From patchwork Fri May 31 12:03:47 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 800526 Delivered-To: patch@linaro.org Received: by 2002:a5d:65c4:0:b0:35b:5a80:51b4 with SMTP id e4csp696303wrw; Fri, 31 May 2024 05:11:05 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWPVSDAD7XqQC8SY2bJe+fsG3salTBK0weT5E1JzGAl180SJ8H0BaRFmb5l9qQ9wVazK41v5rz8bTZuFKpyO/2l X-Google-Smtp-Source: AGHT+IHumDbGF0rE0BgwUna6Vw75TIzJ/bPKjm9/DBSA4CYtJ1DA7uCKqIa76qMPF/1aOd6BYDHe X-Received: by 2002:a05:620a:b90:b0:794:b33f:3d82 with SMTP id af79cd13be357-794f5ebf325mr153010285a.49.1717157465444; Fri, 31 May 2024 05:11:05 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717157465; cv=none; d=google.com; s=arc-20160816; b=cNr80C4a4vHUiGygGgzf+VYDyFhiIL+di5FlClp3kGziC53S5Pnm/d17XQfhhup618 ioHr4NIvsjccFJ+MWczC3fgHy0r2IfS23V2h32QzEh3e9g9r/QdaRyi1ySu2OU+RUALw hMzdRh++68EtCxcg4vZIoZbEl581r16vGUZmHD1e6chu2kieG9k94mLeFLGtVHknVtK0 D5u5b6dbRxD7qZwPO9d5HSqyP3GZaaaBA04rn3dhDsHCz6yZwfr6APt/qBu4s3KdguHT qae86oo4158sklxQvu2UqlwduRbPXvcXRVOz9U1GV8kB2l2HUUSJ8UERxCMTAhLRTU2y ZvSA== 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=GOiKXyZ5P/z+r+ohseMh9b0m5QE2JHM0mBhqhBUbRd8=; fh=PnYt+qEB9tAfMKoqBm2xjKOFpYyFFGPudh5cVIoieJM=; b=OtXoK01pMBUeh+z9w+TE6S371uiDaASHyc40jo3aG+lQjn3BCzgc03BekRx9DHmG7G F8i9OLrTQGFjLordrOWp7QwhqLPi/SUin3OpFcRgtpwEosFyMHyzi9oxGmTJ7droFYM2 1HQiigy6rPnCyZFZQlSFyFCEJGagkTp9Ew/1VlcnObH+zdng8IkWJ1FVjDpGkf3Ahoqx jfEonAtT4xrIpV+JKbeNrwo7/UaBsx+j/THFlhBWKNaoQf6GQdZBLmfGjzIJdjEbCikM qCByslMg9UkAV+rLJ7QOY8rJNCKuXa/hQ109fACkU3tij9vdaVtEoZ7I/YdcZpe8Rn3o PuqA==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=g7ZAbYjz; 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 af79cd13be357-794f2f05c4csi182208485a.135.2024.05.31.05.11.05 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Fri, 31 May 2024 05:11:05 -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=g7ZAbYjz; 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 1sD108-0004Z1-1z; Fri, 31 May 2024 08:04:52 -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 1sD0zn-0004Qs-Bq for qemu-devel@nongnu.org; Fri, 31 May 2024 08:04:31 -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 1sD0zh-0003Tq-RO for qemu-devel@nongnu.org; Fri, 31 May 2024 08:04:30 -0400 Received: by mail-wm1-x336.google.com with SMTP id 5b1f17b1804b1-4211249fbafso18725915e9.3 for ; Fri, 31 May 2024 05:04:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1717157063; x=1717761863; 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=GOiKXyZ5P/z+r+ohseMh9b0m5QE2JHM0mBhqhBUbRd8=; b=g7ZAbYjzpn5il471JCbZtRQ0EsqykAM9UbqvfyOqvoOnCu9nce+1oW4MSQLUdkmtp9 3npcwfa1JHiqIjXDRo98W4WQRFay9f19We3pDvEm7/UvxjlDg3ynjP3tiznZRoHnbFQ5 ROYaP74iESat9nVleXZPjjVjYZvcZ70FaqdBJs+HlIDuIpFQliR1vKHS/DajMcTvoeqL pOpF3PXrStizhBWvW3z03OnxnsVOT20jI8gMaS5XIya55/dQ3Ra5nC0dfIDANhTcvv33 3R5rqWP2xKqofApyQIT8MaWPl01UsIsEL5aoiaLX6eDBhyMEcEESBG7d90URW2E2p9az ZIWw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1717157063; x=1717761863; 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=GOiKXyZ5P/z+r+ohseMh9b0m5QE2JHM0mBhqhBUbRd8=; b=jsGWZD3TKY33KdirtXDMq32ntOYhKVsvbcsMlbqfyYkuJfC8KFVeX8o4NO/slOk+CM IDhCfbq83SemGfZ7Dgaxp2BbqW4Ais6jFj55yvGG/rGxOB0bKteRhTdK9c7REMlHZ3lt M2kQfiEvUoyI2prCGRvzT09VRSgFlJeGWho9eL8aqRuSqxjv7hGLylrH+BYnt7N/Pxyp H0oqO4x327PWe7/BaN3VAgVJuTPRJSlchlw/jOw3TZ25tU/aLOCaBSoyEY2fI/CkxoT9 N/AW9RCHf0VtzpimxInpSMh4BZqwQS26b4pjynsMCXuvjrFJ97cImotWdtu6qymzmnkM 2Jjw== X-Gm-Message-State: AOJu0Yw5j0xiUvk9/L4PzDCmTdnMbdPZP6Q7Iu069ovJjxRqr6vnCv2f BkJA2i/dW5ch6U93e+kbKjNYQXQzbgNz2RdLmuh4Rpnv4eCvTKa0wQv/xKrXxBCaUqdTPMhnlDx Q X-Received: by 2002:a05:600c:1e12:b0:421:2a43:6518 with SMTP id 5b1f17b1804b1-4212e0c12ddmr13941565e9.33.1717157063351; Fri, 31 May 2024 05:04:23 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [2001:8b0:1d0::2]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-42129de0cf9sm37027685e9.13.2024.05.31.05.04.22 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 31 May 2024 05:04:23 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 29/43] target/arm: Convert SRHADD, URHADD to gvec Date: Fri, 31 May 2024 13:03:47 +0100 Message-Id: <20240531120401.394550-30-peter.maydell@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240531120401.394550-1-peter.maydell@linaro.org> References: <20240531120401.394550-1-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: 20240528203044.612851-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 7 -- target/arm/tcg/translate.h | 4 + target/arm/tcg/gengvec.c | 144 ++++++++++++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 27 ------ target/arm/tcg/translate-a64.c | 48 ++--------- target/arm/tcg/translate-neon.c | 26 +----- 6 files changed, 158 insertions(+), 98 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index b95f24ed0aa..85f93025636 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -268,13 +268,6 @@ DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) DEF_HELPER_FLAGS_3(check_hcr_el2_trap, TCG_CALL_NO_WG, void, env, i32, i32) /* neon_helper.c */ -DEF_HELPER_2(neon_rhadd_s8, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_u8, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_s16, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_u16, i32, i32, i32) -DEF_HELPER_2(neon_rhadd_s32, s32, s32, s32) -DEF_HELPER_2(neon_rhadd_u32, i32, i32, i32) - DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 315e0afd043..3b1e68b7794 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -480,6 +480,10 @@ void gen_gvec_shsub(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_uhsub(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_srhadd(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_urhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index c46365c3a6f..119826bf284 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2149,3 +2149,147 @@ void gen_gvec_uhsub(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, assert(vece <= MO_32); tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); } + +static void gen_srhadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_sar8i_i64(a, a, 1); + tcg_gen_vec_sar8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_srhadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_sar16i_i64(a, a, 1); + tcg_gen_vec_sar16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_srhadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_or_i32(t, a, b); + tcg_gen_sari_i32(a, a, 1); + tcg_gen_sari_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_srhadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_or_vec(vece, t, a, b); + tcg_gen_sari_vec(vece, a, a, 1); + tcg_gen_sari_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_srhadd(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_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_srhadd8_i64, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_srhadd16_i64, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_srhadd_i32, + .fniv = gen_srhadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_urhadd8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_shr8i_i64(a, a, 1); + tcg_gen_vec_shr8i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_add8_i64(d, a, b); + tcg_gen_vec_add8_i64(d, d, t); +} + +static void gen_urhadd16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_or_i64(t, a, b); + tcg_gen_vec_shr16i_i64(a, a, 1); + tcg_gen_vec_shr16i_i64(b, b, 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_add16_i64(d, a, b); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_urhadd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_or_i32(t, a, b); + tcg_gen_shri_i32(a, a, 1); + tcg_gen_shri_i32(b, b, 1); + tcg_gen_andi_i32(t, t, 1); + tcg_gen_add_i32(d, a, b); + tcg_gen_add_i32(d, d, t); +} + +static void gen_urhadd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_or_vec(vece, t, a, b); + tcg_gen_shri_vec(vece, a, a, 1); + tcg_gen_shri_vec(vece, b, b, 1); + tcg_gen_and_vec(vece, t, t, tcg_constant_vec_matching(d, vece, 1)); + tcg_gen_add_vec(vece, d, a, b); + tcg_gen_add_vec(vece, d, d, t); +} + +void gen_gvec_urhadd(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_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 g[] = { + { .fni8 = gen_urhadd8_i64, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_urhadd16_i64, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_urhadd_i32, + .fniv = gen_urhadd_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index d1641a5252c..082bfd88adf 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -179,33 +179,6 @@ uint32_t HELPER(glue(neon_,name))(uint32_t arg) \ return arg; \ } -#define NEON_FN(dest, src1, src2) dest = (src1 + src2 + 1) >> 1 -NEON_VOP(rhadd_s8, neon_s8, 4) -NEON_VOP(rhadd_u8, neon_u8, 4) -NEON_VOP(rhadd_s16, neon_s16, 2) -NEON_VOP(rhadd_u16, neon_u16, 2) -#undef NEON_FN - -int32_t HELPER(neon_rhadd_s32)(int32_t src1, int32_t src2) -{ - int32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if ((src1 | src2) & 1) - dest++; - return dest; -} - -uint32_t HELPER(neon_rhadd_u32)(uint32_t src1, uint32_t src2) -{ - uint32_t dest; - - dest = (src1 >> 1) + (src2 >> 1); - if ((src1 | src2) & 1) - dest++; - return dest; -} - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 6571b999f49..40aa7a9d577 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -10915,7 +10915,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int pass; switch (opcode) { case 0x13: /* MUL, PMUL */ @@ -10969,6 +10968,13 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x02: /* SRHADD, URHADD */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_urhadd, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_srhadd, size); + } + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -11021,45 +11027,7 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } return; } - - if (size == 3) { - g_assert_not_reached(); - } else { - for (pass = 0; pass < (is_q ? 4 : 2); 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(); - NeonGenTwoOpFn *genfn = NULL; - NeonGenTwoOpEnvFn *genenvfn = NULL; - - read_vec_element_i32(s, tcg_op1, rn, pass, MO_32); - read_vec_element_i32(s, tcg_op2, rm, pass, MO_32); - - switch (opcode) { - case 0x2: /* SRHADD, URHADD */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 }, - { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 }, - { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 }, - }; - genfn = fns[size][u]; - break; - } - default: - g_assert_not_reached(); - } - - if (genenvfn) { - genenvfn(tcg_res, tcg_env, tcg_op1, tcg_op2); - } else { - genfn(tcg_res, tcg_op1, tcg_op2); - } - - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - clear_vec_high(s, is_q, rd); + g_assert_not_reached(); } /* AdvSIMD three same diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index d59d5804c55..f9a8753906a 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -845,6 +845,8 @@ DO_3SAME_NO_SZ_3(VHADD_S, gen_gvec_shadd) DO_3SAME_NO_SZ_3(VHADD_U, gen_gvec_uhadd) DO_3SAME_NO_SZ_3(VHSUB_S, gen_gvec_shsub) DO_3SAME_NO_SZ_3(VHSUB_U, gen_gvec_uhsub) +DO_3SAME_NO_SZ_3(VRHADD_S, gen_gvec_srhadd) +DO_3SAME_NO_SZ_3(VRHADD_U, gen_gvec_urhadd) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -922,27 +924,6 @@ DO_SHA2(SHA256H, gen_helper_crypto_sha256h) DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) -#define DO_3SAME_32(INSN, FUNC) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - static const GVecGen3 ops[4] = { \ - { .fni4 = gen_helper_neon_##FUNC##8 }, \ - { .fni4 = gen_helper_neon_##FUNC##16 }, \ - { .fni4 = gen_helper_neon_##FUNC##32 }, \ - { 0 }, \ - }; \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ - } \ - static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size > 2) { \ - return false; \ - } \ - return do_3same(s, a, gen_##INSN##_3s); \ - } - /* * Some helper functions need to be passed the tcg_env. In order * to use those with the gvec APIs like tcg_gen_gvec_3() we need @@ -955,9 +936,6 @@ DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) FUNC(d, tcg_env, n, m); \ } -DO_3SAME_32(VRHADD_S, rhadd_s) -DO_3SAME_32(VRHADD_U, rhadd_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); \