From nobody Fri Nov 14 00:50:53 2025 Delivered-To: importer@patchew.org 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; 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=1583756797; cv=none; d=zohomail.com; s=zohoarc; b=D1QRbl4Od9bFFzPFj8ckKmG9tkDw/psYgtKBJjw2TK2twm5e7czjLmC8Fr/U0LrXAffs3TqdoWA88AuXbd8TjX5Yg3vzf6D0N/iXakdOydFO82SrFde7g2TKvOJpuNQDOMb+1RyryNyn3fXqTKn2z2FrMWXNta98PlVTCkYRoYc= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1583756797; 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=7CsUInkgR2nI4iVy4+2rApxsQ7KyM4Q8x3uG28M4al4=; b=MdJnAlQhhZhDSki+R47m5N0aUmJ9xsosPkYhNMSR4We26nb9eUj2fwMt+0UAK8I310jgdF0mPyfRR37QnvL/NvmX6NViMlGXCq8tJdNVoiTaQIZQooqRh7ia3VHc5iuRnvlef/seJXn7UsR4fe4w5fTZZ2pZhgnZYK7CsdTZnuE= 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 1583756797249978.7115069640895; Mon, 9 Mar 2020 05:26:37 -0700 (PDT) Received: from localhost ([::1]:42200 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jBHUS-0001vJ-2P for importer@patchew.org; Mon, 09 Mar 2020 08:26:36 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:56377) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jBHJb-0001a3-Ui for qemu-devel@nongnu.org; Mon, 09 Mar 2020 08:15:25 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1jBHJZ-0002h2-P3 for qemu-devel@nongnu.org; Mon, 09 Mar 2020 08:15:23 -0400 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:48013) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1jBHJZ-0002bq-5W; Mon, 09 Mar 2020 08:15:21 -0400 Received: from L-PF1D6DP4-1208.hz.ali.com(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.GyaeXy8_1583756101) by smtp.aliyun-inc.com(10.147.41.199); Mon, 09 Mar 2020 20:15:17 +0800 X-Alimail-AntiSpam: AC=CONTINUE; BC=0.07632487|-1; CH=blue; DM=||false|; DS=CONTINUE|ham_system_inform|0.00758862-0.000132142-0.992279; FP=1061559410226699766|1|1|7|0|-1|-1|-1; HT=e02c03312; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=10; RT=10; SR=0; TI=SMTPD_---.GyaeXy8_1583756101; From: LIU Zhiwei To: richard.henderson@linaro.org, alistair23@gmail.com, chihmin.chao@sifive.com, palmer@dabbelt.com Subject: [PATCH v3 29/60] target/riscv: vector single-width floating-point add/subtract instructions Date: Mon, 9 Mar 2020 20:14:26 +0800 Message-Id: <20200309121457.13719-30-zhiwei_liu@c-sky.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20200309121457.13719-1-zhiwei_liu@c-sky.com> References: <20200309121457.13719-1-zhiwei_liu@c-sky.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x [generic] [fuzzy] X-Received-From: 121.197.200.217 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: guoren@linux.alibaba.com, qemu-riscv@nongnu.org, qemu-devel@nongnu.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.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 --- target/riscv/helper.h | 16 ++++ target/riscv/insn32.decode | 5 ++ target/riscv/insn_trans/trans_rvv.inc.c | 107 ++++++++++++++++++++++++ target/riscv/vector_helper.c | 89 ++++++++++++++++++++ 4 files changed, 217 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 4cad8679ec..6b46677eeb 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -785,3 +785,19 @@ DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, en= v, i32) DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index c7d589566f..32918c4d11 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -438,6 +438,11 @@ vnclipu_vi 101110 . ..... ..... 011 ..... 1010111= @r_vm vnclip_vv 101111 . ..... ..... 000 ..... 1010111 @r_vm vnclip_vx 101111 . ..... ..... 100 ..... 1010111 @r_vm vnclip_vi 101111 . ..... ..... 011 ..... 1010111 @r_vm +vfadd_vv 000000 . ..... ..... 001 ..... 1010111 @r_vm +vfadd_vf 000000 . ..... ..... 101 ..... 1010111 @r_vm +vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm +vfsub_vf 000010 . ..... ..... 101 ..... 1010111 @r_vm +vfrsub_vf 100111 . ..... ..... 101 ..... 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 11b4887275..af4dcb96c6 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1557,3 +1557,110 @@ GEN_OPIVX_NARROW_TRANS(vnclipu_vx) GEN_OPIVX_NARROW_TRANS(vnclip_vx) GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx) GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-poi= nt + * type, an illegal instruction exception is raised. + */ +static bool opfvv_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s, RVV) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + (s->sew !=3D 0)); +} + +/* OPFVV without GVEC IR */ +#define GEN_OPFVV_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + uint32_t data =3D 0; \ + static gen_helper_gvec_4_ptr * const fns[3] =3D { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + data =3D FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ + data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + 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, 0, s->vlen / 8, data, fns[s->sew - 1]); \ + return true; \ + } \ + return false; \ +} +GEN_OPFVV_TRANS(vfadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfsub_vv, opfvv_check) + +typedef void (*gen_helper_opfvf)(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_ptr, + TCGv_env, TCGv_i32); + +static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, + uint32_t data, gen_helper_opfvf fn, DisasContext *s) +{ + TCGv_ptr dest, src2, mask; + TCGv_i32 desc; + + dest =3D tcg_temp_new_ptr(); + mask =3D tcg_temp_new_ptr(); + src2 =3D tcg_temp_new_ptr(); + desc =3D tcg_const_i32(simd_desc(0, s->vlen / 8, data)); + + tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0)); + + fn(dest, mask, cpu_fpr[rs1], src2, cpu_env, desc); + + tcg_temp_free_ptr(dest); + tcg_temp_free_ptr(mask); + tcg_temp_free_ptr(src2); + tcg_temp_free_i32(desc); + return true; +} + +static bool opfvf_check(DisasContext *s, arg_rmrr *a) +{ +/* + * If the current SEW does not correspond to a supported IEEE floating-poi= nt + * type, an illegal instruction exception is raised + */ + return (vext_check_isa_ill(s, RVV) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (s->sew !=3D 0)); +} + +/* OPFVF without GVEC IR */ +#define GEN_OPFVF_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + uint32_t data =3D 0; \ + static gen_helper_opfvf const fns[3] =3D { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + data =3D FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data =3D FIELD_DP32(data, VDATA, VM, a->vm); \ + data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ + fns[s->sew - 1], s); \ + } \ + return false; \ +} + +GEN_OPFVF_TRANS(vfadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfsub_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 7f61d4c0c4..d49a7194f7 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -21,6 +21,7 @@ #include "exec/memop.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" +#include "fpu/softfloat.h" #include "tcg/tcg-gvec-desc.h" #include =20 @@ -2940,3 +2941,91 @@ RVVCALL(OPIVX2_ENV, vnclipu_vx_w, NOP_UUU_W, H4, H8,= vnclipu32) GEN_VEXT_VX_ENV(vnclipu_vx_b, 1, 1, clearb) GEN_VEXT_VX_ENV(vnclipu_vx_h, 2, 2, clearh) GEN_VEXT_VX_ENV(vnclipu_vx_w, 4, 4, clearl) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ +#define OPFVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX1 s1 =3D *((T1 *)vs1 + HS1(i)); \ + TX2 s2 =3D *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) =3D OP(s2, s1, &env->fp_status); \ +} +RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add) +RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add) +RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add) +GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8, clearq) + +#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX2 s2 =3D *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) =3D OP(s2, (TX1)(T1)s1, &env->fp_status);\ +} + +#define GEN_VEXT_VF(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ + void *vs2, CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t vlmax =3D vext_maxsz(desc) / ESZ; \ + uint32_t mlen =3D vext_mlen(desc); \ + 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; \ + } \ + do_##NAME(vd, s1, vs2, i, env); \ + } \ + if (i !=3D 0) { \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ + } \ +} +RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add) +RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add) +RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add) +GEN_VEXT_VF(vfadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfadd_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub) +RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub) +RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub) +GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub) +RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub) +RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub) +GEN_VEXT_VF(vfsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsub_vf_d, 8, 8, clearq) + +static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s) +{ + return float16_sub(b, a, s); +} + +static uint32_t float32_rsub(uint32_t a, uint32_t b, float_status *s) +{ + return float32_sub(b, a, s); +} + +static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s) +{ + return float64_sub(b, a, s); +} +RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub) +RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub) +RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub) +GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq) --=20 2.23.0