From nobody Tue Feb 10 02:00:48 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 ARC-Seal: i=1; a=rsa-sha256; t=1592634906; cv=none; d=zohomail.com; s=zohoarc; b=kEZhQIEFYlkD+93NPCqfdHmJdQ8Eu+JUQF3FNHaw/V1zP//dEZKv4IOw10hMit1nlamSqKEs6pieiW6TZL3iJuF++xhLn5PO6vaI7fqGtDaF68uQc2EI+dm/wY7GXD/9bFOiSEK3p+cwX07qmazeAObEOLXFa5398aZ5IysjYIs= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1592634906; h=Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=U4wNLn6DXhK7046cq+scG5+qg+VXDH5elu4enj7doo4=; b=ajehecwM6CQryfA0zM8ozXJPaEKyKn68b1WnkGCtMt4vzPbkI27w8vFAlg3EXToXSC9DAA9XuX0bm6CmrvH82Qe4SRTMMOb/cNRCzn/cBVUupdEgO9GQ+EYhkENryECqE/00z5i9F0Y6V2jao7uAfF3u7cX+oDnz1NGu2ULyrxM= ARC-Authentication-Results: i=1; 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 Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1592634906849159.77804555574414; Fri, 19 Jun 2020 23:35:06 -0700 (PDT) Received: from localhost ([::1]:44590 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jmX5k-0002vu-Pg for importer@patchew.org; Sat, 20 Jun 2020 02:35:04 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:58262) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jmX4i-0001ZZ-L5; Sat, 20 Jun 2020 02:34:00 -0400 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:45937) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jmX4e-0007AI-GE; Sat, 20 Jun 2020 02:34:00 -0400 Received: from L-PF1D6DP4-1208.hz.ali.com(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.HpZqTf7_1592634828) by smtp.aliyun-inc.com(10.147.42.197); Sat, 20 Jun 2020 14:33:49 +0800 X-Alimail-AntiSpam: AC=CONTINUE; BC=0.07608639|-1; BR=01201311R171S67ruler371_34042_170602; CH=green; DM=|OVERLOAD|false|; DS=SPAM|spam_ad|0.801865-0.000159662-0.197975; FP=0|0|0|0|0|-1|-1|-1; HT=e01l10434; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=8; RT=8; SR=0; TI=SMTPD_---.HpZqTf7_1592634828; From: LIU Zhiwei To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Subject: [PATCH v10 58/61] target/riscv: vector slide instructions Date: Sat, 20 Jun 2020 12:36:58 +0800 Message-Id: <20200620043701.1323-59-zhiwei_liu@c-sky.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20200620043701.1323-1-zhiwei_liu@c-sky.com> References: <20200620043701.1323-1-zhiwei_liu@c-sky.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: none client-ip=121.197.200.217; envelope-from=zhiwei_liu@c-sky.com; helo=smtp2200-217.mail.aliyun.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/06/19 21:09:48 X-ACL-Warn: Detected OS = Linux 3.x [generic] [fuzzy] X-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, SPF_HELO_NONE=0.001, SPF_NONE=0.001, UNPARSEABLE_RELAY=0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.com, Alistair.Francis@wdc.com, palmer@dabbelt.com, LIU Zhiwei Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Type: text/plain; charset="utf-8" Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson --- target/riscv/helper.h | 17 ++++ target/riscv/insn32.decode | 6 ++ target/riscv/insn_trans/trans_rvv.inc.c | 18 ++++ target/riscv/vector_helper.c | 114 ++++++++++++++++++++++++ 4 files changed, 155 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index c6695ea7a8..29a5eb7049 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1119,3 +1119,20 @@ DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32) DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32) DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32) DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32) + +DEF_HELPER_6(vslideup_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslideup_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslidedown_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 17288a3c95..36123f71b9 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -568,6 +568,12 @@ vext_x_v 001100 1 ..... ..... 010 ..... 1010111= @r vmv_s_x 001101 1 00000 ..... 110 ..... 1010111 @r2 vfmv_f_s 001100 1 ..... 00000 001 ..... 1010111 @r2rd vfmv_s_f 001101 1 00000 ..... 101 ..... 1010111 @r2 +vslideup_vx 001110 . ..... ..... 100 ..... 1010111 @r_vm +vslideup_vi 001110 . ..... ..... 011 ..... 1010111 @r_vm +vslide1up_vx 001110 . ..... ..... 110 ..... 1010111 @r_vm +vslidedown_vx 001111 . ..... ..... 100 ..... 1010111 @r_vm +vslidedown_vi 001111 . ..... ..... 011 ..... 1010111 @r_vm +vslide1down_vx 001111 . ..... ..... 110 ..... 1010111 @r_vm =20 vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm vsetvl 1000000 ..... ..... 111 ..... 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_tr= ans/trans_rvv.inc.c index 884ad910b1..ffb9835d07 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2758,3 +2758,21 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv= _s_f *a) } return false; } + +/* Vector Slide Instructions */ +static bool slideup_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, true) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (a->rd !=3D a->rs2)); +} + +GEN_OPIVX_TRANS(vslideup_vx, slideup_check) +GEN_OPIVX_TRANS(vslide1up_vx, slideup_check) +GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx, slideup_check) + +GEN_OPIVX_TRANS(vslidedown_vx, opivx_check) +GEN_OPIVX_TRANS(vslide1down_vx, opivx_check) +GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 1dc2a1ccb1..28b54d2589 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4697,3 +4697,117 @@ GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb) GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh) GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl) GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq) + +/* + *** Vector Permutation Instructions + */ + +/* Vector Slide Instructions */ +#define GEN_VEXT_VSLIDEUP_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); = \ + uint32_t vlmax =3D env_archcpu(env)->cfg.vlen / mlen; = \ + uint32_t vm =3D vext_vm(desc); = \ + uint32_t vl =3D env->vl; = \ + target_ulong offset =3D s1, i; = \ + \ + for (i =3D offset; i < vl; i++) { = \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i - offset)); = \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] =3D vs2[i] */ +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDEDOWN_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); = \ + uint32_t vlmax =3D env_archcpu(env)->cfg.vlen / mlen; = \ + uint32_t vm =3D vext_vm(desc); = \ + uint32_t vl =3D env->vl; = \ + target_ulong offset =3D s1, i; = \ + \ + for (i =3D 0; i < vl; ++i) { = \ + target_ulong j =3D i + offset; = \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(i)) =3D j >=3D vlmax ? 0 : *((ETYPE *)vs2 + H(j)= ); \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslidedown.vx vd, vs2, rs1, vm # vd[i] =3D vs2[i+rs1] */ +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDE1UP_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); = \ + uint32_t vlmax =3D env_archcpu(env)->cfg.vlen / mlen; = \ + uint32_t vm =3D vext_vm(desc); = \ + uint32_t vl =3D env->vl; = \ + uint32_t i; \ + \ + for (i =3D 0; i < vl; i++) { = \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + if (i =3D=3D 0) { = \ + *((ETYPE *)vd + H(i)) =3D s1; = \ + } else { \ + *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i - 1)); = \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslide1up.vx vd, vs2, rs1, vm # vd[0]=3Dx[rs1], vd[i+1] =3D vs2[i] */ +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq) + +#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); = \ + uint32_t vlmax =3D env_archcpu(env)->cfg.vlen / mlen; = \ + uint32_t vm =3D vext_vm(desc); = \ + uint32_t vl =3D env->vl; = \ + uint32_t i; \ + \ + for (i =3D 0; i < vl; i++) { = \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + if (i =3D=3D vl - 1) { = \ + *((ETYPE *)vd + H(i)) =3D s1; = \ + } else { \ + *((ETYPE *)vd + H(i)) =3D *((ETYPE *)vs2 + H(i + 1)); = \ + } \ + } \ + CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* vslide1down.vx vd, vs2, rs1, vm # vd[i] =3D vs2[i+1], vd[vl-1]=3Dx[rs1]= */ +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1, clearb) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2, clearh) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4, clearl) +GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq) --=20 2.23.0