From nobody Mon Feb 9 20:35:00 2026 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; 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; dmarc=fail(p=none dis=none) header.from=git.sr.ht Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1652207268903512.3753713138867; Tue, 10 May 2022 11:27:48 -0700 (PDT) Received: from localhost ([::1]:34388 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1noUaJ-0004jA-F7 for importer@patchew.org; Tue, 10 May 2022 14:27:47 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:35474) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1noUYq-0001ne-2H; Tue, 10 May 2022 14:26:16 -0400 Received: from mail-b.sr.ht ([173.195.146.151]:45008) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1noUYm-0003SR-Ui; Tue, 10 May 2022 14:26:15 -0400 Received: from git.sr.ht (unknown [173.195.146.142]) by mail-b.sr.ht (Postfix) with ESMTPSA id 15DAB11F0D9; Tue, 10 May 2022 18:26:09 +0000 (UTC) Authentication-Results: mail-b.sr.ht; dkim=none From: ~eopxd Date: Thu, 17 Mar 2022 02:08:01 -0700 Subject: [PATCH qemu v2 07/10] target/riscv: rvv: Add mask agnostic for vector floating-point instructions Message-ID: <165220716770.22380.2493420346587893209-7@git.sr.ht> X-Mailer: git.sr.ht In-Reply-To: <165220716770.22380.2493420346587893209-0@git.sr.ht> To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: Palmer Dabbelt , Alistair Francis , Bin Meng , Frank Chang , WeiWei Li , eop Chen Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 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=173.195.146.151; envelope-from=outgoing@sr.ht; helo=mail-b.sr.ht X-Spam_score_int: 36 X-Spam_score: 3.6 X-Spam_bar: +++ X-Spam_report: (3.6 / 5.0 requ) BAYES_00=-1.9, DATE_IN_PAST_96_XX=3.405, FREEMAIL_FORGED_REPLYTO=2.095, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: ~eopxd Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZM-MESSAGEID: 1652207271100100003 From: Yueh-Ting (eop) Chen Signed-off-by: eop Chen Reviewed-by: Frank Chang Reviewed-by: Weiwei Li --- target/riscv/insn_trans/trans_rvv.c.inc | 12 ++++++++++++ target/riscv/vector_helper.c | 26 +++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index 5cbf323c18..8fb8045957 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -2428,6 +2428,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ data =3D \ FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s);\ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs1), \ vreg_ofs(s, a->rs2), cpu_env, \ @@ -2513,6 +2514,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ data =3D FIELD_DP32(data, VDATA, VTA_ALL_1S, \ s->cfg_vta_all_1s); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ fns[s->sew - 1], s); \ } \ @@ -2552,6 +2554,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs1), \ vreg_ofs(s, a->rs2), cpu_env, \ @@ -2592,6 +2595,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ fns[s->sew - 1], s); \ } \ @@ -2629,6 +2633,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs1), \ vreg_ofs(s, a->rs2), cpu_env, \ @@ -2669,6 +2674,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a= ) \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ fns[s->sew - 1], s); \ } \ @@ -2753,6 +2759,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a, data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); data =3D FIELD_DP32(data, VDATA, VTA, s->vta); + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8, @@ -2867,6 +2874,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_= v_f *a) TCGv_i32 desc; uint32_t data =3D FIELD_DP32(0, VDATA, LMUL, s->lmul); data =3D FIELD_DP32(data, VDATA, VTA, s->vta); + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); static gen_helper_vmv_vx * const fns[3] =3D { gen_helper_vmv_v_x_h, gen_helper_vmv_v_x_w, @@ -2968,6 +2976,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs2), cpu_env, \ s->cfg_ptr->vlen / 8, \ @@ -3021,6 +3030,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs2), cpu_env, \ s->cfg_ptr->vlen / 8, \ @@ -3089,6 +3099,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs2), cpu_env, \ s->cfg_ptr->vlen / 8, \ @@ -3144,6 +3155,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)= \ data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ data =3D FIELD_DP32(data, VDATA, VTA, s->vta); \ + data =3D FIELD_DP32(data, VDATA, VMA, s->vma); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs2), cpu_env, \ s->cfg_ptr->vlen / 8, \ diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 4e48c92617..5b9d766e0e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3053,10 +3053,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, = \ uint32_t total_elems =3D \ vext_get_total_elems(env, desc, ESZ); \ uint32_t vta =3D vext_vta(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + vext_set_elems_1s(vd, vma, i * ESZ, \ + (i + 1) * ESZ); \ continue; \ } \ do_##NAME(vd, vs1, vs2, i, env); \ @@ -3092,10 +3096,14 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, = \ uint32_t total_elems =3D \ vext_get_total_elems(env, desc, ESZ); \ uint32_t vta =3D vext_vta(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + vext_set_elems_1s(vd, vma, i * ESZ, \ + (i + 1) * ESZ); \ continue; \ } \ do_##NAME(vd, s1, vs2, i, env); \ @@ -3667,6 +3675,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ uint32_t total_elems =3D \ vext_get_total_elems(env, desc, ESZ); \ uint32_t vta =3D vext_vta(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ if (vl =3D=3D 0) { \ @@ -3674,6 +3683,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ } \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + vext_set_elems_1s(vd, vma, i * ESZ, \ + (i + 1) * ESZ); \ continue; \ } \ do_##NAME(vd, vs2, i, env); \ @@ -4184,12 +4196,17 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, vo= id *vs2, \ uint32_t vl =3D env->vl; \ uint32_t total_elems =3D env_archcpu(env)->cfg.vlen; \ uint32_t vta_all_1s =3D vext_vta_all_1s(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s1 =3D *((ETYPE *)vs1 + H(i)); \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + if (vma) { \ + vext_set_elem_mask(vd, i, 1); \ + } \ continue; \ } \ vext_set_elem_mask(vd, i, \ @@ -4217,11 +4234,16 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, = void *vs2, \ uint32_t vl =3D env->vl; \ uint32_t total_elems =3D env_archcpu(env)->cfg.vlen; \ uint32_t vta_all_1s =3D vext_vta_all_1s(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ for (i =3D env->vstart; i < vl; i++) { \ ETYPE s2 =3D *((ETYPE *)vs2 + H(i)); \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + if (vma) { \ + vext_set_elem_mask(vd, i, 1); \ + } \ continue; \ } \ vext_set_elem_mask(vd, i, \ @@ -4344,10 +4366,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ uint32_t total_elems =3D \ vext_get_total_elems(env, desc, ESZ); \ uint32_t vta =3D vext_vta(desc); \ + uint32_t vma =3D vext_vma(desc); \ uint32_t i; \ \ for (i =3D env->vstart; i < vl; i++) { \ if (!vm && !vext_elem_mask(v0, i)) { \ + /* set masked-off elements to 1s */ \ + vext_set_elems_1s(vd, vma, i * ESZ, \ + (i + 1) * ESZ); \ continue; \ } \ do_##NAME(vd, vs2, i); \ --=20 2.34.2