From nobody Mon Feb 9 19:54:06 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 1648008455932115.62869055187946; Tue, 22 Mar 2022 21:07:35 -0700 (PDT) Received: from localhost ([::1]:49140 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1nWsHW-0002HA-G3 for importer@patchew.org; Wed, 23 Mar 2022 00:07:34 -0400 Received: from eggs.gnu.org ([209.51.188.92]:57334) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1nWs8R-0004vq-Ov; Tue, 22 Mar 2022 23:58:13 -0400 Received: from mail-b.sr.ht ([173.195.146.151]:36442) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1nWs8N-0005xV-7C; Tue, 22 Mar 2022 23:58:11 -0400 Received: from git.sr.ht (unknown [173.195.146.142]) by mail-b.sr.ht (Postfix) with ESMTPSA id E1F7511EFBD; Wed, 23 Mar 2022 03:58:03 +0000 (UTC) Authentication-Results: mail-b.sr.ht; dkim=none From: ~eopxd Date: Sun, 06 Mar 2022 23:10:25 -0800 Subject: [PATCH qemu v3 05/14] target/riscv: rvv: Add tail agnostic for vector load / store instructions Message-ID: <164800788276.12449.15168787569124374586-5@git.sr.ht> X-Mailer: git.sr.ht In-Reply-To: <164800788276.12449.15168787569124374586-0@git.sr.ht> To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org 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 Cc: WeiWei Li , Frank Chang , eop Chen , Bin Meng , Alistair Francis , Palmer Dabbelt Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZM-MESSAGEID: 1648008456140100001 From: eopXD Signed-off-by: eop Chen Reviewed-by: Frank Chang --- target/riscv/insn_trans/trans_rvv.c.inc | 9 +++++++ target/riscv/vector_helper.c | 32 +++++++++++++++++++++++++ 2 files changed, 41 insertions(+) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_tr= ans/trans_rvv.c.inc index 603abe0e9f..e503c31111 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -711,6 +711,7 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, ui= nt8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_us_trans(a->rd, a->rs1, data, fn, s, false); } =20 @@ -748,6 +749,7 @@ static bool st_us_op(DisasContext *s, arg_r2nfvm *a, ui= nt8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_us_trans(a->rd, a->rs1, data, fn, s, true); } =20 @@ -774,6 +776,7 @@ static bool ld_us_mask_op(DisasContext *s, arg_vlm_v *a= , uint8_t eew) /* EMUL =3D 1, NFIELDS =3D 1 */ data =3D FIELD_DP32(data, VDATA, LMUL, 0); data =3D FIELD_DP32(data, VDATA, NF, 1); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_us_trans(a->rd, a->rs1, data, fn, s, false); } =20 @@ -791,6 +794,7 @@ static bool st_us_mask_op(DisasContext *s, arg_vsm_v *a= , uint8_t eew) /* EMUL =3D 1, NFIELDS =3D 1 */ data =3D FIELD_DP32(data, VDATA, LMUL, 0); data =3D FIELD_DP32(data, VDATA, NF, 1); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_us_trans(a->rd, a->rs1, data, fn, s, true); } =20 @@ -862,6 +866,7 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a,= uint8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, false); } =20 @@ -891,6 +896,7 @@ static bool st_stride_op(DisasContext *s, arg_rnfvm *a,= uint8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); fn =3D fns[eew]; if (fn =3D=3D NULL) { return false; @@ -991,6 +997,7 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, = uint8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, false); } =20 @@ -1043,6 +1050,7 @@ static bool st_index_op(DisasContext *s, arg_rnfvm *a= , uint8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, true); } =20 @@ -1108,6 +1116,7 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a, u= int8_t eew) data =3D FIELD_DP32(data, VDATA, VM, a->vm); data =3D FIELD_DP32(data, VDATA, LMUL, emul); data =3D FIELD_DP32(data, VDATA, NF, a->nf); + data =3D FIELD_DP32(data, VDATA, VTA, s->vta); return ldff_trans(a->rd, a->rs1, data, fn, s); } =20 diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 6c47d39251..082b12ad1d 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -289,6 +289,9 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, uint32_t i, k; uint32_t nf =3D vext_nf(desc); uint32_t max_elems =3D vext_max_elems(desc, log2_esz); + uint32_t vlmax =3D vext_get_total_elem(env_archcpu(env), env->vtype); + uint32_t vta =3D vext_vta(desc); + uint32_t esz =3D 1 << log2_esz; =20 for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { if (!vm && !vext_elem_mask(v0, i)) { @@ -303,6 +306,11 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, } } env->vstart =3D 0; + /* set tail elements to 1s */ + for (k =3D 0; k < nf; ++k) { + vext_set_elems_1s_fns[log2_esz](vd, vta, env->vl + k * vlmax, + env->vl * esz, vlmax * esz); + } } =20 #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN) \ @@ -348,6 +356,9 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState= *env, uint32_t desc, uint32_t i, k; uint32_t nf =3D vext_nf(desc); uint32_t max_elems =3D vext_max_elems(desc, log2_esz); + uint32_t vlmax =3D vext_get_total_elem(env_archcpu(env), env->vtype); + uint32_t vta =3D vext_vta(desc); + uint32_t esz =3D 1 << log2_esz; =20 /* load bytes from guest memory */ for (i =3D env->vstart; i < evl; i++, env->vstart++) { @@ -359,6 +370,11 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVStat= e *env, uint32_t desc, } } env->vstart =3D 0; + /* set tail elements to 1s */ + for (k =3D 0; k < nf; ++k) { + vext_set_elems_1s_fns[log2_esz](vd, vta, env->vl + k * vlmax, + env->vl * esz, vlmax * esz); + } } =20 /* @@ -458,6 +474,9 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t nf =3D vext_nf(desc); uint32_t vm =3D vext_vm(desc); uint32_t max_elems =3D vext_max_elems(desc, log2_esz); + uint32_t vlmax =3D vext_get_total_elem(env_archcpu(env), env->vtype); + uint32_t vta =3D vext_vta(desc); + uint32_t esz =3D 1 << log2_esz; =20 /* load bytes from guest memory */ for (i =3D env->vstart; i < env->vl; i++, env->vstart++) { @@ -473,6 +492,11 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, } } env->vstart =3D 0; + /* set tail elements to 1s */ + for (k =3D 0; k < nf; ++k) { + vext_set_elems_1s_fns[log2_esz](vd, vta, env->vl + k * vlmax, + env->vl * esz, vlmax * esz); + } } =20 #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN) = \ @@ -540,6 +564,9 @@ vext_ldff(void *vd, void *v0, target_ulong base, uint32_t nf =3D vext_nf(desc); uint32_t vm =3D vext_vm(desc); uint32_t max_elems =3D vext_max_elems(desc, log2_esz); + uint32_t vlmax =3D vext_get_total_elem(env_archcpu(env), env->vtype); + uint32_t vta =3D vext_vta(desc); + uint32_t esz =3D 1 << log2_esz; target_ulong addr, offset, remain; =20 /* probe every access*/ @@ -595,6 +622,11 @@ ProbeSuccess: } } env->vstart =3D 0; + /* set tail elements to 1s */ + for (k =3D 0; k < nf; ++k) { + vext_set_elems_1s_fns[log2_esz](vd, vta, env->vl + k * vlmax, + env->vl * esz, vlmax * esz); + } } =20 #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN) \ --=20 2.34.1