From patchwork Wed May 13 16:32:31 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 186651 Delivered-To: patch@linaro.org Received: by 2002:a92:5b0a:0:0:0:0:0 with SMTP id p10csp615246ilb; Wed, 13 May 2020 09:36:08 -0700 (PDT) X-Google-Smtp-Source: ABdhPJwA1YTMWcFeIIoDvi/xVhTBpzHm/xzA6CCswCGoUtp4EJFerzuurnnE49G4jcB8meeHsTwu X-Received: by 2002:a0c:9e6d:: with SMTP id z45mr501861qve.206.1589387767963; Wed, 13 May 2020 09:36:07 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1589387767; cv=none; d=google.com; s=arc-20160816; b=BCBGubiKtVzSSEVMc53OajS1MBmNkAHpWPb6WJzBNFbVpHyPu4E1PElSZiDiKlCkzn 3NcbD53I4Z6KqDeXM+HVchTYET3k4XUMrBfhVEu/KgV9QO75wVlzpytNmTzZCPQBFoFp V3JG8472lnieKuXTa6mtAyDwU2mt4OuOByPi0uQch6SjlCEvg+A8j0IYp5vaDwNDAr55 W5R2UXDc59cCuKBtt9aCZO09wr76OooY+xMrRQLlMt2z9MAgDBFN/9QNkPx5rRJNLf78 aWHY3zoBxl9OmUcMsYb0AmKUlSwzfZOTZxMaWYIYRYUJRTzBepv5utHX+8oe4piVNIvm kgQQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:cc: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=XS/mIW9X0kPcGiRIELKdlQNFPmcbFEWtnUU78dllzHU=; b=Kugnd4Dt4CXsr6mT5ZRl0p3nW5YCYnGhXkN0ylmHCV3HfJ+GqAba72e7sf9viCG60o UTubBRe+K7fAitgGFV0EOyKcN1NUXYKdeKiuYpmosNxkWiEaeEKNVZf0LMMnp2UOoFYP 1vZlO5F7HAV3i6w6DT5Awk6MU9GvTh8rdhTbcrWIBY0IqmzMotyxUQSKrj+2UWbF1so0 5xxwVoIy/NwniPiLHcmC12CySdioidlwEZNXd0X8QyVyS853x0qaCzMgkI6dVcQLZn43 ISiYPoQrcfF3kNSJNLipPZAE16RUg5lDQR3MqAM9OLQq5sjBLJiVd1t5ghnGhraoYwCn XZyQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=ormT12iD; 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 j21si148674qtk.376.2020.05.13.09.36.07 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Wed, 13 May 2020 09:36:07 -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=ormT12iD; 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]:32922 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jYuMZ-0006qz-B0 for patch@linaro.org; Wed, 13 May 2020 12:36:07 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:47938) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jYuJS-0003bX-IX for qemu-devel@nongnu.org; Wed, 13 May 2020 12:32:54 -0400 Received: from mail-pg1-x543.google.com ([2607:f8b0:4864:20::543]:41092) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1jYuJQ-0001zq-Tb for qemu-devel@nongnu.org; Wed, 13 May 2020 12:32:54 -0400 Received: by mail-pg1-x543.google.com with SMTP id r10so7514572pgv.8 for ; Wed, 13 May 2020 09:32:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=XS/mIW9X0kPcGiRIELKdlQNFPmcbFEWtnUU78dllzHU=; b=ormT12iD6QOHXRrN7+7/4bsnrS4trYlzsLobNtEUgiSKCmdzSxNv/fvmvInSb8ZGF5 ue4o66cTjqTyD1dqw55swNyyVQYzlb2McSGUV0hFsPpjR7kJSVvcRbH6iylSYtIzWx65 KDnT7Poce2WTu6IxQxRIbfsqmqt88jo9Voxa1ztPMLKJXVxoBA5tGA9rlCSWPWm/KANM OAth5bX6wXtyuhdOyrlBpLFXFmdHJXWTWeED+p555O+d2d5KwDi/H09h5dgvzLm1FXzC Z3FT6+KgQcdao/bJpk6+g4LtHxtepr01Q3B+EhmPjVSCKwrXstmccnhXkewakW809VW7 1Ocw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=XS/mIW9X0kPcGiRIELKdlQNFPmcbFEWtnUU78dllzHU=; b=UKBzUaV/aB8Adg0smJiF34Kzqc1DTYl2mnLU02HUiMQr1fJrEOJau7RDke8Be986nB x3FYl2bWbHWLkvJPeggImFRhj3ksL3VHTcD4Y5a0SW3U9i2YxnBT03e0/D/z+4VRwWP0 VTeUUvtZ3KBVPaOVQH45sxyjKWjuD1V2uU6ZvmdIMwXBJ5dNcdXw2WVSrJ9xHx5w4Nmy dPcAfFkZGV8ckCBwT8nsCRuUuxlm7QlX6WhxE6wp5VUKxwNbbbhzhAe93d33fn1FR03X dXvnOrlqC5vkQyEBOFwpuY19iD0R0t+24oTdDS4rmD8PaAN/dmmj7YmX9e+BB2Wf3beY +eNQ== X-Gm-Message-State: AOAM530f25MERXZ+PPLrfKQ8YMNfgX+gVFJZYWliGNDc8+OoIOdAVbsZ tRZ+NIwPauJIdD9jvpGU/DwrbxYYfps= X-Received: by 2002:a63:1e01:: with SMTP id e1mr117524pge.351.1589387570498; Wed, 13 May 2020 09:32:50 -0700 (PDT) Received: from localhost.localdomain (174-21-143-238.tukw.qwest.net. [174.21.143.238]) by smtp.gmail.com with ESMTPSA id b11sm158025pgq.50.2020.05.13.09.32.49 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 May 2020 09:32:49 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH v4 02/16] target/arm: Create gen_gvec_{u,s}{rshr,rsra} Date: Wed, 13 May 2020 09:32:31 -0700 Message-Id: <20200513163245.17915-3-richard.henderson@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20200513163245.17915-1-richard.henderson@linaro.org> References: <20200513163245.17915-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::543; envelope-from=richard.henderson@linaro.org; helo=mail-pg1-x543.google.com X-detected-operating-system: by eggs.gnu.org: No matching host in p0f cache. That's all we know. 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_PASS=-0.001, URIBL_BLOCKED=0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: peter.maydell@linaro.org Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" Create vectorized versions of handle_shri_with_rndacc for shift+round and shift+round+accumulate. Add out-of-line helpers in preparation for longer vector lengths from SVE. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson --- target/arm/helper.h | 20 ++ target/arm/translate.h | 9 + target/arm/translate-a64.c | 11 +- target/arm/translate.c | 463 +++++++++++++++++++++++++++++++++++-- target/arm/vec_helper.c | 50 ++++ 5 files changed, 527 insertions(+), 26 deletions(-) -- 2.20.1 diff --git a/target/arm/helper.h b/target/arm/helper.h index 9bc162345c..aeb1f52455 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -701,6 +701,26 @@ DEF_HELPER_FLAGS_3(gvec_usra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_usra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_usra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_srsra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_ursra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index 1839a59a8e..1db3b43a61 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -302,6 +302,15 @@ 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_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, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +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); +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); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 315de9a9b6..50949d306b 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -10218,10 +10218,15 @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, return; case 0x04: /* SRSHR / URSHR (rounding) */ - break; + gen_gvec_fn2i(s, is_q, rd, rn, shift, + is_u ? gen_gvec_urshr : gen_gvec_srshr, size); + return; + case 0x06: /* SRSRA / URSRA (accum + rounding) */ - accumulate = true; - break; + gen_gvec_fn2i(s, is_q, rd, rn, shift, + is_u ? gen_gvec_ursra : gen_gvec_srsra, size); + return; + default: g_assert_not_reached(); } diff --git a/target/arm/translate.c b/target/arm/translate.c index c18140f2e6..aa03dc236b 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -4000,6 +4000,422 @@ void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, } } +/* + * 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); + tcg_temp_free_i64(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); + tcg_temp_free_i64(t); +} + +static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 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); + tcg_temp_free_i32(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); + tcg_temp_free_i64(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); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(ones); +} + +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); + tcg_temp_free_i64(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); + tcg_temp_free_i64(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); + tcg_temp_free_i32(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); + tcg_temp_free_i64(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); + tcg_temp_free_vec(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); + tcg_temp_free_i64(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); + tcg_temp_free_i64(t); +} + +static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 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); + tcg_temp_free_i32(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); + tcg_temp_free_i64(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); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(ones); +} + +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); + tcg_temp_free_i64(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); + tcg_temp_free_i64(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); + tcg_temp_free_i32(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); + tcg_temp_free_i64(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); + tcg_temp_free_vec(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); @@ -5269,6 +5685,30 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 2: /* VRSHR */ + /* Right shift comes here negative. */ + shift = -shift; + if (u) { + gen_gvec_urshr(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } else { + gen_gvec_srshr(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + + case 3: /* VRSRA */ + /* Right shift comes here negative. */ + shift = -shift; + if (u) { + gen_gvec_ursra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } else { + gen_gvec_srsra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + case 4: /* VSRI */ if (!u) { return 1; @@ -5320,13 +5760,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 2: /* VRSHR */ - case 3: /* VRSRA */ - if (u) - gen_helper_neon_rshl_u64(cpu_V0, cpu_V0, cpu_V1); - else - gen_helper_neon_rshl_s64(cpu_V0, cpu_V0, cpu_V1); - break; case 6: /* VQSHLU */ gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, cpu_V0, cpu_V1); @@ -5343,11 +5776,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: g_assert_not_reached(); } - if (op == 3) { - /* Accumulate. */ - neon_load_reg64(cpu_V1, rd + pass); - tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); - } neon_store_reg64(cpu_V0, rd + pass); } else { /* size < 3 */ /* Operands in T0 and T1. */ @@ -5355,10 +5783,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 2: /* VRSHR */ - case 3: /* VRSRA */ - GEN_NEON_INTEGER_OP(rshl); - break; case 6: /* VQSHLU */ switch (size) { case 0: @@ -5384,13 +5808,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) g_assert_not_reached(); } tcg_temp_free_i32(tmp2); - - if (op == 3) { - /* Accumulate. */ - tmp2 = neon_load_reg(rd, pass); - gen_neon_add(size, tmp, tmp2); - tcg_temp_free_i32(tmp2); - } neon_store_reg(rd, pass, tmp); } } /* for pass */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 230085b35e..fd8b2bff49 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -924,6 +924,56 @@ DO_SRA(gvec_usra_d, uint64_t) #undef DO_SRA +#define DO_RSHR(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + TYPE tmp = n[i] >> (shift - 1); \ + d[i] = (tmp >> 1) + (tmp & 1); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_RSHR(gvec_srshr_b, int8_t) +DO_RSHR(gvec_srshr_h, int16_t) +DO_RSHR(gvec_srshr_s, int32_t) +DO_RSHR(gvec_srshr_d, int64_t) + +DO_RSHR(gvec_urshr_b, uint8_t) +DO_RSHR(gvec_urshr_h, uint16_t) +DO_RSHR(gvec_urshr_s, uint32_t) +DO_RSHR(gvec_urshr_d, uint64_t) + +#undef DO_RSHR + +#define DO_RSRA(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + TYPE tmp = n[i] >> (shift - 1); \ + d[i] += (tmp >> 1) + (tmp & 1); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_RSRA(gvec_srsra_b, int8_t) +DO_RSRA(gvec_srsra_h, int16_t) +DO_RSRA(gvec_srsra_s, int32_t) +DO_RSRA(gvec_srsra_d, int64_t) + +DO_RSRA(gvec_ursra_b, uint8_t) +DO_RSRA(gvec_ursra_h, uint16_t) +DO_RSRA(gvec_ursra_s, uint32_t) +DO_RSRA(gvec_ursra_d, uint64_t) + +#undef DO_RSRA + /* * Convert float16 to float32, raising no exceptions and * preserving exceptional values, including SNaN.