8f:b0:354:f359:735a with SMTP id ffacd0b85a97d-3552705681fmr10441059f8f.5.1716905298668; Tue, 28 May 2024 07:08:18 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.18 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:18 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 38/42] target/arm: Use gvec for neon padd Date: Tue, 28 May 2024 15:07:49 +0100 Message-Id: <20240528140753.3620597-39-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::434; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x434.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 2 -- target/arm/tcg/neon_helper.c | 5 ----- target/arm/tcg/translate-neon.c | 3 +-- 3 files changed, 1 insertion(+), 9 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index d3579a101f4..51ed49aa50c 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -354,8 +354,6 @@ DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64) DEF_HELPER_2(neon_add_u8, i32, i32, i32) DEF_HELPER_2(neon_add_u16, i32, i32, i32) -DEF_HELPER_2(neon_padd_u8, i32, i32, i32) -DEF_HELPER_2(neon_padd_u16, i32, i32, i32) DEF_HELPER_2(neon_sub_u8, i32, i32, i32) DEF_HELPER_2(neon_sub_u16, i32, i32, i32) DEF_HELPER_2(neon_mul_u8, i32, i32, i32) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index bc6c4a54e9d..a0b51c88096 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -745,11 +745,6 @@ uint32_t HELPER(neon_add_u16)(uint32_t a, uint32_t b) return (a + b) ^ mask; } -#define NEON_FN(dest, src1, src2) dest = src1 + src2 -NEON_POP(padd_u8, neon_u8, 4) -NEON_POP(padd_u16, neon_u16, 2) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) dest = src1 - src2 NEON_VOP(sub_u8, neon_u8, 4) NEON_VOP(sub_u16, neon_u16, 2) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 2326a05a0aa..6c5a7a98e1b 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -830,6 +830,7 @@ DO_3SAME_NO_SZ_3(VABD_S, gen_gvec_sabd) DO_3SAME_NO_SZ_3(VABA_S, gen_gvec_saba) DO_3SAME_NO_SZ_3(VABD_U, gen_gvec_uabd) DO_3SAME_NO_SZ_3(VABA_U, gen_gvec_uaba) +DO_3SAME_NO_SZ_3(VPADD, gen_gvec_addp) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -1070,13 +1071,11 @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) #define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 #define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 #define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 -#define gen_helper_neon_padd_u32 tcg_gen_add_i32 DO_3SAME_PAIR(VPMAX_S, pmax_s) DO_3SAME_PAIR(VPMIN_S, pmin_s) DO_3SAME_PAIR(VPMAX_U, pmax_u) DO_3SAME_PAIR(VPMIN_U, pmin_u) -DO_3SAME_PAIR(VPADD, padd_u) #define DO_3SAME_VQDMULH(INSN, FUNC) \ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ From patchwork Tue May 28 14:07:50 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799488 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257592wrz; Tue, 28 May 2024 07:13:23 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWDJxDIrqWrBE8HXRGmFc5anNExlzMll8owOF3WWbgtxmZ7+hV/ERsfmWSeCAYj2uyfQewfwEDTPs2agMqHpGXo X-Google-Smtp-Source: AGHT+IEkhzXHTCMcEnflwjmYOK/CtMWuQ3lTdFQpEiLMcOq+GuebY1cKqJixLdJsg/VZiSraXl7n X-Received: by 2002:a67:fd48:0:b0:48a:375f:50aa with SMTP id ada2fe7eead31-48a38657311mr12651112137.24.1716905602882; Tue, 28 May 2024 07:13:22 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905602; cv=none; d=google.com; s=arc-20160816; b=pNw7/LAmBXYjE7zkzyJI85oJXMhAdqcBjk4zQtU8u/Ju9/viE0jIkZGV/mrPf+E4h9 98ScJeDgLRfDle+DzBX7Q3ls0+DBwH2zkFSagj1YhuJz9MIfU/SxD4TAvTBQujyLnEkA EmQh1C86MzD8YnznyEmvQsvmNCbKcdnygDCX4g97BLmmoguLOtQ05PtmKolqvaCE4A91 +HkBgXc083m3fHtNXvNr2B3EWBVWvuFt3J6GUhLW/+/4yJNoPRKTLzcNL2AERHbaitdn NYyfpPmgXaEiQMSMvFg57RHl5LEqhjd6IBIjRwpXiXuTqfB4cDxJcNIU3UbzJKrQPmqS kCqQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=WpKzEX9OYV2Wu/Wru2ElnNiOI7g6jxrjylg53v5eIas=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=RAa6KC5xoJK9+fp8a1o9dZLYLSiRdtFXIZRs7bZyxvkyzcASvM5GzRgNp86nsI+Vmk C2OwUTOVRE+5zoNvS7NbHKYClFJNeA7P7kLXXgtxgQqPA72IEXW+G/un0Cu+9MMoG0Ml FHP1DBpVMfMAhicPomcOOE2bQPsNeXmz7flFzdzAr1P/8bP6Ci5rLGfyeKQflLSlR058 xCvIUaenVLHHi7qnJ9vPHCKwOqw4KxnD/3JCkBsViCTrr2veQTLXqZwoC9VdItOyGbr5 /oGlqQzD7b/iBt/ygWULpD0P/YxclqD3G4mHW2bf2xFd5xknSmlLFt9XPLZrU30VcgIg oVcQ==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=LTy6xJDp; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a2f0edbsi1593721137.372.2024.05.28.07.13.22 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:22 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=LTy6xJDp; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV5-0001l9-9w; Tue, 28 May 2024 10:08:27 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV1-0001iL-QJ for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:23 -0400 Received: from mail-wm1-x334.google.com ([2a00:1450:4864:20::334]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUy-00077l-G6 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:22 -0400 Received: by mail-wm1-x334.google.com with SMTP id 5b1f17b1804b1-420180b59b7so6920935e9.0 for ; Tue, 28 May 2024 07:08:20 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905299; x=1717510099; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=WpKzEX9OYV2Wu/Wru2ElnNiOI7g6jxrjylg53v5eIas=; b=LTy6xJDpG17WlNu+TgcBoffMWO73CJImxwgobQ4i5LxfmcKW179et7f9tIYDEbysWM CV9sSDXb+khIgcfvlw4JLlOrojsr1ycFhYdgaZJl08m/Bonl2/iNpKbBHEuFQI2wJsU2 +ysiGedCFA6JpgoVnFp+6eFg2KnZGMYtt2nUCBWOngbA4z0NwdKmVbJq+47zh9uSz/nb BIkJ6xpimqr6NCo4tAhMpCNr2usXtChQo621gNN/TY+Hz7dMdLxczrcZiMcRFrdpE3/5 HvhGu36PMKpHh4c+62QKfV6Z1+W5F4NBtCzfPbn7o3w+lZHYJ9WUU+S3Gca7disaUzX+ MWnw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905299; x=1717510099; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=WpKzEX9OYV2Wu/Wru2ElnNiOI7g6jxrjylg53v5eIas=; b=GbSfLNKqkxsBcmnke9XJ4BNGvN8RyFgGQe6HtYbb9YnT1btC7ogJ4iq2/EG/sIIO7j hptp9vhL6Gw9QrF3GF25ywj9QVY9eh7GSD20YK0koLaFuYR+XqEVLb0tjfRTH5l/7kvR ZMiCSbZnCPyadny762ccCR3YxEwR8G07Y+Tga9fFiKxBYtnUCt6n1DLiSelJkTug4spG A5fatoVXKpehgytC41RMLxI6ffn7klbAYlmdQueTA3AMKXLqrBw1XMWat4YNlCZiODs3 9wxfnTiC0qHE1liXuQMTgDWYSXqg56hXiOc3stYC9ylZxMWmpwmcicg7clkoCed9QDSN BInA== X-Gm-Message-State: AOJu0Yzo7ZtKGkVkhhKzLAL7hjca2/U6pT157OdWsqpfIWY4mPqKgkex DKWV7BKGgrKDPHnOphxFg1xOIh3xjZjBpOs72mCnJyyEXBFJePOgWEFfI+36Vzd3WE8LS4qt/o2 l X-Received: by 2002:a05:600c:21d5:b0:41f:ed4b:93f9 with SMTP id 5b1f17b1804b1-421089de9f0mr97334165e9.19.1716905299155; Tue, 28 May 2024 07:08:19 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.18 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:18 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 39/42] target/arm: Convert SMAXP, SMINP, UMAXP, UMINP to decodetree Date: Tue, 28 May 2024 15:07:50 +0100 Message-Id: <20240528140753.3620597-40-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::334; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x334.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson These are the last instructions within handle_simd_3same_pair so remove it. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 16 +++++ target/arm/tcg/translate.h | 8 +++ target/arm/tcg/a64.decode | 4 ++ target/arm/tcg/gengvec.c | 48 +++++++++++++ target/arm/tcg/translate-a64.c | 119 +++++---------------------------- target/arm/tcg/vec_helper.c | 16 +++++ 6 files changed, 109 insertions(+), 102 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 51ed49aa50c..f830531dd3d 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -1064,6 +1064,22 @@ DEF_HELPER_FLAGS_4(gvec_addp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_addp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_addp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smaxp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smaxp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smaxp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_sminp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_umaxp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umaxp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umaxp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_uminp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "tcg/helper-a64.h" #include "tcg/helper-sve.h" diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 04771f483b6..3abdbedfe5c 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -516,6 +516,14 @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_addp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_smaxp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_umaxp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 84f5bcc0e08..22dfe8568d6 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -837,6 +837,10 @@ FMINNMP_v 0.10 1110 110 ..... 00000 1 ..... ..... @qrrr_h FMINNMP_v 0.10 1110 1.1 ..... 11000 1 ..... ..... @qrrr_sd ADDP_v 0.00 1110 ..1 ..... 10111 1 ..... ..... @qrrr_e +SMAXP_v 0.00 1110 ..1 ..... 10100 1 ..... ..... @qrrr_e +SMINP_v 0.00 1110 ..1 ..... 10101 1 ..... ..... @qrrr_e +UMAXP_v 0.10 1110 ..1 ..... 10100 1 ..... ..... @qrrr_e +UMINP_v 0.10 1110 ..1 ..... 10101 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index f010dd5a0e8..22c9d17dce4 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -1622,3 +1622,51 @@ void gen_gvec_addp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, }; tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); } + +void gen_gvec_smaxp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_smaxp_b, + gen_helper_gvec_smaxp_h, + gen_helper_gvec_smaxp_s, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +void gen_gvec_sminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_sminp_b, + gen_helper_gvec_sminp_h, + gen_helper_gvec_sminp_s, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +void gen_gvec_umaxp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_umaxp_b, + gen_helper_gvec_umaxp_h, + gen_helper_gvec_umaxp_s, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +void gen_gvec_uminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_uminp_b, + gen_helper_gvec_uminp_h, + gen_helper_gvec_uminp_s, + }; + tcg_debug_assert(vece <= MO_32); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index b8add91112d..9fe70a939bc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1352,6 +1352,17 @@ static bool do_gvec_fn3(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) return true; } +static bool do_gvec_fn3_no64(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn) +{ + if (a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_fn3(s, a->q, a->rd, a->rn, a->rm, fn, a->esz); + } + return true; +} + static bool do_gvec_fn4(DisasContext *s, arg_qrrrr_e *a, GVecGen4Fn *fn) { if (!a->q && a->esz == MO_64) { @@ -5246,6 +5257,10 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = { TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp) TRANS(ADDP_v, do_gvec_fn3, a, gen_gvec_addp) +TRANS(SMAXP_v, do_gvec_fn3_no64, a, gen_gvec_smaxp) +TRANS(SMINP_v, do_gvec_fn3_no64, a, gen_gvec_sminp) +TRANS(UMAXP_v, do_gvec_fn3_no64, a, gen_gvec_umaxp) +TRANS(UMINP_v, do_gvec_fn3_no64, a, gen_gvec_uminp) /* * Advanced SIMD scalar/vector x indexed element @@ -10896,84 +10911,6 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) } } -/* Pairwise op subgroup of C3.6.16. - * - * This is called directly for float pairwise - * operations where the opcode and size are calculated differently. - */ -static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, - int size, int rn, int rm, int rd) -{ - int pass; - - if (!fp_access_check(s)) { - return; - } - - /* These operations work on the concatenated rm:rn, with each pair of - * adjacent elements being operated on to produce an element in the result. - */ - if (size == 3) { - g_assert_not_reached(); - } else { - int maxpass = is_q ? 4 : 2; - TCGv_i32 tcg_res[4]; - - for (pass = 0; pass < maxpass; pass++) { - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - NeonGenTwoOpFn *genfn = NULL; - int passreg = pass < (maxpass / 2) ? rn : rm; - int passelt = (is_q && (pass & 1)) ? 2 : 0; - - read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_32); - read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_32); - tcg_res[pass] = tcg_temp_new_i32(); - - switch (opcode) { - case 0x14: /* SMAXP, UMAXP */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_pmax_s8, gen_helper_neon_pmax_u8 }, - { gen_helper_neon_pmax_s16, gen_helper_neon_pmax_u16 }, - { tcg_gen_smax_i32, tcg_gen_umax_i32 }, - }; - genfn = fns[size][u]; - break; - } - case 0x15: /* SMINP, UMINP */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_pmin_s8, gen_helper_neon_pmin_u8 }, - { gen_helper_neon_pmin_s16, gen_helper_neon_pmin_u16 }, - { tcg_gen_smin_i32, tcg_gen_umin_i32 }, - }; - genfn = fns[size][u]; - break; - } - default: - case 0x17: /* ADDP */ - case 0x58: /* FMAXNMP */ - case 0x5a: /* FADDP */ - case 0x5e: /* FMAXP */ - case 0x78: /* FMINNMP */ - case 0x7e: /* FMINP */ - g_assert_not_reached(); - } - - /* FP ops called directly, otherwise call now */ - if (genfn) { - genfn(tcg_res[pass], tcg_op1, tcg_op2); - } - } - - for (pass = 0; pass < maxpass; pass++) { - write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32); - } - clear_vec_high(s, is_q, rd); - } -} - /* Floating point op subgroup of C3.6.16. */ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) { @@ -11314,30 +11251,6 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) case 0x3: /* logic ops */ disas_simd_3same_logic(s, insn); break; - case 0x14: /* SMAXP, UMAXP */ - case 0x15: /* SMINP, UMINP */ - { - /* Pairwise operations */ - int is_q = extract32(insn, 30, 1); - int u = extract32(insn, 29, 1); - int size = extract32(insn, 22, 2); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - if (opcode == 0x17) { - if (u || (size == 3 && !is_q)) { - unallocated_encoding(s); - return; - } - } else { - if (size == 3) { - unallocated_encoding(s); - return; - } - } - handle_simd_3same_pair(s, is_q, u, opcode, size, rn, rm, rd); - break; - } case 0x18 ... 0x31: /* floating point ops, sz[1] and U are part of opcode */ disas_simd_3same_float(s, insn); @@ -11345,6 +11258,8 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) default: disas_simd_3same_int(s, insn); break; + case 0x14: /* SMAXP, UMAXP */ + case 0x15: /* SMINP, UMINP */ case 0x17: /* ADDP */ unallocated_encoding(s); break; diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 5069899415c..56fea14edb9 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2259,6 +2259,22 @@ DO_3OP_PAIR(gvec_addp_s, ADD, uint32_t, H4) DO_3OP_PAIR(gvec_addp_d, ADD, uint64_t, ) #undef ADD +DO_3OP_PAIR(gvec_smaxp_b, MAX, int8_t, H1) +DO_3OP_PAIR(gvec_smaxp_h, MAX, int16_t, H2) +DO_3OP_PAIR(gvec_smaxp_s, MAX, int32_t, H4) + +DO_3OP_PAIR(gvec_umaxp_b, MAX, uint8_t, H1) +DO_3OP_PAIR(gvec_umaxp_h, MAX, uint16_t, H2) +DO_3OP_PAIR(gvec_umaxp_s, MAX, uint32_t, H4) + +DO_3OP_PAIR(gvec_sminp_b, MIN, int8_t, H1) +DO_3OP_PAIR(gvec_sminp_h, MIN, int16_t, H2) +DO_3OP_PAIR(gvec_sminp_s, MIN, int32_t, H4) + +DO_3OP_PAIR(gvec_uminp_b, MIN, uint8_t, H1) +DO_3OP_PAIR(gvec_uminp_h, MIN, uint16_t, H2) +DO_3OP_PAIR(gvec_uminp_s, MIN, uint32_t, H4) + #undef DO_3OP_PAIR #define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ From patchwork Tue May 28 14:07:51 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799456 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp255330wrz; Tue, 28 May 2024 07:09:50 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX5gRTLXy47gMp2sQ1gjS4g4F0b0Y47qjlo6hGjsV26KLMuseo7ml58JOuTcFUK/yUUw2MSi0wHFGHpm1DTkOuB X-Google-Smtp-Source: AGHT+IHXL+bKDKoGNCygDWvK2t603cdutXPUXuJpIsUuxLCX5uKlSk9SCyAH1iHw2a0BC80OD+iQ X-Received: by 2002:a05:6214:319e:b0:6ab:8eda:1055 with SMTP id 6a1803df08f44-6abcdaa328emr114258666d6.59.1716905389916; Tue, 28 May 2024 07:09:49 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905389; cv=none; d=google.com; s=arc-20160816; b=DnLJr1jTPTEoY3w5ANZgzxPlLjtsepMPsvY8eBkpBctlM4p4kd5LS/qGJSpdxKdSZY 3SHSrpIqbCBDF8GmWiKns1PjIq+A/s/eyhOJQgEGwsqwXhIh+YAxpjbs2wF4xxlcm/4O gXAYJP7xaIfPnjXNef3DdqrKj3DIpEs09ECEp6sVlG3hv4M+NKuJjKAIeA0ngWFEdJL+ qszukSA3esDxANAYTn4OY8zpwMxWJ4T0bS61Y4VyrOJOzBZilF8u9u2uaN6y2gluKVUU FAfso+bTWcTzevi/Dz06drBK6nRKxOG2bCGPAY+laz2FEEsQiNR+NMS6PXwIOWPn8a0L /r8A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=eUpqWL0RMr00yluMUjIv8p2E8ThsTmcfnEs2p/FMlME=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=M5E7bSsUk9BzykFK+dBqPcbsRvX/zLF9VG2wlO6mN2peufuCovWnQKPjPpzAxnCxZW kpoqyO2dRLyQjxyBF1SOQaloBv54AeFWfpKDa8gzbEcfhw+Na6Vjsb6FWfTMNlftpNWf 01skFk4eEx/yBzlWxSWyE9gbyFXt7lIpuDZPXvy2cNmAhIFjl3+QHSrPFiZA0W7oEFFF LVBiUd63HR0zVQntmcqSUqSKyJ77A1PfokH8oF1y3qc0Fy/vYlETuQkrFiCMejAmZK8D Njv7xcG3mFBi8whjwqRfmsjL8eWnUY2Y6OGac+QpwSRq+pk1taWLgqoSCnNXtk+jzc2X 50Tg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=JP63YODx; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 6a1803df08f44-6ad740cd21asi69712476d6.477.2024.05.28.07.09.49 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:09:49 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=JP63YODx; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVJ-0001qa-GH; Tue, 28 May 2024 10:08:43 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV3-0001jn-78 for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:25 -0400 Received: from mail-wr1-x433.google.com ([2a00:1450:4864:20::433]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxUz-00077s-4e for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:24 -0400 Received: by mail-wr1-x433.google.com with SMTP id ffacd0b85a97d-354faf5f1b4so667177f8f.1 for ; Tue, 28 May 2024 07:08:20 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905299; x=1717510099; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=eUpqWL0RMr00yluMUjIv8p2E8ThsTmcfnEs2p/FMlME=; b=JP63YODxM8Aj1Vu1jqUhVe+jhQemESSYdb4OoU6Kwrd6tsN+XuvBMTYz+PtwaTeXUN 3DwFEvRvMv7J2s5xid1ADIkilUcWqm9/mNik3uH7rvYlEDQcptePYP4Mqd68ymS6slVj kv9JiZdq2fUCAT6QtiHC4OqE7IkESkqf4uIMxnZx9pvJ0opjTNmxtcqX499oRckHyE7z cPys387hDKsbJ86l9iAOCZtQ1PIHMQk8ABXsy8jAEmP/EIz1KnM+UgSW16DoMWIGh7HH q5gW648c15As5hcS/kSnJ9uN6/8yuiHRFbJ7Mi/QVIWeJP0KJwQGqB0+WZiwwQlPfyYb VYGw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905299; x=1717510099; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=eUpqWL0RMr00yluMUjIv8p2E8ThsTmcfnEs2p/FMlME=; b=r/ZT+8Tm9cd+keGTho7gUjDM0IQj930NS983yF9rj394GMVdNqNRI6eflVczYp3w9N oHYXYixVB0AaZZOlVFrhHbks6I2NwyldB8stXiAUxZM9TRwJUnXSg4dUXSjinybcogfb UyJVVyxVnK3P/LK2rMi1fZSd1gPPc8pDpgTy+b3AODQayazkzxQXjXOkyYxjkO7zK6Gw jec4xpfjv/A62SklHbpWjaz+crqlxNffuczxE5O/NZEUwArWsN3W0V7aVXBSEcHcsQOG 0qr8PHBcrEarAscSBvoey3LF5Pj6gLZkAZ3IEjAwJB3OYEX6ktGq5Z0UkAbjhKtMobDD 8nfg== X-Gm-Message-State: AOJu0Ywsqkfi/1DASY3i55wZso8ruvSNHCJgEVd0ufnGaPqIqP6gSVRm BBgM26GgO61F0YufEOpHtmR9lK5Fg3V7Cpv5PX2PmKUf29AoV5ZyA0e7rFGAOGOCTALSVQIWwqY P X-Received: by 2002:adf:f24b:0:b0:34e:93c1:7979 with SMTP id ffacd0b85a97d-3552fdaa2fcmr11715091f8f.38.1716905299632; Tue, 28 May 2024 07:08:19 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.19 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:19 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 40/42] target/arm: Use gvec for neon pmax, pmin Date: Tue, 28 May 2024 15:07:51 +0100 Message-Id: <20240528140753.3620597-41-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::433; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x433.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-neon.c | 78 ++------------------------------- 1 file changed, 4 insertions(+), 74 deletions(-) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 6c5a7a98e1b..18b048611b3 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -831,6 +831,10 @@ DO_3SAME_NO_SZ_3(VABA_S, gen_gvec_saba) DO_3SAME_NO_SZ_3(VABD_U, gen_gvec_uabd) DO_3SAME_NO_SZ_3(VABA_U, gen_gvec_uaba) DO_3SAME_NO_SZ_3(VPADD, gen_gvec_addp) +DO_3SAME_NO_SZ_3(VPMAX_S, gen_gvec_smaxp) +DO_3SAME_NO_SZ_3(VPMIN_S, gen_gvec_sminp) +DO_3SAME_NO_SZ_3(VPMAX_U, gen_gvec_umaxp) +DO_3SAME_NO_SZ_3(VPMIN_U, gen_gvec_uminp) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -1003,80 +1007,6 @@ DO_3SAME_32_ENV(VQSHL_U, qshl_u) DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) -static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) -{ - /* Operations handled pairwise 32 bits at a time */ - TCGv_i32 tmp, tmp2, tmp3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if (a->size == 3) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - assert(a->q == 0); /* enforced by decode patterns */ - - /* - * Note that we have to be careful not to clobber the source operands - * in the "vm == vd" case by storing the result of the first pass too - * early. Since Q is 0 there are always just two passes, so instead - * of a complicated loop over each pass we just unroll. - */ - tmp = tcg_temp_new_i32(); - tmp2 = tcg_temp_new_i32(); - tmp3 = tcg_temp_new_i32(); - - read_neon_element32(tmp, a->vn, 0, MO_32); - read_neon_element32(tmp2, a->vn, 1, MO_32); - fn(tmp, tmp, tmp2); - - read_neon_element32(tmp3, a->vm, 0, MO_32); - read_neon_element32(tmp2, a->vm, 1, MO_32); - fn(tmp3, tmp3, tmp2); - - write_neon_element32(tmp, a->vd, 0, MO_32); - write_neon_element32(tmp3, a->vd, 1, MO_32); - - return true; -} - -#define DO_3SAME_PAIR(INSN, func) \ - static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - static NeonGenTwoOpFn * const fns[] = { \ - gen_helper_neon_##func##8, \ - gen_helper_neon_##func##16, \ - gen_helper_neon_##func##32, \ - }; \ - if (a->size > 2) { \ - return false; \ - } \ - return do_3same_pair(s, a, fns[a->size]); \ - } - -/* 32-bit pairwise ops end up the same as the elementwise versions. */ -#define gen_helper_neon_pmax_s32 tcg_gen_smax_i32 -#define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 -#define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 -#define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 - -DO_3SAME_PAIR(VPMAX_S, pmax_s) -DO_3SAME_PAIR(VPMIN_S, pmin_s) -DO_3SAME_PAIR(VPMAX_U, pmax_u) -DO_3SAME_PAIR(VPMIN_U, pmin_u) - #define DO_3SAME_VQDMULH(INSN, FUNC) \ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ From patchwork Tue May 28 14:07:52 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799489 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257742wrz; Tue, 28 May 2024 07:13:38 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXzKcLrDPqyyRdlY6/sL/m2r05DG4JIwbfC5YPGkQvcp2g45UZHWKR7ckww/qrjnaP0Ozr59dCpkk5lkiZhnFsZ X-Google-Smtp-Source: AGHT+IG1pR/grXMb8VGbqpxzL2JXaRWhXC7s09eoTXHVW3Sra8rQ/9m3VUIt00ufVDNrSGhcUMUF X-Received: by 2002:aca:1801:0:b0:3c9:9636:eb48 with SMTP id 5614622812f47-3d1a5c3382amr10827129b6e.17.1716905617654; Tue, 28 May 2024 07:13:37 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905617; cv=none; d=google.com; s=arc-20160816; b=g9qJu5SIxoheBHvoKTF5Khs+sqcpyUyWOBiFm7eX83ftBINmmMd+N0T6LaqeJg+O5f RbOEQrDZIYPleMtk4biewJAo02UPkf4Fbe1LQv7AYJK4ZR4F9E5lb+TclnD3CM4Vxx4t fSvpMrXKA1zJyoN2VbMx6m4cmxXgeBYxr8B1A1yOW9QRM9r6KDWShtxMk/f0tROepNrU tLXVFUnBwNQlIsEBPZd/8461J6iDf/XuQk1Y97aLeRoSTXLbi+G9Rcqu22fg/apszzEd nMr2ungDgUZiXC2JmdXhHZEtPhmJ6ZuBaz91PnRdqO4E5RidGnPJWlwv6VGe3FV2D7SR 8uqQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=4A96dtC09XwXUZPYUp+sD5hXPzHCsb+Is4d1sTgtWoY=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=s3Wl80dgIbuhJBEESnpzoOGFQj/pE/TCBJIkWcWlowwzpUWyg4jDgixmccQfmWiFnp Pl6BrZOVG8CpmuSdS8GDUMYLPMts0h46b8NG5NvMPeSor7eK+ffWjGf4l+p9emfHWhc+ KDNme0epb9oTDExdR4MlM/55LOqzVxKw+TJUbhMPuWlwGXdvmuicbFzV6hFK4quXlwNA 3m80sAKbHj74X38lke5LzXygPLUvDnf0tETQ6nHBb/hqS0vC+0O4+auZheE10ir4sTcn Ch9KqutiNncjCPThbUywHl/1qIv20NOqrR0xn6sDqNgeVWFa9g8YtNRHDNLWAOx8KSQf T4qA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=i8KwYAvD; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id 71dfb90a1353d-4e4f072b0f6si1889417e0c.64.2024.05.28.07.13.37 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:13:37 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=i8KwYAvD; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxV7-0001lv-6m; Tue, 28 May 2024 10:08:29 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV4-0001kg-2x for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:26 -0400 Received: from mail-wm1-x32d.google.com ([2a00:1450:4864:20::32d]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxV1-00078B-Dv for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:25 -0400 Received: by mail-wm1-x32d.google.com with SMTP id 5b1f17b1804b1-421124a04d6so6820745e9.3 for ; Tue, 28 May 2024 07:08:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905300; x=1717510100; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=4A96dtC09XwXUZPYUp+sD5hXPzHCsb+Is4d1sTgtWoY=; b=i8KwYAvDHCx+siyqowlXbvPmP68khkL2ty8JdBuxUGSC8CeZ1x+EN1WomgnUoLkW8m 9OB968dMkrgYYmwdedp0hIRUMNmT/FCzw6PZUY8rvxbhdZU3JDTl2KPdU2Y6iN7sps0F ZMNC7uGwip958ESdob0VhB5y0K8hWcT/Kfqx1tR2kCIUYKC2Gad9wFzPe6yqTgq5waHA 7K5Xp9DuLr0ji9MxTDiuZJRuMikYrRJFvuLV14iGH79Qx0Rg6Ld/Llmn5dXINyAVQc9y IySGfPvJOkHzgEBLqqNB0iG+sfm1ONJRdDY2VoYKt2t7eALyoh9BQQeg//D2dNOTQm+g kDww== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905300; x=1717510100; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=4A96dtC09XwXUZPYUp+sD5hXPzHCsb+Is4d1sTgtWoY=; b=KXB91soJsukthmPnH9pwrFHMefo4OPRG4muYc1QLiSUHHghljsVAKw0OgyjdChLR5A VJh6sSjY5Zq8q9I5qKZx1CeBPd9WtPf4mw+gCU760Dj0u+XVe+ObnKthHgSalLt+1lu8 9XwWADzJCu2WjcpPrLo7tm1P5mjskLW4qHWSPaasszoqY2HcSM0K1rLFkSVhLibecuQL hmPHJkatBOYlEUHSiwsRmWyeWjLYoWcORz7iphkXylm7QVDfRNji72ZUYEgMnJtRTnt0 xqU1x8ujpnFVPQNRjbLiydsXGw8F1g0u5yd2ugmCX2WXJMhOrr5mVNcRW+q99mhu+TlB M0hw== X-Gm-Message-State: AOJu0YyM+0CJbAWg8debWAwcqE0yPRE0BKBqtq6rKuikpcfYAxDLz03T jJVc+lllpEEp8gShNxGCwPxnYqzZweLRc0p7p0+hUPyD1iubo0oo9v/u5dlL8xuDhvEZFri3Cbt 2 X-Received: by 2002:a05:600c:21d5:b0:41f:ed4b:93f9 with SMTP id 5b1f17b1804b1-421089de9f0mr97334635e9.19.1716905300101; Tue, 28 May 2024 07:08:20 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.19 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:19 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 41/42] target/arm: Convert FMLAL, FMLSL to decodetree Date: Tue, 28 May 2024 15:07:52 +0100 Message-Id: <20240528140753.3620597-42-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::32d; envelope-from=peter.maydell@linaro.org; helo=mail-wm1-x32d.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 10 +++ target/arm/tcg/translate-a64.c | 144 ++++++++++----------------------- 2 files changed, 51 insertions(+), 103 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 22dfe8568d6..7e993ed345f 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -797,6 +797,11 @@ FMLA_v 0.00 1110 0.1 ..... 11001 1 ..... ..... @qrrr_sd FMLS_v 0.00 1110 110 ..... 00001 1 ..... ..... @qrrr_h FMLS_v 0.00 1110 1.1 ..... 11001 1 ..... ..... @qrrr_sd +FMLAL_v 0.00 1110 001 ..... 11101 1 ..... ..... @qrrr_h +FMLSL_v 0.00 1110 101 ..... 11101 1 ..... ..... @qrrr_h +FMLAL2_v 0.10 1110 001 ..... 11001 1 ..... ..... @qrrr_h +FMLSL2_v 0.10 1110 101 ..... 11001 1 ..... ..... @qrrr_h + FCMEQ_v 0.00 1110 010 ..... 00100 1 ..... ..... @qrrr_h FCMEQ_v 0.00 1110 0.1 ..... 11100 1 ..... ..... @qrrr_sd @@ -877,3 +882,8 @@ FMLS_vi 0.00 1111 11 0 ..... 0101 . 0 ..... ..... @qrrx_d FMULX_vi 0.10 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h FMULX_vi 0.10 1111 10 . ..... 1001 . 0 ..... ..... @qrrx_s FMULX_vi 0.10 1111 11 0 ..... 1001 . 0 ..... ..... @qrrx_d + +FMLAL_vi 0.00 1111 10 .. .... 0000 . 0 ..... ..... @qrrx_h +FMLSL_vi 0.00 1111 10 .. .... 0100 . 0 ..... ..... @qrrx_h +FMLAL2_vi 0.10 1111 10 .. .... 1000 . 0 ..... ..... @qrrx_h +FMLSL2_vi 0.10 1111 10 .. .... 1100 . 0 ..... ..... @qrrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 9fe70a939bc..a4ff1fd2027 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5256,6 +5256,24 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = { }; TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp) +static bool do_fmlal(DisasContext *s, arg_qrrr_e *a, bool is_s, bool is_2) +{ + if (fp_access_check(s)) { + int data = (is_2 << 1) | is_s; + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), tcg_env, + a->q ? 16 : 8, vec_full_reg_size(s), + data, gen_helper_gvec_fmlal_a64); + } + return true; +} + +TRANS_FEAT(FMLAL_v, aa64_fhm, do_fmlal, a, false, false) +TRANS_FEAT(FMLSL_v, aa64_fhm, do_fmlal, a, true, false) +TRANS_FEAT(FMLAL2_v, aa64_fhm, do_fmlal, a, false, true) +TRANS_FEAT(FMLSL2_v, aa64_fhm, do_fmlal, a, true, true) + TRANS(ADDP_v, do_gvec_fn3, a, gen_gvec_addp) TRANS(SMAXP_v, do_gvec_fn3_no64, a, gen_gvec_smaxp) TRANS(SMINP_v, do_gvec_fn3_no64, a, gen_gvec_sminp) @@ -5447,6 +5465,24 @@ static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg) TRANS(FMLA_vi, do_fmla_vector_idx, a, false) TRANS(FMLS_vi, do_fmla_vector_idx, a, true) +static bool do_fmlal_idx(DisasContext *s, arg_qrrx_e *a, bool is_s, bool is_2) +{ + if (fp_access_check(s)) { + int data = (a->idx << 2) | (is_2 << 1) | is_s; + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), tcg_env, + a->q ? 16 : 8, vec_full_reg_size(s), + data, gen_helper_gvec_fmlal_idx_a64); + } + return true; +} + +TRANS_FEAT(FMLAL_vi, aa64_fhm, do_fmlal_idx, a, false, false) +TRANS_FEAT(FMLSL_vi, aa64_fhm, do_fmlal_idx, a, true, false) +TRANS_FEAT(FMLAL2_vi, aa64_fhm, do_fmlal_idx, a, false, true) +TRANS_FEAT(FMLSL2_vi, aa64_fhm, do_fmlal_idx, a, true, true) + /* * Advanced SIMD scalar pairwise */ @@ -10911,78 +10947,6 @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) } } -/* Floating point op subgroup of C3.6.16. */ -static void disas_simd_3same_float(DisasContext *s, uint32_t insn) -{ - /* For floating point ops, the U, size[1] and opcode bits - * together indicate the operation. size[0] indicates single - * or double. - */ - int fpopcode = extract32(insn, 11, 5) - | (extract32(insn, 23, 1) << 5) - | (extract32(insn, 29, 1) << 6); - int is_q = extract32(insn, 30, 1); - int size = extract32(insn, 22, 1); - int rm = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - if (size == 1 && !is_q) { - unallocated_encoding(s); - return; - } - - switch (fpopcode) { - case 0x1d: /* FMLAL */ - case 0x3d: /* FMLSL */ - case 0x59: /* FMLAL2 */ - case 0x79: /* FMLSL2 */ - if (size & 1 || !dc_isar_feature(aa64_fhm, s)) { - unallocated_encoding(s); - return; - } - if (fp_access_check(s)) { - int is_s = extract32(insn, 23, 1); - int is_2 = extract32(insn, 29, 1); - int data = (is_2 << 1) | is_s; - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), tcg_env, - is_q ? 16 : 8, vec_full_reg_size(s), - data, gen_helper_gvec_fmlal_a64); - } - return; - - default: - case 0x18: /* FMAXNM */ - case 0x19: /* FMLA */ - case 0x1a: /* FADD */ - case 0x1b: /* FMULX */ - case 0x1c: /* FCMEQ */ - case 0x1e: /* FMAX */ - case 0x1f: /* FRECPS */ - case 0x38: /* FMINNM */ - case 0x39: /* FMLS */ - case 0x3a: /* FSUB */ - case 0x3e: /* FMIN */ - case 0x3f: /* FRSQRTS */ - case 0x58: /* FMAXNMP */ - case 0x5a: /* FADDP */ - case 0x5b: /* FMUL */ - case 0x5c: /* FCMGE */ - case 0x5d: /* FACGE */ - case 0x5e: /* FMAXP */ - case 0x5f: /* FDIV */ - case 0x78: /* FMINNMP */ - case 0x7a: /* FABD */ - case 0x7d: /* FACGT */ - case 0x7c: /* FCMGT */ - case 0x7e: /* FMINP */ - unallocated_encoding(s); - return; - } -} - /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { @@ -11251,16 +11215,13 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) case 0x3: /* logic ops */ disas_simd_3same_logic(s, insn); break; - case 0x18 ... 0x31: - /* floating point ops, sz[1] and U are part of opcode */ - disas_simd_3same_float(s, insn); - break; default: disas_simd_3same_int(s, insn); break; case 0x14: /* SMAXP, UMAXP */ case 0x15: /* SMINP, UMINP */ case 0x17: /* ADDP */ + case 0x18 ... 0x31: /* floating point ops */ unallocated_encoding(s); break; } @@ -12526,22 +12487,15 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } is_fp = 2; break; - case 0x00: /* FMLAL */ - case 0x04: /* FMLSL */ - case 0x18: /* FMLAL2 */ - case 0x1c: /* FMLSL2 */ - if (is_scalar || size != MO_32 || !dc_isar_feature(aa64_fhm, s)) { - unallocated_encoding(s); - return; - } - size = MO_16; - /* is_fp, but we pass tcg_env not fp_status. */ - break; default: + case 0x00: /* FMLAL */ case 0x01: /* FMLA */ + case 0x04: /* FMLSL */ case 0x05: /* FMLS */ case 0x09: /* FMUL */ + case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ + case 0x1c: /* FMLSL2 */ unallocated_encoding(s); return; } @@ -12660,22 +12614,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } return; - case 0x00: /* FMLAL */ - case 0x04: /* FMLSL */ - case 0x18: /* FMLAL2 */ - case 0x1c: /* FMLSL2 */ - { - int is_s = extract32(opcode, 2, 1); - int is_2 = u; - int data = (index << 2) | (is_2 << 1) | is_s; - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), tcg_env, - is_q ? 16 : 8, vec_full_reg_size(s), - data, gen_helper_gvec_fmlal_idx_a64); - } - return; - case 0x08: /* MUL */ if (!is_long && !is_scalar) { static gen_helper_gvec_3 * const fns[3] = { From patchwork Tue May 28 14:07:53 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 799475 Delivered-To: patch@linaro.org Received: by 2002:adf:e110:0:b0:35b:5a80:51b4 with SMTP id t16csp257044wrz; Tue, 28 May 2024 07:12:28 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWUi8r4sAgkc7r4qUJgf0jH3YJEooXdNtgfx/CfuGnExTiQEQJDn9SBOx6OjBBGjRssphoQJF0UfKipDyQq4ZLK X-Google-Smtp-Source: AGHT+IEg/q5e2fWi+otM9wSftEKpeDHuFHmn6tQElUZVsdd91uWoKf/dbF8mjwX/eSRtzJP7KiYp X-Received: by 2002:a05:6102:4a04:b0:481:12f:d5ea with SMTP id ada2fe7eead31-48a2bb19515mr12968978137.3.1716905548143; Tue, 28 May 2024 07:12:28 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1716905548; cv=none; d=google.com; s=arc-20160816; b=lYxczPzS8F9ACNp0Msxz+JsOVWrVaRcsy5lkRhpLkib7Je3hm1EFoIsTSEMdg4Vqvi wssSipjlW50zZ2Pj4zK0LYa2TWjUEMOSrUfnKh/Ofq1LG6Uvmg6PsYnVseMNuxhQ0bgA N8ERoj25uoP3USDbo7n+wWZ43hvQgoXgsmvbZxmZEA7vS4jyW9Sw4gjVvOy2maLaq0dZ d6/IDvsJ2OanrJdFRoc5CY2rvalQMNv8G9Hs65LpnOjuIbEp74mV8I5H77dNbH7XNiKv DY6zytihuMYeRy97LuVnZOhHuZzyiOYZ1ZCTCus7lWr7mAEWtT2E/HEF/dFPsXln5Bwh n98A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=EKAQ32eea70hSREqLliF7NT4Dpg+g7C389U018iSzIk=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=z2sGaqJ/lGWlOkaTvGPpV1P9ryELPvsvLjZZ779PPGyY6jxJeUGQNM1XCVcScqD6WL ww2MtlwoOgOxrbVg35Xev+HTGR5IKht6t/w1zCLHk6uWKqN9vavg3L2gFxehiqoreQvd 3rMsZKLtxOea4hjJvRF36va1ZGQ4/Oeiw7l9Wp1qJvcuSh/nS9cH9XpFZhOUb9d6h8ir 2Tiep1L2649vaNABoGHH9RY9K9yp93/WVGU0g2aT3AcSi0t1NKrBbJ+veOV/xzqueP5T 7lCurM1p3Ac6fhq3XlEaQV+2BJ7L+kho9g77qmVdwhi0n4ey5Z7a5NzMPG89HRtF1XKl nHPA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=deIWRq1m; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id ada2fe7eead31-48a3a40754esi2069566137.727.2024.05.28.07.12.27 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Tue, 28 May 2024 07:12:28 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=deIWRq1m; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1sBxVO-0001xp-7Q; Tue, 28 May 2024 10:08:46 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1sBxV3-0001kF-FM for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:25 -0400 Received: from mail-wr1-x433.google.com ([2a00:1450:4864:20::433]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1sBxV1-00078K-En for qemu-devel@nongnu.org; Tue, 28 May 2024 10:08:25 -0400 Received: by mail-wr1-x433.google.com with SMTP id ffacd0b85a97d-357ec504fcdso579421f8f.3 for ; Tue, 28 May 2024 07:08:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1716905300; x=1717510100; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=EKAQ32eea70hSREqLliF7NT4Dpg+g7C389U018iSzIk=; b=deIWRq1mRrNoYQlMVOOU6pzFv5Wj3BAaUGNQENa/5j9rlVP8UFzAnfy0OaWiG/utmG KmIqVI4R4l2l0Y7DKZm2ReSBS7GZHXtPayDhHdf41doqUhU83HJU3l54za4NaBV1Fv91 V0H+vDA3aIcQ2ElDlinHi49SIeO9+LQ9FptTyNIKpNrTpO4Oxk8T0Tl/V7N3SEE4TvEp r04rtfqLdRLgZzhktmzqds4CLbr2pqvoxksfspdW8cELclj2Vm0Y5Ih/AQKVL0HGQxGY BYtzr9kP8Pyxh/Vp3thXaeCk/du6xd4sQSS7zvVZbskRXuTFU/E57ikZ9iGLSHU/0u8+ J3Ug== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1716905300; x=1717510100; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=EKAQ32eea70hSREqLliF7NT4Dpg+g7C389U018iSzIk=; b=KJl9N1RMS85OJlLyb4vrUVOr/D/Ljavks2CAlsMHrF+suej3LL0k8MQB1zYO5uyZ8T JKeVcUWEQ+FvaihtclR7+7/+zCIsMevYeW0/HgBl+x3C2J7XRZ85Rr67H0Y6KgPxtovd jdIBSFmANaZbyc0dWX426x3e3L7AKQFdnLofbVQJdk1R7cRTNIDFnhWBwLxDhlZG1MD8 7eVnSyjpIHqr37kQJd84YGHRYQy9Z5EWUPjKaT2luJtn071s4OEWOwZWu500sLESEH2A I0i6KjoUM+PcHUlESJ3WZKz651LxRq9hzgnqL4fNjutf95IBtzoO2fzGtm5uMzPh5LA/ +AlA== X-Gm-Message-State: AOJu0Yy6hgqOAzRuMTw7ulmf+ad9b9Q+n2pbkCdSLRKzusgetkgXi8NH 3i4V+HBmuGAxoo5kzKclfenuujDA90grMYyoCHaq2lr6pi4rPuTuTUeJwuXtkrSXz3oA0VSOq2B 5 X-Received: by 2002:adf:f890:0:b0:351:c2c1:3682 with SMTP id ffacd0b85a97d-3552fdfd685mr7692898f8f.62.1716905300537; Tue, 28 May 2024 07:08:20 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-3564afc3577sm11361473f8f.102.2024.05.28.07.08.20 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 28 May 2024 07:08:20 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 42/42] target/arm: Convert disas_simd_3same_logic to decodetree Date: Tue, 28 May 2024 15:07:53 +0100 Message-Id: <20240528140753.3620597-43-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240528140753.3620597-1-peter.maydell@linaro.org> References: <20240528140753.3620597-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::433; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x433.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org From: Richard Henderson This includes AND, ORR, EOR, BIC, ORN, BSF, BIT, BIF. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240524232121.284515-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 10 +++++ target/arm/tcg/translate-a64.c | 68 ++++++++++------------------------ 2 files changed, 29 insertions(+), 49 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7e993ed345f..f48adef5bba 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -55,6 +55,7 @@ @rrr_q1e3 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=3 @rrrr_q1e3 ........ ... rm:5 . ra:5 rn:5 rd:5 &qrrrr_e q=1 esz=3 +@qrrr_b . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=0 @qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 @qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd @qrrr_e . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5 &qrrr_e @@ -847,6 +848,15 @@ SMINP_v 0.00 1110 ..1 ..... 10101 1 ..... ..... @qrrr_e UMAXP_v 0.10 1110 ..1 ..... 10100 1 ..... ..... @qrrr_e UMINP_v 0.10 1110 ..1 ..... 10101 1 ..... ..... @qrrr_e +AND_v 0.00 1110 001 ..... 00011 1 ..... ..... @qrrr_b +BIC_v 0.00 1110 011 ..... 00011 1 ..... ..... @qrrr_b +ORR_v 0.00 1110 101 ..... 00011 1 ..... ..... @qrrr_b +ORN_v 0.00 1110 111 ..... 00011 1 ..... ..... @qrrr_b +EOR_v 0.10 1110 001 ..... 00011 1 ..... ..... @qrrr_b +BSL_v 0.10 1110 011 ..... 00011 1 ..... ..... @qrrr_b +BIT_v 0.10 1110 101 ..... 00011 1 ..... ..... @qrrr_b +BIF_v 0.10 1110 111 ..... 00011 1 ..... ..... @qrrr_b + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index a4ff1fd2027..9167e4d0bd6 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5280,6 +5280,24 @@ TRANS(SMINP_v, do_gvec_fn3_no64, a, gen_gvec_sminp) TRANS(UMAXP_v, do_gvec_fn3_no64, a, gen_gvec_umaxp) TRANS(UMINP_v, do_gvec_fn3_no64, a, gen_gvec_uminp) +TRANS(AND_v, do_gvec_fn3, a, tcg_gen_gvec_and) +TRANS(BIC_v, do_gvec_fn3, a, tcg_gen_gvec_andc) +TRANS(ORR_v, do_gvec_fn3, a, tcg_gen_gvec_or) +TRANS(ORN_v, do_gvec_fn3, a, tcg_gen_gvec_orc) +TRANS(EOR_v, do_gvec_fn3, a, tcg_gen_gvec_xor) + +static bool do_bitsel(DisasContext *s, bool is_q, int d, int a, int b, int c) +{ + if (fp_access_check(s)) { + gen_gvec_fn4(s, is_q, d, a, b, c, tcg_gen_gvec_bitsel, 0); + } + return true; +} + +TRANS(BSL_v, do_bitsel, a->q, a->rd, a->rd, a->rn, a->rm) +TRANS(BIT_v, do_bitsel, a->q, a->rd, a->rm, a->rn, a->rd) +TRANS(BIF_v, do_bitsel, a->q, a->rd, a->rm, a->rd, a->rn) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -10901,52 +10919,6 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* Logic op (opcode == 3) subgroup of C3.6.16. */ -static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 22, 2); - bool is_u = extract32(insn, 29, 1); - bool is_q = extract32(insn, 30, 1); - - if (!fp_access_check(s)) { - return; - } - - switch (size + 4 * is_u) { - case 0: /* AND */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_and, 0); - return; - case 1: /* BIC */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_andc, 0); - return; - case 2: /* ORR */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_or, 0); - return; - case 3: /* ORN */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_orc, 0); - return; - case 4: /* EOR */ - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_xor, 0); - return; - - case 5: /* BSL bitwise select */ - gen_gvec_fn4(s, is_q, rd, rd, rn, rm, tcg_gen_gvec_bitsel, 0); - return; - case 6: /* BIT, bitwise insert if true */ - gen_gvec_fn4(s, is_q, rd, rm, rn, rd, tcg_gen_gvec_bitsel, 0); - return; - case 7: /* BIF, bitwise insert if false */ - gen_gvec_fn4(s, is_q, rd, rm, rd, rn, tcg_gen_gvec_bitsel, 0); - return; - - default: - g_assert_not_reached(); - } -} - /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { @@ -11212,12 +11184,10 @@ static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 11, 5); switch (opcode) { - case 0x3: /* logic ops */ - disas_simd_3same_logic(s, insn); - break; default: disas_simd_3same_int(s, insn); break; + case 0x3: /* logic ops */ case 0x14: /* SMAXP, UMAXP */ case 0x15: /* SMINP, UMINP */ case 0x17: /* ADDP */