From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367368; cv=none; d=zohomail.com; s=zohoarc; b=TJPZXfJAu+p8jKkoa6pLcrdCmczVh4uzbyzWrNbZRwH+gplnxTK2BkLtLvD0PEU/ZkFKMJRH/BSFV848DeFDsZlTa3ABH/m//iBcxoCs2D8Pwjrt1v93RLoeSXP1S6Y7cpH/u7/WEXNfVgP5opqCECY8l63puHLtc5upYAXO6N4= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367368; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=8PUZYN/jxC55WgIbgr/YDIPnxwzEfC4uN3+8U/WL+Ts=; b=JXkPvz0+BRt+CI6hSEYpRbLSEO2/Ki1EINrGNJ7Wk/ayP3eWmu2Hf3S3fnsm2W222MFDtmr6CvuyiVhabJtFHwb7yAfRYuxLn+AMKmBNN5+miZxdNpWryuuQTUIRum/uoXmCjVCT/6WM1Svj+4bLQgys9BGhX7HafADHiSuiyAM= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367368717151.54691291238146; Wed, 13 Mar 2024 15:02:48 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWfe-0007Mu-Hn; Wed, 13 Mar 2024 18:01:58 -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 1rkWfb-0007MA-97 for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:01:55 -0400 Received: from mail-pf1-x42d.google.com ([2607:f8b0:4864:20::42d]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfZ-0004I7-Qa for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:01:55 -0400 Received: by mail-pf1-x42d.google.com with SMTP id d2e1a72fcca58-6e6ac741ff7so405776b3a.0 for ; Wed, 13 Mar 2024 15:01:53 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.01.48 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:01:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367311; x=1710972111; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=8PUZYN/jxC55WgIbgr/YDIPnxwzEfC4uN3+8U/WL+Ts=; b=Q06OjxCZerl1XvDcegt72BmQESemm5mNjTw0F2GRybJyrou8cYROoOdA60KFdfE4xC ZLYVwWpYNBMxS+l5HMHGdC+CU/dTuY49QY90sEAra0gAs5bBDlax4XZ+s2Z5lUHga5P9 tW1qlgUKMY0MmCgcEpcLB+XKnaYLPDjE6izztthTmqRGChPuAlWxKv6Cuu5phs138yxl ILgHU/QD++QuxPOcytMD/q/WXb9k/z0FXtaVLgQKiujOBWZC92MEpxYi6AkptvBBn7MW unrBDwSmmkzq3thwCZjZwL0HXZ83QstxPd7qqbX4Ai5fQrm9cqHlwFx4ac9IcXnIhhvm CKgA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367311; x=1710972111; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=8PUZYN/jxC55WgIbgr/YDIPnxwzEfC4uN3+8U/WL+Ts=; b=YWqpIqF76dwWcnw2y/D2xiYdR7z0+XXCV/AYWJHWYNDznE31dBX1hND+eAL9NW2j4n mzGYv0tin9N+Edy5edgfFeMBwLClmKjWcjcCWWP+8FEAVvfWQBMD3GIebi08CE/+BOJd aq0mK4vyWBfj6toNIyZRy7BT8jFB4i7rASWzLrNJ26ixFRqQC3nrqW7mDwWe6qXh9NF6 qzTTlHKZlFtxvUmFA1h/jRn8i3OcOevyGxyBq3ET5g2Y/3Z1wGiAyQFAZ4zLz5FxBxod fmgJX9CBmGeovLWnalsnyBi8pxgks4ZA2xBmy1kC8BMZ5BsUT2C9a3lPWcHZI6WUICd4 Rs6g== X-Gm-Message-State: AOJu0YyvT0AH/PUGfY2VCM9nzXtbQaWNCuaL70Mf7sMkS5+yCF9ve8zs D8KjUWF2J8dvLcLwE9WZ+p92nO4an0jP+WzTH6pmp1akqsr2ayyYBOW8+ErSr6IllGVEOoB5Hcy b X-Google-Smtp-Source: AGHT+IEZcj3UOOX7c2dqK50m68ikQVMYXpWO/kKRFN0xGjiN0eJ1xNOiZv0VjOk+mgzReffP87wrmw== X-Received: by 2002:a05:6a20:c6c8:b0:1a3:1246:c43e with SMTP id gw8-20020a056a20c6c800b001a31246c43emr228712pzb.28.1710367311677; Wed, 13 Mar 2024 15:01:51 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 1/8] target/riscv/vector_helper.c: set vstart = 0 in GEN_VEXT_VSLIDEUP_VX() Date: Wed, 13 Mar 2024 19:01:34 -0300 Message-ID: <20240313220141.427730-2-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::42d; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-x42d.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=unavailable 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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367369294100001 Content-Type: text/plain; charset="utf-8" The helper isn't setting env->vstart =3D 0 after its execution, as it is expected from every vector instruction that completes successfully. Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/vector_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index fe56c007d5..ca79571ae2 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4781,6 +4781,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , void *vs2, \ } \ *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i - offset)); = \ } \ + env->vstart =3D 0; = \ /* set tail elements to 1s */ \ vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \ } --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367368; cv=none; d=zohomail.com; s=zohoarc; b=BUPxtXoUl03pnwNzlTdQgeLOxTpVSdYubiQt9cXNqmUl6HYnJh9t1s9xJXNLBBBzNQpcMxQa+mCWqZ8IHMX/vdm5VBIbCTWG84/G7ONqefzER1MmrJIQxzL7ph0+oWCZ9G2a3qE/iaEF7i7/k1XsSo4HRuAv+YAi/DZbj8Bahtw= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367368; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=DgCmMDQSmZuQF2R71f2SMhy+sJRtIk+zLEeTXoFqnr0=; b=RR1pMX4TndV/cJLrz7W+fD3fTNlAeK4aLNW8sih6o5+fIcUZ3bqBZVKXcLORVuzZ0jW+LjXPZ7Tgbc+KWgnh1GJ6YBpePVSyeoDGZbiWxEapdZsTgpLsNmgAzDBC7PsJy0li2MBGzduZ/RcJf3ctRDtjyN98EUfhpWShQikcYZg= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367368743795.8467266306961; Wed, 13 Mar 2024 15:02:48 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWfi-0007NU-C9; Wed, 13 Mar 2024 18:02:02 -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 1rkWff-0007N8-VP for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:01:59 -0400 Received: from mail-pf1-x429.google.com ([2607:f8b0:4864:20::429]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfe-0004IT-1A for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:01:59 -0400 Received: by mail-pf1-x429.google.com with SMTP id d2e1a72fcca58-6e6b75211ceso385354b3a.0 for ; Wed, 13 Mar 2024 15:01:56 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.01.51 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:01:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367315; x=1710972115; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=DgCmMDQSmZuQF2R71f2SMhy+sJRtIk+zLEeTXoFqnr0=; b=FcLUht3Jl4ztI0Xs93QZnyFKt60nFXmdMPaM7Wv7b7EFoJJDSiHWLpk7JGVcA0Qt+2 HdS8bDJuN3jzX6SWym75pw//tB/ghVQ0JuY4GxCx++BgOVcPyu3VrYyNvGFjvdakPiMU 3ATXWXYIJt5Te965Nr0ie1I8O9hFbJzOt5fHJX+S3NkP5DoMLp3SuwhYNJ+80Jfv3Bz6 YkKLPin4kbJoiD+nOiLileZFm8lkgxoUjqNf6d0e+lgNHHefoA0963my3X1AjFX6htKx xPW2j+6FM+Vsdc8a9tRW8NZzYJsWA5VzGp3t/sdEWwB1laFRPcnPXIuKY+g1LzAbft06 j40Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367315; x=1710972115; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=DgCmMDQSmZuQF2R71f2SMhy+sJRtIk+zLEeTXoFqnr0=; b=Z8xb1hSSZJkJrRp4jUsZzTLh+qQy7PCHdM2CXdAzfHHEeWq+gApGmur6EPOSk/Fs1m NPkKoZHf+fPO7vhz0FhQNQzYznqtZElphm894uWKjzXovZMOjJODlDuukanoBChVtXfk TuMYCdULowpytnAQ0nwNJQsdvkgELZZ1Da4fJ1WuJL3O0nk+EisKOwBIX6UWAO2ynzxB eXR30aMkxfpc9t0TPMGWg10l8Jr6++GMei9PDP6wBJL2cfk6RXmT3GqoDVAfzwLc9yku OhJhdJEexZYLJKdZHNzgtTCA0n0Yo0d7H1O/DMAq8fsRP/gpjPFY+ixRGWLjwf5n7TRU nb/Q== X-Gm-Message-State: AOJu0YyruU+cc9DTSVGOn32ufFA6dhqPhWrV0ZpmJUb777EJu2Q/bpjI TtlBb7sa3oPYo16y2v/Tr6mlmeVtDymCJjEvcHRmJ/1nY4QwzaNXU508gBz+l8pGr+tssySzmEu B X-Google-Smtp-Source: AGHT+IGNiU2Ud1v0MUvDfJ7c5mrHDTOIZFsFdPrs3ba/09te0l464Q8gmGcUt24N5ZKbx1mt8RpHsQ== X-Received: by 2002:a05:6a20:7f9d:b0:1a3:3c59:9db8 with SMTP id d29-20020a056a207f9d00b001a33c599db8mr254265pzj.39.1710367314775; Wed, 13 Mar 2024 15:01:54 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 2/8] trans_rvv.c.inc: set vstart = 0 in int scalar move insns Date: Wed, 13 Mar 2024 19:01:35 -0300 Message-ID: <20240313220141.427730-3-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::429; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367370959100015 Content-Type: text/plain; charset="utf-8" trans_vmv_x_s, trans_vmv_s_x, trans_vfmv_f_s and trans_vfmv_s_f aren't setting vstart =3D 0 after execution. This is usually done by a helper in vector_helper.c but these functions don't use helpers. We'll set vstart after any potential 'over' brconds, and that will also mandate a mark_vs_dirty() too. Fixes: dedc53cbc9 ("target/riscv: rvv-1.0: integer scalar move instructions= ") Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson --- target/riscv/insn_trans/trans_rvv.c.inc | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index e42728990e..8c16a9f5b3 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -3373,6 +3373,8 @@ static bool trans_vmv_x_s(DisasContext *s, arg_vmv_x_= s *a) vec_element_loadi(s, t1, a->rs2, 0, true); tcg_gen_trunc_i64_tl(dest, t1); gen_set_gpr(s, a->rd, dest); + tcg_gen_movi_tl(cpu_vstart, 0); + mark_vs_dirty(s); return true; } return false; @@ -3399,8 +3401,9 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_= x *a) s1 =3D get_gpr(s, a->rs1, EXT_NONE); tcg_gen_ext_tl_i64(t1, s1); vec_element_storei(s, a->rd, 0, t1); - mark_vs_dirty(s); gen_set_label(over); + tcg_gen_movi_tl(cpu_vstart, 0); + mark_vs_dirty(s); return true; } return false; @@ -3427,6 +3430,8 @@ static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_= f_s *a) } =20 mark_fs_dirty(s); + tcg_gen_movi_tl(cpu_vstart, 0); + mark_vs_dirty(s); return true; } return false; @@ -3452,8 +3457,9 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_= s_f *a) do_nanbox(s, t1, cpu_fpr[a->rs1]); =20 vec_element_storei(s, a->rd, 0, t1); - mark_vs_dirty(s); gen_set_label(over); + tcg_gen_movi_tl(cpu_vstart, 0); + mark_vs_dirty(s); return true; } return false; --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367415; cv=none; d=zohomail.com; s=zohoarc; b=IoycAp1paMg+42mOjUA6fMk5eRjB8oWlO67nyQP9Sqw2aq0vsi/zuXQ61mHnbDw/tVCSuN1zl3eMTiTjOx8qusAsI8GJcyoI9xexOY9R4PkTyvMqV74/OfOV3QWIIwnaratgG2rYRO7CeQWtn1E+S11zd90K03qWGPY745EawTg= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367415; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=CfFgw9URtygopPhOgbzJ9EGeFoJg6+PXSkK7w0QGBRo=; b=lRx9QSrs+hS3NwrBmBlfVL5FHZM7vtAFnKm/aSjDrYUFQdC3WOQHdzl/OUJnkRaT2H0tzpYWvGt8WGAR6S6oEpAlsF9QsM4yTETTpvdJ450WI2ODfjBr+6hVSUXmGZZMI7D60CU3ImbwwRznL3mJYD3p6NqxNxHuMMjX90M15cs= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 17103674157121005.4094981284009; Wed, 13 Mar 2024 15:03:35 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWgK-0007VI-9q; Wed, 13 Mar 2024 18:02:40 -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 1rkWfr-0007OU-Nm for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:13 -0400 Received: from mail-pf1-x42b.google.com ([2607:f8b0:4864:20::42b]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfg-0004Ij-4O for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:11 -0400 Received: by mail-pf1-x42b.google.com with SMTP id d2e1a72fcca58-6e6b6e000a4so320781b3a.0 for ; Wed, 13 Mar 2024 15:01:59 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.01.55 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:01:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367318; x=1710972118; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=CfFgw9URtygopPhOgbzJ9EGeFoJg6+PXSkK7w0QGBRo=; b=Yvtazkhld1epol0LZEQ5SOx5+2z6TPvAD59tIiLLpsmm1U1hLIeqd01wsj0VsHM40Q AaZ5zx7WfnVt6FCfjCplwm1YjP/r5kfn1T3Vj9xoeWI+8wJLgaAlS4UYBg6r4UMGltYu J+fIiIIQ7K6oMeQkSEkcQHA+GdXdbBMNWliD22zbioFdlEw6CVhCMKQfAV93IUR76/Ro BWm7uq91MWgZ5M12AdRDpqVZmvgj30iJeO4XaVy/acH0FdLANCHztigK6PUNeSvCSm9d 1zDc+AkH3MP7ACkkHi2n4K16YL18Pv9SvMT2G4Ue3z5dORCu9QichW3Tn/l7Y7rsNvsx qFpA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367318; x=1710972118; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=CfFgw9URtygopPhOgbzJ9EGeFoJg6+PXSkK7w0QGBRo=; b=EqdqM1r6Z+qld6hyNldbKfdudVzVKuXNWT1LJ7nP97Gs97dPfF6108W7sow6+Z+oSp DSb4MaJD/Ewt/sd9WOmbypFliMdG2rAi57T237SmGmMHLabmlbemsYqGwUe1Xmamu6lf R1maHzuRtrtQzhgj2mSN1fLTByPwHJttp1CezTWT75eFNPp76HjGuMQ95LByc+R8Acjj aq6QEV+bvRwCxrWWIwAg7871xp1U9U+ZJBQDKOx20Dx2dWljDgCzUkpX3To9Yi5n58tu QTc7TUFQOfNq9qDjkYjWNmfixC0bHo+/UQIbT3R0I9T524R14wgCbxIsvUwkH2ukI3Pq fkww== X-Gm-Message-State: AOJu0YwBNzdWUzep2X5PvcBWYfRapOEVEyW3N+xqthhS1uMiWVLGHex5 5A/zUsNuRjShCALMxNTVYdsEUsHX8CJ8iPS/dB3xp+q2++kEiIYR89fj/kVDzegJV9vIfOFN2ri r X-Google-Smtp-Source: AGHT+IFYCls9YSFH+X05Q7X9LuLa+hHy6rj8HAIHenlhmK0C7XmWg0UxKgusNJEcJIZW53AOkziNqA== X-Received: by 2002:a05:6a00:181f:b0:6e6:96cb:3ab8 with SMTP id y31-20020a056a00181f00b006e696cb3ab8mr133749pfa.10.1710367317887; Wed, 13 Mar 2024 15:01:57 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 3/8] target/riscv: always clear vstart in whole vec move insns Date: Wed, 13 Mar 2024 19:01:36 -0300 Message-ID: <20240313220141.427730-4-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::42b; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-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, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=unavailable 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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367417145100007 Content-Type: text/plain; charset="utf-8" These insns have 2 paths: we'll either have vstart already cleared if vstart_eq_zero or we'll do a brcond to check if vstart >=3D maxsz to call the 'vmvr_v' helper. The helper will clear vstart if it executes until the end, or if vstart >=3D vl. However, if vstart >=3D maxsz, the helper will be skipped, and vstart won't be cleared since the helper is being responsible from doing it. We want to make the helpers responsible to manage vstart, including these corner cases, precisely to avoid these situations. Move the vstart >=3D maxsz cond to the helper, and be sure to clear vstart if that happens. This way we're now sure that vstart is being cleared in the end of the execution, regardless of the path taken. Fixes: f714361ed7 ("target/riscv: rvv-1.0: implement vstart CSR") Signed-off-by: Daniel Henrique Barboza --- target/riscv/insn_trans/trans_rvv.c.inc | 3 --- target/riscv/vector_helper.c | 5 +++++ 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index 8c16a9f5b3..52c26a7834 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -3664,12 +3664,9 @@ static bool trans_##NAME(DisasContext *s, arg_##NAME= * a) \ vreg_ofs(s, a->rs2), maxsz, maxsz); \ mark_vs_dirty(s); \ } else { \ - TCGLabel *over =3D gen_new_label(); \ - tcg_gen_brcondi_tl(TCG_COND_GEU, cpu_vstart, maxsz, over); \ tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), \ tcg_env, maxsz, maxsz, 0, gen_helper_vmvr_v= ); \ mark_vs_dirty(s); \ - gen_set_label(over); \ } \ return true; \ } \ diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index ca79571ae2..cd8235ea98 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -5075,6 +5075,11 @@ void HELPER(vmvr_v)(void *vd, void *vs2, CPURISCVSta= te *env, uint32_t desc) uint32_t startb =3D env->vstart * sewb; uint32_t i =3D startb; =20 + if (env->vstart >=3D maxsz) { + env->vstart =3D 0; + return; + } + memcpy((uint8_t *)vd + H1(i), (uint8_t *)vs2 + H1(i), maxsz - startb); --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367387; cv=none; d=zohomail.com; s=zohoarc; b=Sddb72N5wrMYMykhqFUfjPI4Ih2+RShyq2Da+Cjw95WQG0SZoNPxpOYTUqpORFz84OvQ1r1dIi2/mQqxtmGJ/tqvCwQvp1P3Kzf8L7A9upwVzBLDmuwjtCFE+FsoCiBy6wIZegGi3Inij3WGIiyAN41uQsT0zqWcVnQlTNewUHI= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367387; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=HPly5yBBZQQVtgU/69v3f7o9ty+mZmpXig0D2/l9sek=; b=UqCJezcGuUtVeI6CqdgYiSonnj4OuI/G79gALkIxc6X2Zf1Aaw9eO7fRvuWfZcYFhZWTGk2X5VBiqBMXn0io44jDkhK9ZBdUwUa0Bv4LAfS81/Ji4PfbO9uOX5JOGVKZ+UaIe+JminaQD2s/t7oRkzgKuPBgDjlQ1OWHErUnjlM= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367387503606.3357498740995; Wed, 13 Mar 2024 15:03:07 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWgF-0007Su-6v; Wed, 13 Mar 2024 18:02:35 -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 1rkWfq-0007O7-C5 for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:10 -0400 Received: from mail-pf1-x432.google.com ([2607:f8b0:4864:20::432]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfj-0004J2-Ev for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:10 -0400 Received: by mail-pf1-x432.google.com with SMTP id d2e1a72fcca58-6e6a9fafacdso312205b3a.2 for ; Wed, 13 Mar 2024 15:02:03 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.01.58 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:02:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367321; x=1710972121; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=HPly5yBBZQQVtgU/69v3f7o9ty+mZmpXig0D2/l9sek=; b=R7jiD+ii3wAWAnCHmWsf3PZM6SMheqfbml6VTZqDoGCzTrD0Fw3bHxqZLbFZLRv2cz j8hjFPX7y6tId6jgaPpFKfILfgsOv4rPfa+VLXC1eRIpd8BnNdgVjqg5Gk7RYlT6IDIU zh4VDi5pe5yQGTQcicSmlmpNfFNcLXQUqMPnsZvRzaAjOjgrySZrpplr0MYjfDwXZtMy n6f7tWNOahw9n/ZWNGSQhFiH2JQMMiE9T+KX9ingcq6VaYfoX/n0lSffGwAVwflN6Y8+ qwiTPBMzH7x5Fo76Lq9txszPzxpiNxedWd//R7kA2WN3K2srbN8n+c1QxLuwERxXYrFA nWuQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367321; x=1710972121; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=HPly5yBBZQQVtgU/69v3f7o9ty+mZmpXig0D2/l9sek=; b=cFgSHk4QjHenHs/lOnI4GsLdmbv57fwF7/U53f2IuWTQ84GZ3uTKMJ83mHPsFoEWjA nSHlx2ri3cybAa14L99qIt7qchtUhFGauXBWiY5X8c9W1qnDisRn7b5QjPNu7hvL8CfH ujdEJajZ2qAnJsmYng6AyaKAm9EAUTxbx97FErUBU5ConNm81OdDsUooACBfgAGEKwRZ LqpanjTtZ1dJhCN+i49djV8/x0wn7li2XbQl7EpQKnZCk1fmsmOBH2INm7CG1w/Mo0Qy Z6V1jOQTB7+3QFtKyhd7tenwWSxJfIraFLaJQKsqxy+YLVApvx9WtdQ2H+fA6Eg6JhmK WSuQ== X-Gm-Message-State: AOJu0Yw6TsPO0rea7wtDKflt8L0CyH89yruRBKePu6r3BbvzeQfWyrIc bKS34zXiODhf47+V+fgmswt1QDfImAWp4rD6QpIujhZhxnE9bJO80nf2UuXwru0tiIDF1ygb7Qd Z X-Google-Smtp-Source: AGHT+IHjcswP445Lqak7DEYOnImeOOSlBNAYbNXPMNAJUpYy7J5de9HmjtobIBvKiPo9WyPdy6sDjw== X-Received: by 2002:a05:6a00:22d1:b0:6e5:43b5:953b with SMTP id f17-20020a056a0022d100b006e543b5953bmr19401pfj.14.1710367321074; Wed, 13 Mar 2024 15:02:01 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 4/8] target/riscv/vector_helpers: do early exit when vstart >= vl Date: Wed, 13 Mar 2024 19:01:37 -0300 Message-ID: <20240313220141.427730-5-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::432; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-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=unavailable 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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367389073100003 Content-Type: text/plain; charset="utf-8" We're going to make changes that will required each helper to be responsible for the 'vstart' management, i.e. we will relieve the 'vstart < vl' assumption that helpers have today. Helpers are usually able to deal with vstart >=3D vl, i.e. doing nothing aside from setting vstart =3D 0 at the end, but the tail update functions will update the tail regardless of vstart being valid or not. Unifying the tail update process in a single function that would handle the vstart >=3D vl case isn't trivial. We have 2 functions that are used to update tail: vext_set_tail_elems_1s() and vext_set_elems_1s(). The latter is a more generic function that is also used to mask elements. There's no easy way of making all callers using vext_set_tail_elems_1s() because we're not encoding NF properly in all cases [1]. This patch takes a blunt approach: do an early exit in every single vector helper if vstart >=3D vl. We can worry about unifying the tail update process later. [1] https://lore.kernel.org/qemu-riscv/1590234b-0291-432a-a0fa-c5a6876097bc= @linux.alibaba.com/ Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson --- target/riscv/vcrypto_helper.c | 32 ++++++++++++ target/riscv/vector_helper.c | 88 +++++++++++++++++++++++++++++++++ target/riscv/vector_internals.c | 4 ++ target/riscv/vector_internals.h | 9 ++++ 4 files changed, 133 insertions(+) diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c index e2d719b13b..f7423df226 100644 --- a/target/riscv/vcrypto_helper.c +++ b/target/riscv/vcrypto_helper.c @@ -222,6 +222,8 @@ static inline void xor_round_key(AESState *round_state,= AESState *round_key) uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); = \ uint32_t vta =3D vext_vta(desc); = \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { = \ AESState round_key; \ round_key.d[0] =3D *((uint64_t *)vs2 + H8(i * 2 + 0)); = \ @@ -246,6 +248,8 @@ static inline void xor_round_key(AESState *round_state,= AESState *round_key) uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); = \ uint32_t vta =3D vext_vta(desc); = \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { = \ AESState round_key; \ round_key.d[0] =3D *((uint64_t *)vs2 + H8(0)); = \ @@ -305,6 +309,8 @@ void HELPER(vaeskf1_vi)(void *vd_vptr, void *vs2_vptr, = uint32_t uimm, uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + uimm &=3D 0b1111; if (uimm > 10 || uimm =3D=3D 0) { uimm ^=3D 0b1000; @@ -351,6 +357,8 @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, = uint32_t uimm, uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + uimm &=3D 0b1111; if (uimm > 14 || uimm < 2) { uimm ^=3D 0b1000; @@ -457,6 +465,8 @@ void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2,= CPURISCVState *env, uint32_t total_elems; uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { if (sew =3D=3D MO_32) { vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * = 4, @@ -572,6 +582,8 @@ void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs= 2, CPURISCVState *env, uint32_t total_elems; uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, ((uint32_t *)vs1) + 4 * i + 2); @@ -590,6 +602,8 @@ void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs= 2, CPURISCVState *env, uint32_t total_elems; uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, ((uint64_t *)vs1) + 4 * i + 2); @@ -608,6 +622,8 @@ void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs= 2, CPURISCVState *env, uint32_t total_elems; uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, (((uint32_t *)vs1) + 4 * i)); @@ -626,6 +642,8 @@ void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs= 2, CPURISCVState *env, uint32_t total_elems; uint32_t vta =3D vext_vta(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, (((uint64_t *)vs1) + 4 * i)); @@ -658,6 +676,8 @@ void HELPER(vsm3me_vv)(void *vd_vptr, void *vs1_vptr, v= oid *vs2_vptr, uint32_t *vs1 =3D vs1_vptr; uint32_t *vs2 =3D vs2_vptr; =20 + VSTART_CHECK_EARLY_EXIT(env); + for (int i =3D env->vstart / 8; i < env->vl / 8; i++) { uint32_t w[24]; for (int j =3D 0; j < 8; j++) { @@ -757,6 +777,8 @@ void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, ui= nt32_t uimm, uint32_t *vs2 =3D vs2_vptr; uint32_t v1[8], v2[8], v3[8]; =20 + VSTART_CHECK_EARLY_EXIT(env); + for (int i =3D env->vstart / 8; i < env->vl / 8; i++) { for (int k =3D 0; k < 8; k++) { v2[k] =3D bswap32(vd[H4(i * 8 + k)]); @@ -780,6 +802,8 @@ void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, vo= id *vs2_vptr, uint32_t vta =3D vext_vta(desc); uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { uint64_t Y[2] =3D {vd[i * 2 + 0], vd[i * 2 + 1]}; uint64_t H[2] =3D {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; @@ -817,6 +841,8 @@ void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CP= URISCVState *env, uint32_t vta =3D vext_vta(desc); uint32_t total_elems =3D vext_get_total_elems(env, desc, 4); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart / 4; i < env->vl / 4; i++) { uint64_t Y[2] =3D {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])}; uint64_t H[2] =3D {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])}; @@ -853,6 +879,8 @@ void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uim= m5, CPURISCVState *env, uint32_t esz =3D sizeof(uint32_t); uint32_t total_elems =3D vext_get_total_elems(env, desc, esz); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D group_start; i < group_end; ++i) { uint32_t vstart =3D i * egs; uint32_t vend =3D (i + 1) * egs; @@ -909,6 +937,8 @@ void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVStat= e *env, uint32_t desc) uint32_t esz =3D sizeof(uint32_t); uint32_t total_elems =3D vext_get_total_elems(env, desc, esz); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D group_start; i < group_end; ++i) { uint32_t vstart =3D i * egs; uint32_t vend =3D (i + 1) * egs; @@ -943,6 +973,8 @@ void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVStat= e *env, uint32_t desc) uint32_t esz =3D sizeof(uint32_t); uint32_t total_elems =3D vext_get_total_elems(env, desc, esz); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D group_start; i < group_end; ++i) { uint32_t vstart =3D i * egs; uint32_t vend =3D (i + 1) * egs; diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index cd8235ea98..48d041dd4e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -207,6 +207,8 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, uint32_t esz =3D 1 << log2_esz; uint32_t vma =3D vext_vma(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { k =3D 0; while (k < nf) { @@ -272,6 +274,8 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState= *env, uint32_t desc, uint32_t max_elems =3D vext_max_elems(desc, log2_esz); uint32_t esz =3D 1 << log2_esz; =20 + VSTART_CHECK_EARLY_EXIT(env); + /* load bytes from guest memory */ for (i =3D env->vstart; i < evl; i++, env->vstart++) { k =3D 0; @@ -386,6 +390,8 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t esz =3D 1 << log2_esz; uint32_t vma =3D vext_vma(desc); =20 + VSTART_CHECK_EARLY_EXIT(env); + /* load bytes from guest memory */ for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { k =3D 0; @@ -477,6 +483,8 @@ vext_ldff(void *vd, void *v0, target_ulong base, target_ulong addr, offset, remain; int mmu_index =3D riscv_env_mmu_index(env, false); =20 + VSTART_CHECK_EARLY_EXIT(env); + /* probe every access */ for (i =3D env->vstart; i < env->vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -572,6 +580,8 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVSt= ate *env, uint32_t desc, uint32_t vlenb =3D riscv_cpu_cfg(env)->vlenb; uint32_t max_elems =3D vlenb >> log2_esz; =20 + VSTART_CHECK_EARLY_EXIT(env); + k =3D env->vstart / max_elems; off =3D env->vstart % max_elems; =20 @@ -877,6 +887,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *= vs2, \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ @@ -909,6 +921,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, = void *vs2, \ uint32_t vta =3D vext_vta(desc); = \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); = \ ETYPE carry =3D vext_elem_mask(v0, i); = \ @@ -944,6 +958,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *= vs2, \ uint32_t vta_all_1s =3D vext_vta_all_1s(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ @@ -982,6 +998,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, = \ uint32_t vta_all_1s =3D vext_vta_all_1s(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ ETYPE carry =3D !vm && vext_elem_mask(v0, i); \ @@ -1078,6 +1096,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t vma =3D vext_vma(desc); = \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -1125,6 +1145,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -1187,6 +1209,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void= *vs2, \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ @@ -1252,6 +1276,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , void *vs2, \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -1799,6 +1825,8 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState = *env, \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ *((ETYPE *)vd + H(i)) =3D s1; \ @@ -1823,6 +1851,8 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVStat= e *env, \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ *((ETYPE *)vd + H(i)) =3D (ETYPE)s1; \ } \ @@ -1846,6 +1876,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void= *vs2, \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE *vt =3D (!vext_elem_mask(v0, i) ? vs2 : vs1); \ *((ETYPE *)vd + H(i)) =3D *(vt + H(i)); \ @@ -1870,6 +1902,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ ETYPE d =3D (!vext_elem_mask(v0, i) ? s2 : \ @@ -1915,6 +1949,8 @@ vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2, uint32_t vl, uint32_t vm, int vxrm, opivv2_rm_fn *fn, uint32_t vma, uint32_t esz) { + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -2040,6 +2076,8 @@ vext_vx_rm_1(void *vd, void *v0, target_long s1, void= *vs2, uint32_t vl, uint32_t vm, int vxrm, opivx2_rm_fn *fn, uint32_t vma, uint32_t esz) { + VSTART_CHECK_EARLY_EXIT(env); + for (uint32_t i =3D env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -2837,6 +2875,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -2880,6 +2920,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, = \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -3466,6 +3508,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ if (vl =3D=3D 0) { \ return; \ } \ @@ -3987,6 +4031,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void= *vs2, \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ @@ -4027,6 +4073,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, vo= id *vs2, \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4220,6 +4268,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, vo= id *vs2, \ uint32_t vta =3D vext_vta(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ *((ETYPE *)vd + H(i)) =3D \ @@ -4386,6 +4436,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t i; \ TD s1 =3D *((TD *)vs1 + HD(0)); \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ TS2 s2 =3D *((TS2 *)vs2 + HS2(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4472,6 +4524,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t i; \ TD s1 =3D *((TD *)vs1 + HD(0)); \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ TS2 s2 =3D *((TS2 *)vs2 + HS2(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4544,6 +4598,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t i; \ int a, b; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ a =3D vext_elem_mask(vs1, i); \ b =3D vext_elem_mask(vs2, i); \ @@ -4585,6 +4641,11 @@ target_ulong HELPER(vcpop_m)(void *v0, void *vs2, CP= URISCVState *env, uint32_t vl =3D env->vl; int i; =20 + if (env->vstart >=3D env->vl) { + env->vstart =3D 0; + return 0; + } + for (i =3D env->vstart; i < vl; i++) { if (vm || vext_elem_mask(v0, i)) { if (vext_elem_mask(vs2, i)) { @@ -4604,6 +4665,11 @@ target_ulong HELPER(vfirst_m)(void *v0, void *vs2, C= PURISCVState *env, uint32_t vl =3D env->vl; int i; =20 + if (env->vstart >=3D env->vl) { + env->vstart =3D 0; + return 0; + } + for (i =3D env->vstart; i < vl; i++) { if (vm || vext_elem_mask(v0, i)) { if (vext_elem_mask(vs2, i)) { @@ -4632,6 +4698,8 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPU= RISCVState *env, int i; bool first_mask_bit =3D false; =20 + VSTART_CHECK_EARLY_EXIT(env); + for (i =3D env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -4704,6 +4772,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, CPUR= ISCVState *env, \ uint32_t sum =3D 0; = \ int i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -4737,6 +4807,8 @@ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *= env, uint32_t desc) \ uint32_t vma =3D vext_vma(desc); = \ int i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -4772,6 +4844,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , void *vs2, \ uint32_t vma =3D vext_vma(desc); = \ target_ulong offset =3D s1, i_min, i; = \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ i_min =3D MAX(env->vstart, offset); = \ for (i =3D i_min; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ @@ -4805,6 +4879,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , void *vs2, \ uint32_t vma =3D vext_vma(desc); = \ target_ulong i_max, i_min, i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ i_min =3D MIN(s1 < vlmax ? vlmax - s1 : 0, vl); = \ i_max =3D MAX(i_min, env->vstart); = \ for (i =3D env->vstart; i < i_max; ++i) { = \ @@ -4847,6 +4923,8 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0, = uint64_t s1, \ uint32_t vma =3D vext_vma(desc); = \ uint32_t i; = \ = \ + VSTART_CHECK_EARLY_EXIT(env); = \ + = \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { = \ /* set masked-off elements to 1s */ = \ @@ -4896,6 +4974,8 @@ static void vslide1down_##BITWIDTH(void *vd, void *v0= , uint64_t s1, \ uint32_t vma =3D vext_vma(desc); = \ uint32_t i; = \ = \ + VSTART_CHECK_EARLY_EXIT(env); = \ + = \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { = \ /* set masked-off elements to 1s */ = \ @@ -4971,6 +5051,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void= *vs2, \ uint64_t index; \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -5014,6 +5096,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1= , void *vs2, \ uint64_t index =3D s1; = \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ @@ -5048,6 +5132,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void= *vs2, \ uint32_t vta =3D vext_vta(desc); = \ uint32_t num =3D 0, i; = \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { = \ if (!vext_elem_mask(vs1, i)) { \ continue; \ @@ -5100,6 +5186,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internal= s.c index 12f5964fbb..996c21eb31 100644 --- a/target/riscv/vector_internals.c +++ b/target/riscv/vector_internals.c @@ -44,6 +44,8 @@ void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, uint32_t vma =3D vext_vma(desc); uint32_t i; =20 + VSTART_CHECK_EARLY_EXIT(env); + for (i =3D env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ @@ -68,6 +70,8 @@ void do_vext_vx(void *vd, void *v0, target_long s1, void = *vs2, uint32_t vma =3D vext_vma(desc); uint32_t i; =20 + VSTART_CHECK_EARLY_EXIT(env); + for (i =3D env->vstart; i < vl; i++) { if (!vm && !vext_elem_mask(v0, i)) { /* set masked-off elements to 1s */ diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internal= s.h index 842765f6c1..9e1e15b575 100644 --- a/target/riscv/vector_internals.h +++ b/target/riscv/vector_internals.h @@ -24,6 +24,13 @@ #include "tcg/tcg-gvec-desc.h" #include "internals.h" =20 +#define VSTART_CHECK_EARLY_EXIT(env) do { \ + if (env->vstart >=3D env->vl) { \ + env->vstart =3D 0; \ + return; \ + } \ +} while (0) + static inline uint32_t vext_nf(uint32_t desc) { return FIELD_EX32(simd_data(desc), VDATA, NF); @@ -151,6 +158,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ + VSTART_CHECK_EARLY_EXIT(env); \ + \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ /* set masked-off elements to 1s */ \ --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367368; cv=none; d=zohomail.com; s=zohoarc; b=bZQzUNSsulUVCSYN7Euj/4OsBK9CcACYxdpOTRPylDikOmJnoqtBCEpczfEtmow2TTGZPisYXrFh+mRFDt06HcmyKcHAP7lKNmMa02Y3C0CQBtNXZ/z1BK1JzEKr6s76926NoN9zkbUBfvEm3WWl+Sj+I2DzNFOIotSsHbmJRIY= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367368; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=WAQtiEYaEmXoE54cweN4qIPvZeaMFXARcRJhZYrN3gg=; b=OYdQVDr0H77xeSnmWbPabfRERGZyUMpwRRgWcrNB8iWz6HAeESURHNnAzSdVOjFBUN7TMbOwihZlQuzia6eeIBGB1hGqxb78tKG61RNLD1MUMoCO8fsV2h5zukT95EA/qGw/kkKf5lUQojAqP40aM+QTCJkl4woHvI87uZju8aw= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367368739904.5471011129702; Wed, 13 Mar 2024 15:02:48 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWgF-0007TB-FL; Wed, 13 Mar 2024 18:02:37 -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 1rkWfr-0007OV-Pf for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:13 -0400 Received: from mail-oa1-x34.google.com ([2001:4860:4864:20::34]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfm-0004JC-NY for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:11 -0400 Received: by mail-oa1-x34.google.com with SMTP id 586e51a60fabf-221960e3edcso165203fac.0 for ; Wed, 13 Mar 2024 15:02:06 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.02.01 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:02:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367325; x=1710972125; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=WAQtiEYaEmXoE54cweN4qIPvZeaMFXARcRJhZYrN3gg=; b=L53bTzlGH8Ufc/y/v1ONE5Y7S8YaHTclSpFu8Ji7atV5I+p2vcvopV4MNX8zKQiNuA W09eI7f9ikSGHN1oj1WxWpgMoKB7TIe9cW+6co1WLZ4NFt29IggTvtDwU3JPxit2XnrX ZYTksvyD283qNNWm4RwgoRswPHk4Jzsw+3AR7vI/AMXpgm9OIX/mrodPqUbVq3VsnerR x0bmc85YOTKP8XfGGL8J5xxT/Rk9wrbSC7/b33GZfcOdr6yxNtEXe8kT9oGGxGkOPp0R mUCpBj6EuXGMKpBuhAVO/wcKm/bKJU0mlrWS9vZMiBeKj9nCtgh3uEePvDg513VisjHC m2kg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367325; x=1710972125; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=WAQtiEYaEmXoE54cweN4qIPvZeaMFXARcRJhZYrN3gg=; b=WdNghAyigqsE/Y0tgE1VVSQdi8uBatJt4JA2dTO9xgeYCC0swCVJ/ZB9k581JXGkzZ 8EWfewyV13MtcUQfFGaZoXlDoALL4ViR3AVpn269jkIOhLyQ2O5tE2gvsnKhwlEH+pd/ NHXzwII/HWsYMIJNx5f481kLv3rVIktcS4aRWKXHlAhQt6gnTl/Pl7l5urb0XP0pOL0+ HfCHr8N2WlM4omS6H8kVQqMWc05a+diDOeMJ93ykbZcZaRh51MAPw/bqcBxYP4J7J7HI uY+OMr+SCXsNEZa3W46jRDbxocij47P7bkQjEuPz30VL+qIuFjpeOTww/feXNSkMZ3fb A/kA== X-Gm-Message-State: AOJu0YyxjHlRlS279fKKR+G78GZvA1hNaBA5otGwyebxh8eLWr4BcvC8 plwfXYdX0QPQLdQEJQv+0yJYBqx0TTc257bX5oHvnBIlsP3+GF8MZD8OGTMGqpoSHyAOZQe7+nX C X-Google-Smtp-Source: AGHT+IHQaHJl3IPmnfiQyAuqMmK5eAE1SOgu75WuBFU5uMdDKPEiXt0G11Zi7QPMvMv+PE9yZC5TgA== X-Received: by 2002:a05:6870:c093:b0:219:7981:30c0 with SMTP id c19-20020a056870c09300b00219798130c0mr124721oad.19.1710367324524; Wed, 13 Mar 2024 15:02:04 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 5/8] target/riscv: remove 'over' brconds from vector trans Date: Wed, 13 Mar 2024 19:01:38 -0300 Message-ID: <20240313220141.427730-6-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2001:4860:4864:20::34; envelope-from=dbarboza@ventanamicro.com; helo=mail-oa1-x34.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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367369336100003 Content-Type: text/plain; charset="utf-8" The previous patch added an early vstart >=3D vl exit in all vector helpers, most of them using the VSTART_CHECK_EARLY_EXIT() macro, and now we're left with a lot of 'brcond' that has not use. The pattern goes like this: VSTART_CHECK_EARLY_EXIT(env); (...) tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); (...) gen_set_label(over); return true; The early exit makes the 'brcond' unneeded since it's already granted that vstart < vl. Remove all 'over' conditionals from the vector helpers. Note that not all insns uses helpers, and for those cases the 'brcond' jump is the only way to filter vstart >=3D vl. This is the case of trans_vmv_s_x() and trans_vfmv_s_f(). We won't remove the 'brcond' conditionals from them. While we're at it, remove the (vl =3D=3D 0) brconds from trans_rvbf16.c.inc too since they're unneeded. Suggested-by: Richard Henderson Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvbf16.c.inc | 12 --- target/riscv/insn_trans/trans_rvv.c.inc | 105 --------------------- target/riscv/insn_trans/trans_rvvk.c.inc | 18 ---- 3 files changed, 135 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvbf16.c.inc b/target/riscv/insn= _trans/trans_rvbf16.c.inc index 8ee99df3f3..a842e76a6b 100644 --- a/target/riscv/insn_trans/trans_rvbf16.c.inc +++ b/target/riscv/insn_trans/trans_rvbf16.c.inc @@ -71,11 +71,8 @@ static bool trans_vfncvtbf16_f_f_w(DisasContext *ctx, ar= g_vfncvtbf16_f_f_w *a) =20 if (opfv_narrow_check(ctx, a) && (ctx->sew =3D=3D MO_16)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); =20 gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, ctx->lmul); @@ -87,7 +84,6 @@ static bool trans_vfncvtbf16_f_f_w(DisasContext *ctx, arg= _vfncvtbf16_f_f_w *a) ctx->cfg_ptr->vlenb, data, gen_helper_vfncvtbf16_f_f_w); mark_vs_dirty(ctx); - gen_set_label(over); return true; } return false; @@ -100,11 +96,8 @@ static bool trans_vfwcvtbf16_f_f_v(DisasContext *ctx, a= rg_vfwcvtbf16_f_f_v *a) =20 if (opfv_widen_check(ctx, a) && (ctx->sew =3D=3D MO_16)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); =20 gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, ctx->lmul); @@ -116,7 +109,6 @@ static bool trans_vfwcvtbf16_f_f_v(DisasContext *ctx, a= rg_vfwcvtbf16_f_f_v *a) ctx->cfg_ptr->vlenb, data, gen_helper_vfwcvtbf16_f_f_v); mark_vs_dirty(ctx); - gen_set_label(over); return true; } return false; @@ -130,11 +122,8 @@ static bool trans_vfwmaccbf16_vv(DisasContext *ctx, ar= g_vfwmaccbf16_vv *a) if (require_rvv(ctx) && vext_check_isa_ill(ctx) && (ctx->sew =3D=3D MO= _16) && vext_check_dss(ctx, a->rd, a->rs1, a->rs2, a->vm)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); =20 gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, ctx->lmul); @@ -147,7 +136,6 @@ static bool trans_vfwmaccbf16_vv(DisasContext *ctx, arg= _vfwmaccbf16_vv *a) ctx->cfg_ptr->vlenb, data, gen_helper_vfwmaccbf16_vv); mark_vs_dirty(ctx); - gen_set_label(over); return true; } return false; diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index 52c26a7834..4c1a064cf6 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -616,9 +616,6 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, ui= nt32_t data, TCGv base; TCGv_i32 desc; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); base =3D get_gpr(s, rs1, EXT_NONE); @@ -660,7 +657,6 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, ui= nt32_t data, tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } =20 - gen_set_label(over); return true; } =20 @@ -802,9 +798,6 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1= , uint32_t rs2, TCGv base, stride; TCGv_i32 desc; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); base =3D get_gpr(s, rs1, EXT_NONE); @@ -819,7 +812,6 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1= , uint32_t rs2, =20 fn(dest, mask, base, stride, tcg_env, desc); =20 - gen_set_label(over); return true; } =20 @@ -906,9 +898,6 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1,= uint32_t vs2, TCGv base; TCGv_i32 desc; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); index =3D tcg_temp_new_ptr(); @@ -924,7 +913,6 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1,= uint32_t vs2, =20 fn(dest, mask, base, index, tcg_env, desc); =20 - gen_set_label(over); return true; } =20 @@ -1044,9 +1032,6 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uin= t32_t data, TCGv base; TCGv_i32 desc; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); base =3D get_gpr(s, rs1, EXT_NONE); @@ -1059,7 +1044,6 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uin= t32_t data, fn(dest, mask, base, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -1100,10 +1084,6 @@ static bool ldst_whole_trans(uint32_t vd, uint32_t r= s1, uint32_t nf, uint32_t width, gen_helper_ldst_whole *fn, DisasContext *s) { - uint32_t evl =3D s->cfg_ptr->vlenb * nf / width; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_GEU, cpu_vstart, evl, over); - TCGv_ptr dest; TCGv base; TCGv_i32 desc; @@ -1120,8 +1100,6 @@ static bool ldst_whole_trans(uint32_t vd, uint32_t rs= 1, uint32_t nf, =20 fn(dest, base, tcg_env, desc); =20 - gen_set_label(over); - return true; } =20 @@ -1195,10 +1173,6 @@ static inline bool do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn, gen_helper_gvec_4_ptr *fn) { - TCGLabel *over =3D gen_new_label(); - - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1), @@ -1216,7 +1190,6 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3F= n *gvec_fn, s->cfg_ptr->vlenb, data, fn); } mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -1248,9 +1221,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, uint32_t vm, TCGv_i32 desc; uint32_t data =3D 0; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); src2 =3D tcg_temp_new_ptr(); @@ -1271,7 +1241,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, uint32_t vm, fn(dest, mask, src1, src2, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -1410,9 +1379,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, ui= nt32_t vs2, uint32_t vm, TCGv_i32 desc; uint32_t data =3D 0; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); src2 =3D tcg_temp_new_ptr(); @@ -1433,7 +1399,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, ui= nt32_t vs2, uint32_t vm, fn(dest, mask, src1, src2, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -1495,8 +1460,6 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr = *a, { if (checkfn(s, a)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -1509,7 +1472,6 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr = *a, s->cfg_ptr->vlenb, data, fn); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -1571,8 +1533,6 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr = *a, { if (opiwv_widen_check(s, a)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -1584,7 +1544,6 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr = *a, tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -1643,8 +1602,6 @@ static bool opivv_trans(uint32_t vd, uint32_t vs1, ui= nt32_t vs2, uint32_t vm, gen_helper_gvec_4_ptr *fn, DisasContext *s) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -1655,7 +1612,6 @@ static bool opivv_trans(uint32_t vd, uint32_t vs1, ui= nt32_t vs2, uint32_t vm, vreg_ofs(s, vs2), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -1834,8 +1790,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -1848,7 +1802,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2045,14 +1998,11 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_= v_v *a) gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h, gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d, }; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fns[s->sew]); - gen_set_label(over); } mark_vs_dirty(s); return true; @@ -2068,8 +2018,6 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_= x *a) /* vmv.v.x has rs2 =3D 0 and vm =3D 1 */ vext_check_ss(s, a->rd, 0, 1)) { TCGv s1; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 s1 =3D get_gpr(s, a->rs1, EXT_SIGN); =20 @@ -2102,7 +2050,6 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_= x *a) } =20 mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -2129,8 +2076,6 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_= i *a) gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h, gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, }; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 s1 =3D tcg_constant_i64(simm); dest =3D tcg_temp_new_ptr(); @@ -2140,7 +2085,6 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_= i *a) fns[s->sew](dest, s1, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); } return true; } @@ -2275,9 +2219,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ gen_helper_##NAME##_w, \ gen_helper_##NAME##_d, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2292,7 +2234,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2310,9 +2251,6 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, TCGv_i32 desc; TCGv_i64 t1; =20 - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); - dest =3D tcg_temp_new_ptr(); mask =3D tcg_temp_new_ptr(); src2 =3D tcg_temp_new_ptr(); @@ -2330,7 +2268,6 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, fn(dest, mask, t1, src2, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } =20 @@ -2393,9 +2330,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ static gen_helper_gvec_4_ptr * const fns[2] =3D { \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2408,7 +2343,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2467,9 +2401,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ static gen_helper_gvec_4_ptr * const fns[2] =3D { \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2482,7 +2414,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2584,9 +2515,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a, { if (checkfn(s, a)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); gen_set_rm_chkfrm(s, rm); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -2597,7 +2526,6 @@ static bool do_opfv(DisasContext *s, arg_rmr *a, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -2696,8 +2624,6 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, }; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 t1 =3D tcg_temp_new_i64(); /* NaN-box f[rs1] */ @@ -2711,7 +2637,6 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) fns[s->sew - 1](dest, t1, tcg_env, desc); =20 mark_vs_dirty(s); - gen_set_label(over); } return true; } @@ -2773,9 +2698,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ gen_helper_##HELPER##_h, \ gen_helper_##HELPER##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2787,7 +2710,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2824,9 +2746,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm(s, RISCV_FRM_DYN); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2838,7 +2758,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2891,9 +2810,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ gen_helper_##HELPER##_h, \ gen_helper_##HELPER##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2905,7 +2822,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -2940,9 +2856,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ gen_helper_##HELPER##_h, \ gen_helper_##HELPER##_w, \ }; \ - TCGLabel *over =3D gen_new_label(); \ gen_set_rm_chkfrm(s, FRM); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -2954,7 +2868,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -3031,8 +2944,6 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) = \ vext_check_isa_ill(s)) { \ uint32_t data =3D 0; \ gen_helper_gvec_4_ptr *fn =3D gen_helper_##NAME; \ - TCGLabel *over =3D gen_new_label(); \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D \ @@ -3043,7 +2954,6 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) = \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, fn); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -3131,8 +3041,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->vstart_eq_zero) { \ uint32_t data =3D 0; \ gen_helper_gvec_3_ptr *fn =3D gen_helper_##NAME; \ - TCGLabel *over =3D gen_new_label(); \ - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ @@ -3145,7 +3053,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, \ data, fn); \ mark_vs_dirty(s); \ - gen_set_label(over); \ return true; \ } \ return false; \ @@ -3171,8 +3078,6 @@ static bool trans_viota_m(DisasContext *s, arg_viota_= m *a) require_align(a->rd, s->lmul) && s->vstart_eq_zero) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -3187,7 +3092,6 @@ static bool trans_viota_m(DisasContext *s, arg_viota_= m *a) s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fns[s->sew]); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -3201,8 +3105,6 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) require_align(a->rd, s->lmul) && require_vm(a->vm, a->rd)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -3217,7 +3119,6 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) s->cfg_ptr->vlenb, data, fns[s->sew]); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -3630,8 +3531,6 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r= *a) gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h, gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d, }; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); =20 data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); data =3D FIELD_DP32(data, VDATA, VTA, s->vta); @@ -3641,7 +3540,6 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r= *a) s->cfg_ptr->vlenb, data, fns[s->sew]); mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -3695,8 +3593,6 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, u= int8_t seq) { uint32_t data =3D 0; gen_helper_gvec_3_ptr *fn; - TCGLabel *over =3D gen_new_label(); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); =20 static gen_helper_gvec_3_ptr * const fns[6][4] =3D { { @@ -3741,7 +3637,6 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, u= int8_t seq) s->cfg_ptr->vlenb, data, fn); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } =20 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_t= rans/trans_rvvk.c.inc index a5cdd1b67f..6d640e4596 100644 --- a/target/riscv/insn_trans/trans_rvvk.c.inc +++ b/target/riscv/insn_trans/trans_rvvk.c.inc @@ -164,8 +164,6 @@ GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvkb_vx_che= ck) gen_helper_##NAME##_w, = \ gen_helper_##NAME##_d, = \ }; = \ - TCGLabel *over =3D gen_new_label(); = \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); = \ = \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); = \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); = \ @@ -177,7 +175,6 @@ GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvkb_vx_che= ck) s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, = \ data, fns[s->sew]); = \ mark_vs_dirty(s); = \ - gen_set_label(over); = \ return true; = \ } = \ return false; = \ @@ -249,14 +246,12 @@ GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vws= ll_vx_check) TCGv_ptr rd_v, rs2_v; = \ TCGv_i32 desc, egs; = \ uint32_t data =3D 0; = \ - TCGLabel *over =3D gen_new_label(); = \ = \ if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { = \ /* save opcode for unwinding in case we throw an exception= */ \ decode_save_opc(s); = \ egs =3D tcg_constant_i32(EGS); = \ gen_helper_egs_check(egs, tcg_env); = \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);= \ } = \ = \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); = \ @@ -272,7 +267,6 @@ GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll= _vx_check) tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); = \ gen_helper_##NAME(rd_v, rs2_v, tcg_env, desc); = \ mark_vs_dirty(s); = \ - gen_set_label(over); = \ return true; = \ } = \ return false; = \ @@ -325,14 +319,12 @@ GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED= _EGS) TCGv_ptr rd_v, rs2_v; = \ TCGv_i32 uimm_v, desc, egs; = \ uint32_t data =3D 0; = \ - TCGLabel *over =3D gen_new_label(); = \ = \ if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { = \ /* save opcode for unwinding in case we throw an exception= */ \ decode_save_opc(s); = \ egs =3D tcg_constant_i32(EGS); = \ gen_helper_egs_check(egs, tcg_env); = \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);= \ } = \ = \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); = \ @@ -350,7 +342,6 @@ GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED_E= GS) tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); = \ gen_helper_##NAME(rd_v, rs2_v, uimm_v, tcg_env, desc); = \ mark_vs_dirty(s); = \ - gen_set_label(over); = \ return true; = \ } = \ return false; = \ @@ -394,7 +385,6 @@ GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED= _EGS) { = \ if (CHECK(s, a)) { = \ uint32_t data =3D 0; = \ - TCGLabel *over =3D gen_new_label(); = \ TCGv_i32 egs; = \ = \ if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { = \ @@ -402,7 +392,6 @@ GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED= _EGS) decode_save_opc(s); = \ egs =3D tcg_constant_i32(EGS); = \ gen_helper_egs_check(egs, tcg_env); = \ - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);= \ } = \ = \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); = \ @@ -417,7 +406,6 @@ GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED= _EGS) data, gen_helper_##NAME); = \ = \ mark_vs_dirty(s); = \ - gen_set_label(over); = \ return true; = \ } = \ return false; = \ @@ -448,7 +436,6 @@ static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr = *a) { if (vsha_check(s, a)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); TCGv_i32 egs; =20 if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { @@ -456,7 +443,6 @@ static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr = *a) decode_save_opc(s); egs =3D tcg_constant_i32(ZVKNH_EGS); gen_helper_egs_check(egs, tcg_env); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); } =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); @@ -472,7 +458,6 @@ static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr = *a) gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } return false; @@ -482,7 +467,6 @@ static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr = *a) { if (vsha_check(s, a)) { uint32_t data =3D 0; - TCGLabel *over =3D gen_new_label(); TCGv_i32 egs; =20 if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { @@ -490,7 +474,6 @@ static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr = *a) decode_save_opc(s); egs =3D tcg_constant_i32(ZVKNH_EGS); gen_helper_egs_check(egs, tcg_env); - tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); } =20 data =3D FIELD_DP32(data, VDATA, VM, a->vm); @@ -506,7 +489,6 @@ static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr = *a) gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv); =20 mark_vs_dirty(s); - gen_set_label(over); return true; } return false; --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367399; cv=none; d=zohomail.com; s=zohoarc; b=lmvq76XKCR8Z+pJ0dGX4mQl60XZgsy7YL4QeHElkBzN/t6nQ/gyf/32XE0L0mNPokyQ8umtC56UqEbfDAhP3ku3+WywdwTXIjNDsW6H1FKac7eRTDFzSRuzzQVTYxPEEoACLlWYio+mLQUVIkeiODak1YHPUBusPP957I6eYmvo= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367399; h=Content-Type:Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=M1pgxbL4ext+eLfj8GE9V3VngjTMGW2LA/FcQ0QZgQg=; b=L1HGODelvPfIURgIaAuspt3LRHerHOaoLjMKoHnFow6yIAJ0aB9tYMNLMRnP0oB58M0NQnmbbQd5fxGS19tGuWQ9k/qzdIEwHjn+FvgdBZ8FG2c9CU6bG9IpM1I/RR1x101p7K/4QW3K3dqp1+z6Q9XWjbC2Itgb3gJuISFSrrw= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367399424833.346136746246; Wed, 13 Mar 2024 15:03:19 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWgK-0007VJ-HY; Wed, 13 Mar 2024 18:02:41 -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 1rkWfr-0007OX-RX for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:13 -0400 Received: from mail-pf1-x434.google.com ([2607:f8b0:4864:20::434]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfq-0004JT-5P for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:11 -0400 Received: by mail-pf1-x434.google.com with SMTP id d2e1a72fcca58-6e6bee809b8so373892b3a.1 for ; Wed, 13 Mar 2024 15:02:09 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.02.04 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:02:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367328; x=1710972128; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=M1pgxbL4ext+eLfj8GE9V3VngjTMGW2LA/FcQ0QZgQg=; b=hpuWcTMFzrBRzzh2zoD79qVKHxVr/w9Dw4qdcbr5C9lB0rAO9sOFdbbxpAkKOI/rrC 4NjAopwLUaP1VC9nUBsrzjq2V0ellK1ucIZm06WwWZlrZOKZjnmIXMFLqGZK8EUPCMEO xpLItscv/jhIRIYxMnjA39H3C6yA3BmcSKMJXvLAiIoYMVw1k/kQg1uVo9l7SpFLaruk toNOeOFnbOhSUfZslfR8ZzI7K3L6KZRIY0goss8fevG+BO87hQ5NrwWeNh6HbCBBYLi0 vq153eROtO6l/pThHuYIFjXE5wyCH9nNNqQb0pcaChO6K9aJ9kNS6YuKaNxdcReVcEBy CMtA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367328; x=1710972128; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=M1pgxbL4ext+eLfj8GE9V3VngjTMGW2LA/FcQ0QZgQg=; b=YLVXmtj0sQ86sqzZhFvW1H3I5YFQB2KmVYpvYJ42z++0t0+4kdmy+SLkidUwU2J39R qPD+S2BSBhrEkF60K8rK7coXqnWassq7GBX6NGstOTZ7znST/kZhAWkDLcODAM2Tnctf JsSCZLvQ2YktmpYjewljMuY5uMLuQecGp9Wq2zoxYBhEZeyBqWSJGvaYEK4l7tauo3EH yais5PpQX53uxEJZ+3tUr3ZPCmOHW+WBe0yfPsBL0xWCaD+SWeg53ILSpBUy6+mOQsmb 5pHWjfIkTvG6NHofAMMDjLDWADEa6ohM3iUrtNAyZyM5FIjfOTAP8dCMvb6xzJ3HHJaa htrQ== X-Gm-Message-State: AOJu0YwhEAfEAqkkHQ7uEGLgxF9smVPaR8qPEypWhGFJpxLlUGfLbF92 QTcLsgfp65yEu7MDIoKTkdGigkfA4Gg2KznMc8f5CqKSV/xMx6ZEj95z2zNUSkkbzH6stxc9Z0Z H X-Google-Smtp-Source: AGHT+IGp/Ln0kwRIHpnc6obWnua89IWtM3mpNckKU/0OTEFw8CCNOy+L4CP2xmYDa9z0crLdcdqO+g== X-Received: by 2002:a05:6a00:3901:b0:6e6:5343:c165 with SMTP id fh1-20020a056a00390100b006e65343c165mr23688pfb.16.1710367327972; Wed, 13 Mar 2024 15:02:07 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 6/8] trans_rvv.c.inc: remove redundant mark_vs_dirty() calls Date: Wed, 13 Mar 2024 19:01:39 -0300 Message-ID: <20240313220141.427730-7-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::434; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367401062100003 trans_vmv_v_i , trans_vfmv_v_f and the trans_##NAME macro from GEN_VMV_WHOLE_TRANS() are calling mark_vs_dirty() in both branches of their 'ifs'. conditionals. Call it just once in the end like other functions are doing. Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis Reviewed-by: Philippe Mathieu-Daud=C3=A9 --- target/riscv/insn_trans/trans_rvv.c.inc | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index 4c1a064cf6..b0f19dcd85 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -2065,7 +2065,6 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_= i *a) if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), simm); - mark_vs_dirty(s); } else { TCGv_i32 desc; TCGv_i64 s1; @@ -2083,9 +2082,8 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_= i *a) s->cfg_ptr->vlenb, data)); tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd)); fns[s->sew](dest, s1, tcg_env, desc); - - mark_vs_dirty(s); } + mark_vs_dirty(s); return true; } return false; @@ -2612,7 +2610,6 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) =20 tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), t1); - mark_vs_dirty(s); } else { TCGv_ptr dest; TCGv_i32 desc; @@ -2635,9 +2632,8 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd)); =20 fns[s->sew - 1](dest, t1, tcg_env, desc); - - mark_vs_dirty(s); } + mark_vs_dirty(s); return true; } return false; @@ -3560,12 +3556,11 @@ static bool trans_##NAME(DisasContext *s, arg_##NAM= E * a) \ if (s->vstart_eq_zero) { \ tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd), \ vreg_ofs(s, a->rs2), maxsz, maxsz); \ - mark_vs_dirty(s); \ } else { \ tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), \ tcg_env, maxsz, maxsz, 0, gen_helper_vmvr_v= ); \ - mark_vs_dirty(s); \ } \ + mark_vs_dirty(s); \ return true; \ } \ return false; \ --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367413; cv=none; d=zohomail.com; s=zohoarc; b=DeYuCyzwcUZq4Gb5YwZ5Gz0Cq/KsiQgeDa63aTnZzcQgrI+97lAPpClM9529ZUugbRUPUTHX9SF0SAdzqYycjznFOWTuhUzO4DkMNoTepToRqpY58S8Lw+nLXz3URx9ZF0Hjyw2qVHlBwCQRScid69Be3oLbaxG7+DT+mnbQkps= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367413; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=+XA5ffEo8To2rVDIbAWsqAEMLNL3+D/BqqOB3honEjw=; b=CwnwNDA0/Lmu9VMp4T2XJIXMzuOabL0AJ0xPSoQddVhtLC8x59nSGgbg4uM8iSKA05+Km16M9cbNqdog6j96AJsQexQicaoY/mN/qVEiWEopdaq7y4nr23aqSWHNe2unxn2cC32qrhqMyWG7cKlAw/GPwKFOTvfOUrhnF4KO138= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367413237362.6981251726161; Wed, 13 Mar 2024 15:03:33 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWgh-00081p-UN; Wed, 13 Mar 2024 18:03:05 -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 1rkWg2-0007RX-8a for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:29 -0400 Received: from mail-oa1-x34.google.com ([2001:4860:4864:20::34]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWft-0004KM-Ff for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:19 -0400 Received: by mail-oa1-x34.google.com with SMTP id 586e51a60fabf-2218a0f55e1so243230fac.1 for ; Wed, 13 Mar 2024 15:02:13 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.02.08 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:02:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367331; x=1710972131; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=+XA5ffEo8To2rVDIbAWsqAEMLNL3+D/BqqOB3honEjw=; b=HVS8qnP8cGGcB9po1CAX2yA+O6VzknzoSBKWfb9co1qLU9MzQfanWeXEaPuNDNPPZn 1f/zjwm2jIyRangyqMygHmWLy1n7Jw1n+kpnUEgvZ42pTHH4A8tdVMxNL3jxDfYpVoM+ RmIHuXHYkD6jZk1rXF45xw88SnxLmt4crXHq5NpRq+R5ZyLaftrmBrxJbZ/sOrZhqfvf TH85D/LLORSzJPodfyw/p822WA/S3bvGMhp4/OirQ1/RI3S4L5emKz6NpVwFrBmk1XQK XaUvl8mm9qGOK6lBxdqL3/+LTRW6WA09GOcuOxvwZdvsj1GC2Kjjz86RJOTrdyIimAHt 2Z7g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367331; x=1710972131; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=+XA5ffEo8To2rVDIbAWsqAEMLNL3+D/BqqOB3honEjw=; b=jlgCd9GuL7UCNU9cSxR5zYfp5IgJINgA2j/0ZAotP2EAsU3ZR1U3otI0/d8QitXrX5 TTuuyMt/WIBLLndigxxtZtuCX/5VcTcNVNHyvTPJmnftcaRQD7r63/wAkY7jrEktjT3j s8OPNAJeqrCGk26/LLZtYit36OuraojiZSOrRBffqJjXN3UcBxkPTkiogN7UeSjW73lo sN+hxyHIcw7DrMgJr4E98TybngxwgHhUAzOzhn11GFHGhp4ub6GtpQ07WFOzDvg51bDM WShy8w/80JFtGsyNaW0F0dRRGXI7oDxsWhox4IP/53DdNXROZdogOnHe705n55rAH7l9 4hXQ== X-Gm-Message-State: AOJu0YxlXL/oEG/WirH42L0plZvbVQZXC9o6+2/oBlZ0gzGZV2Yryiwc w9GvAyzsbBfJgUhaRNf4L9Q9EAbW7hpeOyVMDyGMGKr/ZNCoOmKA/HHvyu0f98jEXFGqJT3f2u2 8 X-Google-Smtp-Source: AGHT+IEhKI1z4JFGgu8R0fCGhealzxZ8jyUDvsUkbgaGn5IuQGUA6Gpj7Zf3GO3JmrHOsyLrQJpIrA== X-Received: by 2002:a05:6871:554:b0:221:14d4:6ab9 with SMTP id t20-20020a056871055400b0022114d46ab9mr118277oal.2.1710367331362; Wed, 13 Mar 2024 15:02:11 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Ivan Klokov , Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 7/8] target/riscv: enable 'vstart_eq_zero' in the end of insns Date: Wed, 13 Mar 2024 19:01:40 -0300 Message-ID: <20240313220141.427730-8-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2001:4860:4864:20::34; envelope-from=dbarboza@ventanamicro.com; helo=mail-oa1-x34.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_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01, T_SPF_HELO_TEMPERROR=0.01 autolearn=unavailable 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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367415178100003 Content-Type: text/plain; charset="utf-8" From: Ivan Klokov The vstart_eq_zero flag is updated at the beginning of the translation phase from the env->vstart variable. During the execution phase all functions will set env->vstart =3D 0 after a successful execution, but the vstart_eq_zero flag remains the same as at the start of the block. This will wrongly cause SIGILLs in translations that requires env->vstart =3D 0 and might be reading vstart_eq_zero =3D false. This patch adds a new finalize_rvv_inst() helper that is called at the end of each vector instruction that will both update vstart_eq_zero and do a mark_vs_dirty(). Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1976 Signed-off-by: Ivan Klokov Signed-off-by: Daniel Henrique Barboza Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/insn_trans/trans_rvbf16.c.inc | 6 +- target/riscv/insn_trans/trans_rvv.c.inc | 83 ++++++++++++---------- target/riscv/insn_trans/trans_rvvk.c.inc | 12 ++-- target/riscv/translate.c | 6 ++ 4 files changed, 59 insertions(+), 48 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvbf16.c.inc b/target/riscv/insn= _trans/trans_rvbf16.c.inc index a842e76a6b..0a9cd1ec31 100644 --- a/target/riscv/insn_trans/trans_rvbf16.c.inc +++ b/target/riscv/insn_trans/trans_rvbf16.c.inc @@ -83,7 +83,7 @@ static bool trans_vfncvtbf16_f_f_w(DisasContext *ctx, arg= _vfncvtbf16_f_f_w *a) ctx->cfg_ptr->vlenb, ctx->cfg_ptr->vlenb, data, gen_helper_vfncvtbf16_f_f_w); - mark_vs_dirty(ctx); + finalize_rvv_inst(ctx); return true; } return false; @@ -108,7 +108,7 @@ static bool trans_vfwcvtbf16_f_f_v(DisasContext *ctx, a= rg_vfwcvtbf16_f_f_v *a) ctx->cfg_ptr->vlenb, ctx->cfg_ptr->vlenb, data, gen_helper_vfwcvtbf16_f_f_v); - mark_vs_dirty(ctx); + finalize_rvv_inst(ctx); return true; } return false; @@ -135,7 +135,7 @@ static bool trans_vfwmaccbf16_vv(DisasContext *ctx, arg= _vfwmaccbf16_vv *a) ctx->cfg_ptr->vlenb, ctx->cfg_ptr->vlenb, data, gen_helper_vfwmaccbf16_vv); - mark_vs_dirty(ctx); + finalize_rvv_inst(ctx); return true; } return false; diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index b0f19dcd85..b3d467a874 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -167,7 +167,7 @@ static bool do_vsetvl(DisasContext *s, int rd, int rs1,= TCGv s2) =20 gen_helper_vsetvl(dst, tcg_env, s1, s2); gen_set_gpr(s, rd, dst); - mark_vs_dirty(s); + finalize_rvv_inst(s); =20 gen_update_pc(s, s->cur_insn_len); lookup_and_goto_ptr(s); @@ -187,7 +187,7 @@ static bool do_vsetivli(DisasContext *s, int rd, TCGv s= 1, TCGv s2) =20 gen_helper_vsetvl(dst, tcg_env, s1, s2); gen_set_gpr(s, rd, dst); - mark_vs_dirty(s); + finalize_rvv_inst(s); gen_update_pc(s, s->cur_insn_len); lookup_and_goto_ptr(s); s->base.is_jmp =3D DISAS_NORETURN; @@ -657,6 +657,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, ui= nt32_t data, tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } =20 + finalize_rvv_inst(s); return true; } =20 @@ -812,6 +813,7 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1= , uint32_t rs2, =20 fn(dest, mask, base, stride, tcg_env, desc); =20 + finalize_rvv_inst(s); return true; } =20 @@ -913,6 +915,7 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1,= uint32_t vs2, =20 fn(dest, mask, base, index, tcg_env, desc); =20 + finalize_rvv_inst(s); return true; } =20 @@ -1043,7 +1046,7 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uin= t32_t data, =20 fn(dest, mask, base, tcg_env, desc); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -1100,6 +1103,7 @@ static bool ldst_whole_trans(uint32_t vd, uint32_t rs= 1, uint32_t nf, =20 fn(dest, base, tcg_env, desc); =20 + finalize_rvv_inst(s); return true; } =20 @@ -1189,7 +1193,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3F= n *gvec_fn, tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); } - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -1240,7 +1244,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, uint32_t vm, =20 fn(dest, mask, src1, src2, tcg_env, desc); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -1265,7 +1269,7 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2s= Fn *gvec_fn, gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), src1, MAXSZ(s), MAXSZ(s)); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1398,7 +1402,7 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, ui= nt32_t vs2, uint32_t vm, =20 fn(dest, mask, src1, src2, tcg_env, desc); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -1412,7 +1416,7 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2i= Fn *gvec_fn, if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s)); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, imm_mode); @@ -1471,7 +1475,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr = *a, tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -1543,7 +1547,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr = *a, vreg_ofs(s, a->rs2), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -1611,7 +1615,7 @@ static bool opivv_trans(uint32_t vd, uint32_t vs1, ui= nt32_t vs2, uint32_t vm, tcg_gen_gvec_4_ptr(vreg_ofs(s, vd), vreg_ofs(s, 0), vreg_ofs(s, vs1), vreg_ofs(s, vs2), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -1744,7 +1748,7 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVe= cGen2sFn32 *gvec_fn, gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), src1, MAXSZ(s), MAXSZ(s)); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s); @@ -1801,7 +1805,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2004,7 +2008,7 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_= v *a) s->cfg_ptr->vlenb, data, fns[s->sew]); } - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -2049,7 +2053,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_= x *a) fns[s->sew](dest, s1_i64, tcg_env, desc); } =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -2083,7 +2087,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_= i *a) tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd)); fns[s->sew](dest, s1, tcg_env, desc); } - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -2231,7 +2235,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2265,7 +2269,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, ui= nt32_t vs2, =20 fn(dest, mask, t1, src2, tcg_env, desc); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 @@ -2340,7 +2344,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2411,7 +2415,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2523,7 +2527,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a, vreg_ofs(s, a->rs2), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -2633,7 +2637,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) =20 fns[s->sew - 1](dest, t1, tcg_env, desc); } - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -2705,7 +2709,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2753,7 +2757,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2817,7 +2821,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew - 1]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2863,7 +2867,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, \ fns[s->sew]); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -2949,7 +2953,7 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) = \ vreg_ofs(s, a->rs2), tcg_env, \ s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, data, fn); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -3048,7 +3052,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ tcg_env, s->cfg_ptr->vlenb, \ s->cfg_ptr->vlenb, \ data, fn); \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -3087,7 +3091,7 @@ static bool trans_viota_m(DisasContext *s, arg_viota_= m *a) vreg_ofs(s, a->rs2), tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fns[s->sew]); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3114,7 +3118,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fns[s->sew]); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3271,7 +3275,7 @@ static bool trans_vmv_x_s(DisasContext *s, arg_vmv_x_= s *a) tcg_gen_trunc_i64_tl(dest, t1); gen_set_gpr(s, a->rd, dest); tcg_gen_movi_tl(cpu_vstart, 0); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3300,7 +3304,7 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_= x *a) vec_element_storei(s, a->rd, 0, t1); gen_set_label(over); tcg_gen_movi_tl(cpu_vstart, 0); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3328,7 +3332,7 @@ static bool trans_vfmv_f_s(DisasContext *s, arg_vfmv_= f_s *a) =20 mark_fs_dirty(s); tcg_gen_movi_tl(cpu_vstart, 0); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3354,9 +3358,10 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv= _s_f *a) do_nanbox(s, t1, cpu_fpr[a->rs1]); =20 vec_element_storei(s, a->rd, 0, t1); + gen_set_label(over); tcg_gen_movi_tl(cpu_vstart, 0); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3462,7 +3467,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rm= rr *a) =20 tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), dest); - mark_vs_dirty(s); + finalize_rvv_inst(s); } else { static gen_helper_opivx * const fns[4] =3D { gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h, @@ -3490,7 +3495,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rm= rr *a) endian_ofs(s, a->rs2, a->rs1), MAXSZ(s), MAXSZ(s)); } - mark_vs_dirty(s); + finalize_rvv_inst(s); } else { static gen_helper_opivx * const fns[4] =3D { gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h, @@ -3535,7 +3540,7 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r= *a) tcg_env, s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fns[s->sew]); - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -3560,7 +3565,7 @@ static bool trans_##NAME(DisasContext *s, arg_##NAME = * a) \ tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), \ tcg_env, maxsz, maxsz, 0, gen_helper_vmvr_v= ); \ } \ - mark_vs_dirty(s); \ + finalize_rvv_inst(s); \ return true; \ } \ return false; \ @@ -3631,7 +3636,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, u= int8_t seq) s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, data, fn); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } =20 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_t= rans/trans_rvvk.c.inc index 6d640e4596..ae1f40174a 100644 --- a/target/riscv/insn_trans/trans_rvvk.c.inc +++ b/target/riscv/insn_trans/trans_rvvk.c.inc @@ -174,7 +174,7 @@ GEN_OPIVX_GVEC_TRANS_CHECK(vandn_vx, andcs, zvkb_vx_che= ck) vreg_ofs(s, a->rs2), tcg_env, = \ s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, = \ data, fns[s->sew]); = \ - mark_vs_dirty(s); = \ + finalize_rvv_inst(s); = \ return true; = \ } = \ return false; = \ @@ -266,7 +266,7 @@ GEN_OPIVI_WIDEN_TRANS(vwsll_vi, IMM_ZX, vwsll_vx, vwsll= _vx_check) tcg_gen_addi_ptr(rd_v, tcg_env, vreg_ofs(s, a->rd)); = \ tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); = \ gen_helper_##NAME(rd_v, rs2_v, tcg_env, desc); = \ - mark_vs_dirty(s); = \ + finalize_rvv_inst(s); = \ return true; = \ } = \ return false; = \ @@ -341,7 +341,7 @@ GEN_V_UNMASKED_TRANS(vaesem_vs, vaes_check_vs, ZVKNED_E= GS) tcg_gen_addi_ptr(rd_v, tcg_env, vreg_ofs(s, a->rd)); = \ tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); = \ gen_helper_##NAME(rd_v, rs2_v, uimm_v, tcg_env, desc); = \ - mark_vs_dirty(s); = \ + finalize_rvv_inst(s); = \ return true; = \ } = \ return false; = \ @@ -405,7 +405,7 @@ GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED= _EGS) s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, = \ data, gen_helper_##NAME); = \ = \ - mark_vs_dirty(s); = \ + finalize_rvv_inst(s); = \ return true; = \ } = \ return false; = \ @@ -457,7 +457,7 @@ static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr = *a) s->sew =3D=3D MO_32 ? gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; @@ -488,7 +488,7 @@ static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr = *a) s->sew =3D=3D MO_32 ? gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv); =20 - mark_vs_dirty(s); + finalize_rvv_inst(s); return true; } return false; diff --git a/target/riscv/translate.c b/target/riscv/translate.c index ea5d52b2ef..9d57089fcc 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -676,6 +676,12 @@ static void mark_vs_dirty(DisasContext *ctx) static inline void mark_vs_dirty(DisasContext *ctx) { } #endif =20 +static void finalize_rvv_inst(DisasContext *ctx) +{ + mark_vs_dirty(ctx); + ctx->vstart_eq_zero =3D true; +} + static void gen_set_rm(DisasContext *ctx, int rm) { if (ctx->frm =3D=3D rm) { --=20 2.43.2 From nobody Sun May 12 21:20:38 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1710367424; cv=none; d=zohomail.com; s=zohoarc; b=ggn1AEBchcRQhtdkU4TbQ6xPYUroSvrOsw99kYYWqxWAQvcvG/UYkbRboKUr0Tj1r8fzfe66ZPstHS2APRYvWVexxmve6KSWb1PkpjoZnSQPCBD7sAfALd3WCyW+lCx+R9JrfzZHBHmKG3nyjyzxPjSLdan053vTAgqeydZcQFc= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1710367424; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=1nhYYmgtTkAPTHuRKnPIpy8B5UZ1KuAVaIrpsMSHG6w=; b=hSCgmmc24fC7DWMUdK0kIuywrTZP2pYSMCIZIl58UYvGzqDK+2lmgYILmVWLomEwzRgWYxqAbfIU2HDslcMSNWQOf6Vv+SMBgBl0JQdJgq0OIyBDfFqkYfjc9XZjRtUYv3urwu8kpVdSHKI2ZAtp1WTsBGVm551doQFXv7KqZEk= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1710367424445425.36931359873756; Wed, 13 Mar 2024 15:03:44 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rkWh4-0008Mw-OC; Wed, 13 Mar 2024 18:03:26 -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 1rkWg2-0007RY-91 for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:29 -0400 Received: from mail-pf1-x433.google.com ([2607:f8b0:4864:20::433]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1rkWfw-0004M2-CO for qemu-devel@nongnu.org; Wed, 13 Mar 2024 18:02:20 -0400 Received: by mail-pf1-x433.google.com with SMTP id d2e1a72fcca58-6e6c8b1ccd7so204536b3a.0 for ; Wed, 13 Mar 2024 15:02:15 -0700 (PDT) Received: from grind.dc1.ventanamicro.com ([177.94.15.159]) by smtp.gmail.com with ESMTPSA id ln17-20020a056a003cd100b006e6bcbea9e0sm95812pfb.88.2024.03.13.15.02.11 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Mar 2024 15:02:14 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ventanamicro.com; s=google; t=1710367334; x=1710972134; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=1nhYYmgtTkAPTHuRKnPIpy8B5UZ1KuAVaIrpsMSHG6w=; b=U30au1jBwLQ/9dadBib40wYFnQRgC4O2Ct7i5p6cGyO00e1thGmuVNztEWRHtaYRIN S9OT3xzJsNtCzR27RD+gXy99SN61p5hR572FtlwuGAcaakihorRudI6sQZTYhw8tTYsP xig6Wod7a2lgv2LW4Bms0jwUB+1eDNmW/evdIvaEAcpVWc4b3Tf2xhsyEBJ6dKKjBG2G iePkIRHSTf5M6xjgJ2aEIo8jgUqTKHRTqsFtUARuaaRc6oDu19b6AN13+t3OUea1snC2 okDrJIwSsWyJ9WqjsCNBCTWWxw6ID+Nao2JWGmBmRlUauQk1le8tqVxDaCOZ+u6+d2+G Z6kw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1710367334; x=1710972134; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=1nhYYmgtTkAPTHuRKnPIpy8B5UZ1KuAVaIrpsMSHG6w=; b=AYVcRFcCVwhaU6DKOUiWxUlPNHMsDCkIPXYF419GOmVKS2ZZGBr+9pUKS+rLokRkH0 VWAgiUcOFdAkG9ALB+7FMJZt1mUbTJruzAi0KlWvXQvpk86uOg7mdMxyETSG+d+lQeP0 1uBl7mjOYleOsWwjKl21bwD24pTfNkpjh1U0rW8NZlmYOCRIrdXh3e5iS1k56jjyS2dR cTdj4sPYp9lFMX31yPH5/vSBTjCeLv1j5fuYGLmUl1HyC4iLpuuxRk+dK73QICkB3YTc DyYoXjUkEaTL/9K606hP/uXLEI2RIQGejBAx/x/HM23uczRrOHXbLEa6LE757Q8YpxuZ GC1w== X-Gm-Message-State: AOJu0YyrvRQnItbIiyIRKC7DofzGqV+3ENK2T9g8KxbQAVaFvx3F8JS0 i9fcaamNcvz0x1WeXmMPBLZyfqhP0CJKrVjhVU1FsxZOjzWdh8DNDSOVL//84DLrBJs0XirgSBy C X-Google-Smtp-Source: AGHT+IFMLLyxCXBsgdn/lQG33UZ8Wd6skfsqdDaij/M5BXJkwTnbIGKz095CKQ5nSQqRLOFiP3mEFg== X-Received: by 2002:a05:6a00:1828:b0:6e5:ec63:95ce with SMTP id y40-20020a056a00182800b006e5ec6395cemr26748pfa.10.1710367334563; Wed, 13 Mar 2024 15:02:14 -0700 (PDT) From: Daniel Henrique Barboza To: qemu-devel@nongnu.org Cc: qemu-riscv@nongnu.org, alistair.francis@wdc.com, bmeng@tinylab.org, liwei1518@gmail.com, zhiwei_liu@linux.alibaba.com, palmer@rivosinc.com, richard.henderson@linaro.org, philmd@linaro.org, Daniel Henrique Barboza Subject: [PATCH for-9.0 v14 8/8] target/riscv/vector_helper.c: optimize loops in ldst helpers Date: Wed, 13 Mar 2024 19:01:41 -0300 Message-ID: <20240313220141.427730-9-dbarboza@ventanamicro.com> X-Mailer: git-send-email 2.43.2 In-Reply-To: <20240313220141.427730-1-dbarboza@ventanamicro.com> References: <20240313220141.427730-1-dbarboza@ventanamicro.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::433; envelope-from=dbarboza@ventanamicro.com; helo=mail-pf1-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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @ventanamicro.com) X-ZM-MESSAGEID: 1710367425149100001 Content-Type: text/plain; charset="utf-8" Change the for loops in ldst helpers to do a single increment in the counter, and assign it env->vstart, to avoid re-reading from vstart every time. Suggested-by: Richard Henderson Signed-off-by: Daniel Henrique Barboza Reviewed-by: Alistair Francis Reviewed-by: Richard Henderson --- target/riscv/vector_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 48d041dd4e..6ee5380d0e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -209,7 +209,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, =20 VSTART_CHECK_EARLY_EXIT(env); =20 - for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { + for (i =3D env->vstart; i < env->vl; env->vstart =3D ++i) { k =3D 0; while (k < nf) { if (!vm && !vext_elem_mask(v0, i)) { @@ -277,7 +277,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState= *env, uint32_t desc, VSTART_CHECK_EARLY_EXIT(env); =20 /* load bytes from guest memory */ - for (i =3D env->vstart; i < evl; i++, env->vstart++) { + for (i =3D env->vstart; i < evl; env->vstart =3D ++i) { k =3D 0; while (k < nf) { target_ulong addr =3D base + ((i * nf + k) << log2_esz); @@ -393,7 +393,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, VSTART_CHECK_EARLY_EXIT(env); =20 /* load bytes from guest memory */ - for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { + for (i =3D env->vstart; i < env->vl; env->vstart =3D ++i) { k =3D 0; while (k < nf) { if (!vm && !vext_elem_mask(v0, i)) { --=20 2.43.2