From patchwork Thu Jun 13 12:14:18 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 166636 Delivered-To: patch@linaro.org Received: by 2002:a92:4782:0:0:0:0:0 with SMTP id e2csp725192ilk; Thu, 13 Jun 2019 05:57:36 -0700 (PDT) X-Google-Smtp-Source: APXvYqzYeRbcBxYurPi3kyAUUGUedWrTNpI56XSuT1N6yhPSPswvznce5+PAyBHfn4dMRqbLlmQY X-Received: by 2002:a05:620a:232:: with SMTP id u18mr52515478qkm.131.1560430656594; Thu, 13 Jun 2019 05:57:36 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1560430656; cv=none; d=google.com; s=arc-20160816; b=seURmFPoJGB932LchIyR8UJFPT/HV8c5jBJgYjEbbI/TV9zjDfPcFbhvY6njiE4rXs nD+y0rEdcG0MaukgwxO/KgJCZ8s0OnaQoAQWibtHcKBG8kgDNRUrjrc7q2ebyVORYjyR Qe5HvZr1Rcz7BYphPTEo1zLU+9GKQ+Ba2KT2mY8nnWEas3ifBmD+pnrX7P7XIh9GktrG pkB/bXRd0xgy0Xr4Z55nJnXOafpkYgOWA8axwVhXZ0wzlPscUKgshyFAP4B8zp8sRtrZ C1vbJfvn4fhga2fVXfIj3+EG2waiubPRpDLrz+z5TAfv4poRu5OoJyu27W9wGgR1URQZ fB0w== 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:subject :content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:to:from:dkim-signature; bh=jTppJkM3EO9LMSyvXV94q5a6w/CwGAvYzQRIh3u70xk=; b=QUE0QqkMEO4JYVl6Az7oxa3TAzg7+CPgR7GAttLoWM2vjOGTgxsLWuP6KalbBXDRMj DSC8kgpJwK5cxmJgNpTqly5rfvlYfWBICyYanpIB6sRhppuUtISOJdpqFAaa8xl3GOeh H1tjaJc6BgYzzJuzyTpj/aAzamSG945tjxyGnNoKzUYRVEO/4noPH7wnv5g0867IB097 4V8wpfa3culgBN5vfzno1JD9MQZvqn3+SFmJgaD93fwT7x8qkQjZ16UGwNN0qVkvD/dr 6dn1sQgyqQsil/E0zNChk80dWHgcGc6/9FniHPlIUuY3nWEIKZvBjJOmq/HRhb2H3722 JXhQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=EXZpBIPP; 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=fail (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 t4si1809108qtq.2.2019.06.13.05.57.36 for (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Thu, 13 Jun 2019 05:57:36 -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=fail header.i=@linaro.org header.s=google header.b=EXZpBIPP; 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=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:39544 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hbPIO-0005L7-6C for patch@linaro.org; Thu, 13 Jun 2019 08:57:36 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:59366) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hbOdZ-0008Gu-Uc for qemu-devel@nongnu.org; Thu, 13 Jun 2019 08:15:43 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hbOdT-0004X4-Qc for qemu-devel@nongnu.org; Thu, 13 Jun 2019 08:15:25 -0400 Received: from mail-wr1-x432.google.com ([2a00:1450:4864:20::432]:32995) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1hbOdR-0004P4-LG for qemu-devel@nongnu.org; Thu, 13 Jun 2019 08:15:19 -0400 Received: by mail-wr1-x432.google.com with SMTP id n9so20574248wru.0 for ; Thu, 13 Jun 2019 05:15:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references:mime-version :content-transfer-encoding; bh=jTppJkM3EO9LMSyvXV94q5a6w/CwGAvYzQRIh3u70xk=; b=EXZpBIPPGaZa/qXM4JMh5R4v/2nL+F2ZeaM507y1PBiWkzJoeNWJK/xir/VfZibRU7 zN/cZaiwBUBHNsio3lf1llzuLTyaECWbt51XnZ2Tv1BK5beQ7IcthsYNC5rPB3FLpj5L /xqhfDsHcTpWgn1t+/BKPHmTBrl/8IOv5tR7EtxksTrQ7Whu+Vrj0tkQnqlkfWVlsv36 IduZBa/ztKS5DaIdpjxU/Cg3mEyDGQHXlqH/MaomINPmvmVhsBtNz49DPPFbREkUMeEW IyCTGWvEvIMSFdJi2u+S1+wejZji/7tOXO3bs/DRNxdaJn6lXune7pfdMSS30q/Y1mtl dzkg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=jTppJkM3EO9LMSyvXV94q5a6w/CwGAvYzQRIh3u70xk=; b=WJ/MFH26zurdH7JfrcEuTlTAUA8bF/bLIRJt1zGgkjRftCXeV0ndDpFcRwteBBIlrN zbl/i/lDsY2MoVqgnUBOTeqmXcnEr4lDGkBFj0ZYFw2TuY3kYT8Qa4O5A9RdMj39tR+O Bcaypsr3S0O1T7pavkU/ekYiKdLrlKHGpuT8ld02UrdJUg+JA1I9Mv7F9HCiJqHjx+QD GsPcSGsBzusR6XKnwKEPi8Ce/ZkscG6/lJ4yhBHJYtJkBudWfksz1U5vUx19vTe43Y+f DCyNcFdia24MJEgWgd+TSurDy6ImyKxVCH+vy5Mudi48AL12XVyHNCaV1RbSKnSQPdzr lRsA== X-Gm-Message-State: APjAAAUQz9A+4QpiLj96wbzM/HaxN4a6ylvjJAwIIXnKTOk4YqkrfqaT 5GxMPq3QTwke6jrD2tBQgo3g8V0XTJp6og== X-Received: by 2002:adf:f683:: with SMTP id v3mr2045559wrp.258.1560428110985; Thu, 13 Jun 2019 05:15:10 -0700 (PDT) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [81.2.115.148]) by smtp.gmail.com with ESMTPSA id y6sm2010576wrp.12.2019.06.13.05.15.09 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 13 Jun 2019 05:15:10 -0700 (PDT) From: Peter Maydell To: qemu-devel@nongnu.org Date: Thu, 13 Jun 2019 13:14:18 +0100 Message-Id: <20190613121433.5246-34-peter.maydell@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190613121433.5246-1-peter.maydell@linaro.org> References: <20190613121433.5246-1-peter.maydell@linaro.org> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2a00:1450:4864:20::432 Subject: [Qemu-devel] [PULL 33/48] target/arm: Convert VFP fused multiply-add insns to decodetree 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: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" Convert the VFP fused multiply-add instructions (VFNMA, VFNMS, VFMA, VFMS) to decodetree. Note that in the old decode structure we were implementing these to honour the VFP vector stride/length. These instructions were introduced in VFPv4, and in the v7A architecture they are UNPREDICTABLE if the vector stride or length are non-zero. In v8A they must UNDEF if stride or length are non-zero, like all VFP instructions; we choose to UNDEF always. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson --- target/arm/translate-vfp.inc.c | 121 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 53 +-------------- target/arm/vfp.decode | 9 +++ 3 files changed, 131 insertions(+), 52 deletions(-) -- 2.20.1 diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index 6af99605d5c..ba6506a378c 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -1481,3 +1481,124 @@ static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_sp *a) { return do_vfp_3op_dp(s, gen_helper_vfp_divd, a->vd, a->vn, a->vm, false); } + +static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) +{ + /* + * VFNMA : fd = muladd(-fd, fn, fm) + * VFNMS : fd = muladd(-fd, -fn, fm) + * VFMA : fd = muladd( fd, fn, fm) + * VFMS : fd = muladd( fd, -fn, fm) + * + * These are fused multiply-add, and must be done as one floating + * point operation with no rounding between the multiplication and + * addition steps. NB that doing the negations here as separate + * steps is correct : an input NaN should come out with its sign + * bit flipped if it is a negated-input. + */ + TCGv_ptr fpst; + TCGv_i32 vn, vm, vd; + + /* + * Present in VFPv4 only. + * In v7A, UNPREDICTABLE with non-zero vector length/stride; from + * v8A, must UNDEF. We choose to UNDEF for both v7A and v8A. + */ + if (!arm_dc_feature(s, ARM_FEATURE_VFP4) || + (s->vec_len != 0 || s->vec_stride != 0)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vn = tcg_temp_new_i32(); + vm = tcg_temp_new_i32(); + vd = tcg_temp_new_i32(); + + neon_load_reg32(vn, a->vn); + neon_load_reg32(vm, a->vm); + if (a->o2) { + /* VFNMS, VFMS */ + gen_helper_vfp_negs(vn, vn); + } + neon_load_reg32(vd, a->vd); + if (a->o1 & 1) { + /* VFNMA, VFNMS */ + gen_helper_vfp_negs(vd, vd); + } + fpst = get_fpstatus_ptr(0); + gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); + neon_store_reg32(vd, a->vd); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(vn); + tcg_temp_free_i32(vm); + tcg_temp_free_i32(vd); + + return true; +} + +static bool trans_VFM_dp(DisasContext *s, arg_VFM_sp *a) +{ + /* + * VFNMA : fd = muladd(-fd, fn, fm) + * VFNMS : fd = muladd(-fd, -fn, fm) + * VFMA : fd = muladd( fd, fn, fm) + * VFMS : fd = muladd( fd, -fn, fm) + * + * These are fused multiply-add, and must be done as one floating + * point operation with no rounding between the multiplication and + * addition steps. NB that doing the negations here as separate + * steps is correct : an input NaN should come out with its sign + * bit flipped if it is a negated-input. + */ + TCGv_ptr fpst; + TCGv_i64 vn, vm, vd; + + /* + * Present in VFPv4 only. + * In v7A, UNPREDICTABLE with non-zero vector length/stride; from + * v8A, must UNDEF. We choose to UNDEF for both v7A and v8A. + */ + if (!arm_dc_feature(s, ARM_FEATURE_VFP4) || + (s->vec_len != 0 || s->vec_stride != 0)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vn = tcg_temp_new_i64(); + vm = tcg_temp_new_i64(); + vd = tcg_temp_new_i64(); + + neon_load_reg64(vn, a->vn); + neon_load_reg64(vm, a->vm); + if (a->o2) { + /* VFNMS, VFMS */ + gen_helper_vfp_negd(vn, vn); + } + neon_load_reg64(vd, a->vd); + if (a->o1 & 1) { + /* VFNMA, VFNMS */ + gen_helper_vfp_negd(vd, vd); + } + fpst = get_fpstatus_ptr(0); + gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); + neon_store_reg64(vd, a->vd); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i64(vn); + tcg_temp_free_i64(vm); + tcg_temp_free_i64(vd); + + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index d802f046769..75280e0e524 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -3093,7 +3093,7 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) rn = VFP_SREG_N(insn); switch (op) { - case 0 ... 8: + case 0 ... 13: /* Already handled by decodetree */ return 1; default: @@ -3279,57 +3279,6 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) for (;;) { /* Perform the calculation. */ switch (op) { - case 10: /* VFNMA : fd = muladd(-fd, fn, fm) */ - case 11: /* VFNMS : fd = muladd(-fd, -fn, fm) */ - case 12: /* VFMA : fd = muladd( fd, fn, fm) */ - case 13: /* VFMS : fd = muladd( fd, -fn, fm) */ - /* These are fused multiply-add, and must be done as one - * floating point operation with no rounding between the - * multiplication and addition steps. - * NB that doing the negations here as separate steps is - * correct : an input NaN should come out with its sign bit - * flipped if it is a negated-input. - */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP4)) { - return 1; - } - if (dp) { - TCGv_ptr fpst; - TCGv_i64 frd; - if (op & 1) { - /* VFNMS, VFMS */ - gen_helper_vfp_negd(cpu_F0d, cpu_F0d); - } - frd = tcg_temp_new_i64(); - tcg_gen_ld_f64(frd, cpu_env, vfp_reg_offset(dp, rd)); - if (op & 2) { - /* VFNMA, VFNMS */ - gen_helper_vfp_negd(frd, frd); - } - fpst = get_fpstatus_ptr(0); - gen_helper_vfp_muladdd(cpu_F0d, cpu_F0d, - cpu_F1d, frd, fpst); - tcg_temp_free_ptr(fpst); - tcg_temp_free_i64(frd); - } else { - TCGv_ptr fpst; - TCGv_i32 frd; - if (op & 1) { - /* VFNMS, VFMS */ - gen_helper_vfp_negs(cpu_F0s, cpu_F0s); - } - frd = tcg_temp_new_i32(); - tcg_gen_ld_f32(frd, cpu_env, vfp_reg_offset(dp, rd)); - if (op & 2) { - gen_helper_vfp_negs(frd, frd); - } - fpst = get_fpstatus_ptr(0); - gen_helper_vfp_muladds(cpu_F0s, cpu_F0s, - cpu_F1s, frd, fpst); - tcg_temp_free_ptr(fpst); - tcg_temp_free_i32(frd); - } - break; case 14: /* fconst */ if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { return 1; diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index de305f60e18..37eec0e1310 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -142,3 +142,12 @@ VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... \ vm=%vm_sp vn=%vn_sp vd=%vd_sp VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +VFM_sp ---- 1110 1.01 .... .... 1010 . o2:1 . 0 .... \ + vm=%vm_sp vn=%vn_sp vd=%vd_sp o1=1 +VFM_dp ---- 1110 1.01 .... .... 1011 . o2:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp o1=1 +VFM_sp ---- 1110 1.10 .... .... 1010 . o2:1 . 0 .... \ + vm=%vm_sp vn=%vn_sp vd=%vd_sp o1=2 +VFM_dp ---- 1110 1.10 .... .... 1011 . o2:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp o1=2