From nobody Sat Jul 5 01:02:38 2025 Delivered-To: importer2@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+importer2=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 1652444937479800.153824959032; Fri, 13 May 2022 05:28:57 -0700 (PDT) Received: from localhost ([::1]:44764 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1npUPg-0000zt-6K for importer2@patchew.org; Fri, 13 May 2022 08:28:56 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:49862) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1npTw2-0000Mk-Tx; Fri, 13 May 2022 07:58:20 -0400 Received: from mail-b.sr.ht ([173.195.146.151]:45446) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1npTvz-00029r-Cc; Fri, 13 May 2022 07:58:18 -0400 Received: from git.sr.ht (unknown [173.195.146.142]) by mail-b.sr.ht (Postfix) with ESMTPSA id AFC9F11F13A; Fri, 13 May 2022 11:58:10 +0000 (UTC) Authentication-Results: mail-b.sr.ht; dkim=none From: ~eopxd Date: Thu, 17 Mar 2022 02:32:47 -0700 Subject: [PATCH qemu v4 09/10] target/riscv: rvv: Add mask agnostic for vector permutation instructions Message-ID: <165244308918.21805.1094821418229175817-9@git.sr.ht> X-Mailer: git.sr.ht In-Reply-To: <165244308918.21805.1094821418229175817-0@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+importer2=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+importer2=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZM-MESSAGEID: 1652444938604100001 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 | 1 + target/riscv/vector_helper.c | 26 +++++++++++++++++++++++-- 2 files changed, 25 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 333c6f5ef5..fde07c7fcf 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -3879,6 +3879,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, u= int8_t seq) 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); =20 tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), vreg_ofs(s, a->rs2), cpu_env, diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index e4c6530dfa..5c6cf1594f 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -5017,11 +5017,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong = s1, void *vs2, \ uint32_t esz =3D sizeof(ETYPE); = \ 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); = \ target_ulong offset =3D s1, i_min, i; = \ \ i_min =3D MAX(env->vstart, offset); = \ for (i =3D i_min; 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; \ } \ *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i - offset)); = \ @@ -5046,13 +5049,17 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong = s1, void *vs2, \ uint32_t esz =3D sizeof(ETYPE); = \ 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); = \ target_ulong i_max, i; \ \ i_max =3D MAX(MIN(s1 < vlmax ? vlmax - s1 : 0, vl), env->vstart); = \ for (i =3D env->vstart; i < i_max; ++i) { = \ - if (vm || vext_elem_mask(v0, i)) { \ - *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i + s1)); = \ + 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; \ } \ + *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i + s1)); = \ } \ \ for (i =3D i_max; i < vl; ++i) { = \ @@ -5082,10 +5089,13 @@ static void vslide1up_##BITWIDTH(void *vd, void *v0= , target_ulong s1, \ uint32_t esz =3D sizeof(ETYPE); = \ 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; = \ } = \ if (i =3D=3D 0) { = \ @@ -5127,10 +5137,13 @@ static void vslide1down_##BITWIDTH(void *vd, void *= v0, target_ulong s1, \ uint32_t esz =3D sizeof(ETYPE); = \ 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; = \ } = \ if (i =3D=3D vl - 1) { = \ @@ -5198,11 +5211,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, vo= id *vs2, \ uint32_t esz =3D sizeof(TS2); = \ 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); = \ uint64_t index; \ 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; \ } \ index =3D *((TS1 *)vs1 + HS1(i)); = \ @@ -5238,11 +5254,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong = s1, void *vs2, \ uint32_t esz =3D sizeof(ETYPE); = \ 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); = \ uint64_t index =3D s1; = \ 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; \ } \ if (index >=3D vlmax) { = \ @@ -5317,10 +5336,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, = \ uint32_t esz =3D sizeof(ETYPE); \ 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; \ } \ *((ETYPE *)vd + HD(i)) =3D *((DTYPE *)vs2 + HS1(i)); \ --=20 2.34.2