From: frank.chang@sifive.com To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: Sagar Karandikar <sagark@eecs.berkeley.edu>, Frank Chang <frank.chang@sifive.com>, Bastian Koppelmann <kbastian@mail.uni-paderborn.de>, Richard Henderson <richard.henderson@linaro.org>, Alistair Francis <Alistair.Francis@wdc.com>, Palmer Dabbelt <palmer@dabbelt.com>, LIU Zhiwei <zhiwei_liu@c-sky.com> Subject: [PATCH v7 11/75] target/riscv: rvv-1.0: remove MLEN calculations Date: Fri, 26 Feb 2021 11:17:55 +0800 [thread overview] Message-ID: <20210226031902.23656-12-frank.chang@sifive.com> (raw) In-Reply-To: <20210226031902.23656-1-frank.chang@sifive.com> From: Frank Chang <frank.chang@sifive.com> As in RVV 1.0 design, MLEN is hardcoded with value 1 (Section 4.5). Thus, remove all MLEN related calculations. Signed-off-by: Frank Chang <frank.chang@sifive.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> --- target/riscv/insn_trans/trans_rvv.c.inc | 35 +--- target/riscv/internals.h | 9 +- target/riscv/translate.c | 2 - target/riscv/vector_helper.c | 250 ++++++++++-------------- 4 files changed, 110 insertions(+), 186 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 56ce39e769a..46e18a62b59 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -247,7 +247,6 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -300,7 +299,6 @@ static bool st_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -387,7 +385,6 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -426,7 +423,6 @@ static bool st_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) gen_helper_vsse_v_w, gen_helper_vsse_v_d } }; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -518,7 +514,6 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -570,7 +565,6 @@ static bool st_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -649,7 +643,6 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -760,7 +753,6 @@ static bool amo_op(DisasContext *s, arg_rwdvm *a, uint8_t seq) } } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, WD, a->wd); @@ -839,7 +831,6 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn, } else { uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -885,7 +876,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, src1 = tcg_temp_new(); gen_get_gpr(src1, rs1); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data)); @@ -1034,7 +1024,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, } else { src1 = tcg_const_tl(sextract64(imm, 0, 5)); } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data)); @@ -1130,7 +1119,6 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a, TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -1219,7 +1207,6 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a, TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -1298,7 +1285,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1489,7 +1475,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1859,7 +1844,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1932,7 +1916,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_d, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -1973,7 +1956,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2011,7 +1993,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -2048,7 +2029,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2084,7 +2064,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -2164,7 +2143,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2307,7 +2285,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2356,7 +2333,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2419,7 +2395,6 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = 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), \ @@ -2449,7 +2424,6 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a) TCGv dst; TCGv_i32 desc; uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -2481,7 +2455,6 @@ static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a) TCGv dst; TCGv_i32 desc; uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -2517,7 +2490,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \ @@ -2545,7 +2517,6 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); static gen_helper_gvec_3_ptr * const fns[4] = { @@ -2572,7 +2543,6 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); static gen_helper_gvec_2_ptr * const fns[4] = { @@ -2863,7 +2833,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a) } if (a->vm && s->vl_eq_vlmax) { - int vlmax = s->vlen / s->mlen; + int vlmax = s->vlen; TCGv_i64 dest = tcg_temp_new_i64(); if (a->rs1 == 0) { @@ -2894,7 +2864,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a) } if (a->vm && s->vl_eq_vlmax) { - if (a->rs1 >= s->vlen / s->mlen) { + if (a->rs1 >= s->vlen) { tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), 0); } else { @@ -2934,7 +2904,6 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = 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), diff --git a/target/riscv/internals.h b/target/riscv/internals.h index b15ad394bb9..c3bbeea9a94 100644 --- a/target/riscv/internals.h +++ b/target/riscv/internals.h @@ -22,11 +22,10 @@ #include "hw/registerfields.h" /* share data between vector helpers and decode code */ -FIELD(VDATA, MLEN, 0, 8) -FIELD(VDATA, VM, 8, 1) -FIELD(VDATA, LMUL, 9, 2) -FIELD(VDATA, NF, 11, 4) -FIELD(VDATA, WD, 11, 1) +FIELD(VDATA, VM, 0, 1) +FIELD(VDATA, LMUL, 1, 3) +FIELD(VDATA, NF, 4, 4) +FIELD(VDATA, WD, 4, 1) /* float point classify helpers */ target_ulong fclass_h(uint64_t frs1); diff --git a/target/riscv/translate.c b/target/riscv/translate.c index fdb0a83a610..6e1896188c0 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -63,7 +63,6 @@ typedef struct DisasContext { uint8_t lmul; uint8_t sew; uint16_t vlen; - uint16_t mlen; bool vl_eq_vlmax; CPUState *cs; } DisasContext; @@ -855,7 +854,6 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL); ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW); ctx->lmul = FIELD_EX32(tb_flags, TB_FLAGS, LMUL); - ctx->mlen = 1 << (ctx->sew + 3 - ctx->lmul); ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); ctx->cs = cs; } diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index bc3f212ceac..12301e943e6 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -81,11 +81,6 @@ static inline uint32_t vext_nf(uint32_t desc) return FIELD_EX32(simd_data(desc), VDATA, NF); } -static inline uint32_t vext_mlen(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, MLEN); -} - static inline uint32_t vext_vm(uint32_t desc) { return FIELD_EX32(simd_data(desc), VDATA, VM); @@ -188,19 +183,24 @@ static void clearq(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) vext_clear(cur, cnt, tot); } -static inline void vext_set_elem_mask(void *v0, int mlen, int index, +static inline void vext_set_elem_mask(void *v0, int index, uint8_t value) { - int idx = (index * mlen) / 64; - int pos = (index * mlen) % 64; + int idx = index / 64; + int pos = index % 64; uint64_t old = ((uint64_t *)v0)[idx]; - ((uint64_t *)v0)[idx] = deposit64(old, pos, mlen, value); + ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value); } -static inline int vext_elem_mask(void *v0, int mlen, int index) +/* + * Earlier designs (pre-0.9) had a varying number of bits + * per mask value (MLEN). In the 0.9 design, MLEN=1. + * (Section 4.5) + */ +static inline int vext_elem_mask(void *v0, int index) { - int idx = (index * mlen) / 64; - int pos = (index * mlen) % 64; + int idx = index / 64; + int pos = index % 64; return (((uint64_t *)v0)[idx] >> pos) & 1; } @@ -277,12 +277,11 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, { uint32_t i, k; uint32_t nf = vext_nf(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, base + stride * i, nf * msz, ra, access_type); @@ -290,7 +289,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, /* do real access */ for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -506,12 +505,11 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t i, k; uint32_t nf = vext_nf(desc); uint32_t vm = vext_vm(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, get_index_addr(base, i, vs2), nf * msz, ra, @@ -520,7 +518,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, /* load bytes from guest memory */ for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -604,7 +602,6 @@ vext_ldff(void *vd, void *v0, target_ulong base, { void *host; uint32_t i, k, vl = 0; - uint32_t mlen = vext_mlen(desc); uint32_t nf = vext_nf(desc); uint32_t vm = vext_vm(desc); uint32_t vlmax = vext_maxsz(desc) / esz; @@ -612,7 +609,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } addr = base + nf * i * msz; @@ -653,7 +650,7 @@ ProbeSuccess: } for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -784,18 +781,17 @@ vext_amo_noatomic(void *vs3, void *v0, target_ulong base, target_long addr; uint32_t wd = vext_wd(desc); uint32_t vm = vext_vm(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_LOAD); probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_STORE); } for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } addr = get_index_addr(base, i, vs2); @@ -911,13 +907,12 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, opivv2_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, vs1, vs2, i); @@ -976,13 +971,12 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2, opivx2_fn fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, s1, vs2, i); @@ -1172,7 +1166,6 @@ GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -1181,7 +1174,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ *((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \ } \ @@ -1202,7 +1195,6 @@ GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -1210,7 +1202,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\ } \ @@ -1235,7 +1227,6 @@ GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ uint32_t i; \ @@ -1243,12 +1234,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ - vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1, carry));\ + vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1266,20 +1257,19 @@ GEN_VEXT_VMADC_VVM(vmsbc_vvm_d, uint64_t, H8, DO_MSBC) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)(target_long)s1, carry)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1353,7 +1343,6 @@ GEN_VEXT_VX(vxor_vx_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(TS1); \ @@ -1361,7 +1350,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ TS1 s1 = *((TS1 *)vs1 + HS1(i)); \ @@ -1391,7 +1380,6 @@ GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(TD); \ @@ -1399,7 +1387,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ @@ -1448,7 +1436,6 @@ GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -1457,13 +1444,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1)); \ + vext_set_elem_mask(vd, i, DO_OP(s2, s1)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1501,7 +1488,6 @@ GEN_VEXT_CMP_VV(vmsle_vv_d, int64_t, H8, DO_MSLE) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -1509,14 +1495,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)(target_long)s1)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -2078,14 +2064,13 @@ GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - ETYPE *vt = (!vext_elem_mask(v0, mlen, i) ? vs2 : vs1); \ + ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \ *((ETYPE *)vd + H(i)) = *(vt + H(i)); \ } \ CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ @@ -2100,7 +2085,6 @@ GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -2108,7 +2092,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - ETYPE d = (!vext_elem_mask(v0, mlen, i) ? s2 : \ + ETYPE d = (!vext_elem_mask(v0, i) ? s2 : \ (ETYPE)(target_long)s1); \ *((ETYPE *)vd + H(i)) = d; \ } \ @@ -2146,11 +2130,11 @@ do_##NAME(void *vd, void *vs1, void *vs2, int i, \ static inline void vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, - uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + uint32_t vl, uint32_t vm, int vxrm, opivv2_rm_fn *fn) { for (uint32_t i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, vs1, vs2, i, env, vxrm); @@ -2164,26 +2148,25 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2, opivv2_rm_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; switch (env->vxrm) { case 0: /* rnu */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 0, fn); + env, vl, vm, 0, fn); break; case 1: /* rne */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 1, fn); + env, vl, vm, 1, fn); break; case 2: /* rdn */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 2, fn); + env, vl, vm, 2, fn); break; default: /* rod */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 3, fn); + env, vl, vm, 3, fn); break; } @@ -2266,11 +2249,11 @@ do_##NAME(void *vd, target_long s1, void *vs2, int i, \ static inline void vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2, CPURISCVState *env, - uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + uint32_t vl, uint32_t vm, int vxrm, opivx2_rm_fn *fn) { for (uint32_t i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, s1, vs2, i, env, vxrm); @@ -2284,26 +2267,25 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2, opivx2_rm_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; switch (env->vxrm) { case 0: /* rnu */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 0, fn); + env, vl, vm, 0, fn); break; case 1: /* rne */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 1, fn); + env, vl, vm, 1, fn); break; case 2: /* rdn */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 2, fn); + env, vl, vm, 2, fn); break; default: /* rod */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 3, fn); + env, vl, vm, 3, fn); break; } @@ -3188,13 +3170,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs1, vs2, i, env); \ @@ -3223,13 +3204,12 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, s1, vs2, i, env); \ @@ -3794,7 +3774,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -3803,7 +3782,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ return; \ } \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs2, i, env); \ @@ -3935,7 +3914,6 @@ GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -3944,14 +3922,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, s1, &env->fp_status)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -3963,7 +3941,6 @@ GEN_VEXT_CMP_VV_ENV(vmfeq_vv_d, uint64_t, H8, float64_eq_quiet) void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -3971,14 +3948,14 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)s1, &env->fp_status)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -4092,13 +4069,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs2, i); \ @@ -4175,7 +4151,6 @@ GEN_VEXT_V(vfclass_v_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ @@ -4185,7 +4160,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ *((ETYPE *)vd + H(i)) \ - = (!vm && !vext_elem_mask(v0, mlen, i) ? s2 : s1); \ + = (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \ } \ CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ } @@ -4316,7 +4291,6 @@ GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl) void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -4325,7 +4299,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ \ for (i = 0; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ s1 = OP(s1, (TD)s2); \ @@ -4399,7 +4373,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -4408,7 +4381,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ \ for (i = 0; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ s1 = OP(s1, (TD)s2, &env->fp_status); \ @@ -4437,7 +4410,6 @@ GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq) void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; @@ -4446,7 +4418,7 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, for (i = 0; i < vl; i++) { uint16_t s2 = *((uint16_t *)vs2 + H2(i)); - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } s1 = float32_add(s1, float16_to_float32(s2, true, &env->fp_status), @@ -4459,7 +4431,6 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; @@ -4468,7 +4439,7 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, for (i = 0; i < vl; i++) { uint32_t s2 = *((uint32_t *)vs2 + H4(i)); - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } s1 = float64_add(s1, float32_to_float64(s2, &env->fp_status), @@ -4487,19 +4458,18 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vl = env->vl; \ uint32_t i; \ int a, b; \ \ for (i = 0; i < vl; i++) { \ - a = vext_elem_mask(vs1, mlen, i); \ - b = vext_elem_mask(vs2, mlen, i); \ - vext_set_elem_mask(vd, mlen, i, OP(b, a)); \ + a = vext_elem_mask(vs1, i); \ + b = vext_elem_mask(vs2, i); \ + vext_set_elem_mask(vd, i, OP(b, a)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -4523,14 +4493,13 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env, uint32_t desc) { target_ulong cnt = 0; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; for (i = 0; i < vl; i++) { - if (vm || vext_elem_mask(v0, mlen, i)) { - if (vext_elem_mask(vs2, mlen, i)) { + if (vm || vext_elem_mask(v0, i)) { + if (vext_elem_mask(vs2, i)) { cnt++; } } @@ -4542,14 +4511,13 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env, target_ulong HELPER(vmfirst_m)(void *v0, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; for (i = 0; i < vl; i++) { - if (vm || vext_elem_mask(v0, mlen, i)) { - if (vext_elem_mask(vs2, mlen, i)) { + if (vm || vext_elem_mask(v0, i)) { + if (vext_elem_mask(vs2, i)) { return i; } } @@ -4566,39 +4534,38 @@ enum set_mask_type { static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, uint32_t desc, enum set_mask_type type) { - uint32_t mlen = vext_mlen(desc); - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; + uint32_t vlmax = env_archcpu(env)->cfg.vlen; uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; bool first_mask_bit = false; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } /* write a zero to all following active elements */ if (first_mask_bit) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); continue; } - if (vext_elem_mask(vs2, mlen, i)) { + if (vext_elem_mask(vs2, i)) { first_mask_bit = true; if (type == BEFORE_FIRST) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } else { - vext_set_elem_mask(vd, mlen, i, 1); + vext_set_elem_mask(vd, i, 1); } } else { if (type == ONLY_FIRST) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } else { - vext_set_elem_mask(vd, mlen, i, 1); + vext_set_elem_mask(vd, i, 1); } } } for (; i < vlmax; i++) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } } @@ -4625,19 +4592,18 @@ void HELPER(vmsof_m)(void *vd, void *v0, void *vs2, CPURISCVState *env, void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t sum = 0; \ int i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = sum; \ - if (vext_elem_mask(vs2, mlen, i)) { \ + if (vext_elem_mask(vs2, i)) { \ sum++; \ } \ } \ @@ -4653,14 +4619,13 @@ GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq) #define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN) \ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ int i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = i; \ @@ -4682,14 +4647,13 @@ GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ target_ulong offset = s1, i; \ \ for (i = offset; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \ @@ -4707,15 +4671,14 @@ GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ target_ulong offset = s1, i; \ \ for (i = 0; i < vl; ++i) { \ target_ulong j = i + offset; \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = j >= vlmax ? 0 : *((ETYPE *)vs2 + H(j)); \ @@ -4733,14 +4696,13 @@ GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (i == 0) { \ @@ -4762,14 +4724,13 @@ GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (i == vl - 1) { \ @@ -4792,14 +4753,13 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t index, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ index = *((ETYPE *)vs1 + H(i)); \ @@ -4822,14 +4782,13 @@ GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t index = s1, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (index >= vlmax) { \ @@ -4852,13 +4811,12 @@ GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vl = env->vl; \ uint32_t num = 0, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vext_elem_mask(vs1, mlen, i)) { \ + if (!vext_elem_mask(vs1, i)) { \ continue; \ } \ *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \ -- 2.17.1
WARNING: multiple messages have this Message-ID (diff)
From: frank.chang@sifive.com To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: Frank Chang <frank.chang@sifive.com>, Palmer Dabbelt <palmer@dabbelt.com>, Alistair Francis <Alistair.Francis@wdc.com>, Sagar Karandikar <sagark@eecs.berkeley.edu>, Bastian Koppelmann <kbastian@mail.uni-paderborn.de>, Richard Henderson <richard.henderson@linaro.org>, LIU Zhiwei <zhiwei_liu@c-sky.com> Subject: [PATCH v7 11/75] target/riscv: rvv-1.0: remove MLEN calculations Date: Fri, 26 Feb 2021 11:17:55 +0800 [thread overview] Message-ID: <20210226031902.23656-12-frank.chang@sifive.com> (raw) In-Reply-To: <20210226031902.23656-1-frank.chang@sifive.com> From: Frank Chang <frank.chang@sifive.com> As in RVV 1.0 design, MLEN is hardcoded with value 1 (Section 4.5). Thus, remove all MLEN related calculations. Signed-off-by: Frank Chang <frank.chang@sifive.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> --- target/riscv/insn_trans/trans_rvv.c.inc | 35 +--- target/riscv/internals.h | 9 +- target/riscv/translate.c | 2 - target/riscv/vector_helper.c | 250 ++++++++++-------------- 4 files changed, 110 insertions(+), 186 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 56ce39e769a..46e18a62b59 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -247,7 +247,6 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -300,7 +299,6 @@ static bool st_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -387,7 +385,6 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -426,7 +423,6 @@ static bool st_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) gen_helper_vsse_v_w, gen_helper_vsse_v_d } }; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -518,7 +514,6 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -570,7 +565,6 @@ static bool st_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -649,7 +643,6 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq) return false; } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, NF, a->nf); @@ -760,7 +753,6 @@ static bool amo_op(DisasContext *s, arg_rwdvm *a, uint8_t seq) } } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); data = FIELD_DP32(data, VDATA, WD, a->wd); @@ -839,7 +831,6 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn, } else { uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -885,7 +876,6 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm, src1 = tcg_temp_new(); gen_get_gpr(src1, rs1); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data)); @@ -1034,7 +1024,6 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm, } else { src1 = tcg_const_tl(sextract64(imm, 0, 5)); } - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data)); @@ -1130,7 +1119,6 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a, TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -1219,7 +1207,6 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a, TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), @@ -1298,7 +1285,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1489,7 +1475,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1859,7 +1844,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -1932,7 +1916,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_d, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -1973,7 +1956,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2011,7 +1993,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -2048,7 +2029,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2084,7 +2064,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ gen_helper_##NAME##_h, gen_helper_##NAME##_w, \ }; \ gen_set_rm(s, 7); \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ @@ -2164,7 +2143,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2307,7 +2285,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2356,7 +2333,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ gen_set_rm(s, 7); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ @@ -2419,7 +2395,6 @@ static bool trans_##NAME(DisasContext *s, arg_r *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = 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), \ @@ -2449,7 +2424,6 @@ static bool trans_vmpopc_m(DisasContext *s, arg_rmr *a) TCGv dst; TCGv_i32 desc; uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -2481,7 +2455,6 @@ static bool trans_vmfirst_m(DisasContext *s, arg_rmr *a) TCGv dst; TCGv_i32 desc; uint32_t data = 0; - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); @@ -2517,7 +2490,6 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ TCGLabel *over = gen_new_label(); \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), \ @@ -2545,7 +2517,6 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); static gen_helper_gvec_3_ptr * const fns[4] = { @@ -2572,7 +2543,6 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = FIELD_DP32(data, VDATA, VM, a->vm); data = FIELD_DP32(data, VDATA, LMUL, s->lmul); static gen_helper_gvec_2_ptr * const fns[4] = { @@ -2863,7 +2833,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a) } if (a->vm && s->vl_eq_vlmax) { - int vlmax = s->vlen / s->mlen; + int vlmax = s->vlen; TCGv_i64 dest = tcg_temp_new_i64(); if (a->rs1 == 0) { @@ -2894,7 +2864,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a) } if (a->vm && s->vl_eq_vlmax) { - if (a->rs1 >= s->vlen / s->mlen) { + if (a->rs1 >= s->vlen) { tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), 0); } else { @@ -2934,7 +2904,6 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r *a) TCGLabel *over = gen_new_label(); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); - data = FIELD_DP32(data, VDATA, MLEN, s->mlen); data = 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), diff --git a/target/riscv/internals.h b/target/riscv/internals.h index b15ad394bb9..c3bbeea9a94 100644 --- a/target/riscv/internals.h +++ b/target/riscv/internals.h @@ -22,11 +22,10 @@ #include "hw/registerfields.h" /* share data between vector helpers and decode code */ -FIELD(VDATA, MLEN, 0, 8) -FIELD(VDATA, VM, 8, 1) -FIELD(VDATA, LMUL, 9, 2) -FIELD(VDATA, NF, 11, 4) -FIELD(VDATA, WD, 11, 1) +FIELD(VDATA, VM, 0, 1) +FIELD(VDATA, LMUL, 1, 3) +FIELD(VDATA, NF, 4, 4) +FIELD(VDATA, WD, 4, 1) /* float point classify helpers */ target_ulong fclass_h(uint64_t frs1); diff --git a/target/riscv/translate.c b/target/riscv/translate.c index fdb0a83a610..6e1896188c0 100644 --- a/target/riscv/translate.c +++ b/target/riscv/translate.c @@ -63,7 +63,6 @@ typedef struct DisasContext { uint8_t lmul; uint8_t sew; uint16_t vlen; - uint16_t mlen; bool vl_eq_vlmax; CPUState *cs; } DisasContext; @@ -855,7 +854,6 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL); ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW); ctx->lmul = FIELD_EX32(tb_flags, TB_FLAGS, LMUL); - ctx->mlen = 1 << (ctx->sew + 3 - ctx->lmul); ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX); ctx->cs = cs; } diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index bc3f212ceac..12301e943e6 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -81,11 +81,6 @@ static inline uint32_t vext_nf(uint32_t desc) return FIELD_EX32(simd_data(desc), VDATA, NF); } -static inline uint32_t vext_mlen(uint32_t desc) -{ - return FIELD_EX32(simd_data(desc), VDATA, MLEN); -} - static inline uint32_t vext_vm(uint32_t desc) { return FIELD_EX32(simd_data(desc), VDATA, VM); @@ -188,19 +183,24 @@ static void clearq(void *vd, uint32_t idx, uint32_t cnt, uint32_t tot) vext_clear(cur, cnt, tot); } -static inline void vext_set_elem_mask(void *v0, int mlen, int index, +static inline void vext_set_elem_mask(void *v0, int index, uint8_t value) { - int idx = (index * mlen) / 64; - int pos = (index * mlen) % 64; + int idx = index / 64; + int pos = index % 64; uint64_t old = ((uint64_t *)v0)[idx]; - ((uint64_t *)v0)[idx] = deposit64(old, pos, mlen, value); + ((uint64_t *)v0)[idx] = deposit64(old, pos, 1, value); } -static inline int vext_elem_mask(void *v0, int mlen, int index) +/* + * Earlier designs (pre-0.9) had a varying number of bits + * per mask value (MLEN). In the 0.9 design, MLEN=1. + * (Section 4.5) + */ +static inline int vext_elem_mask(void *v0, int index) { - int idx = (index * mlen) / 64; - int pos = (index * mlen) % 64; + int idx = index / 64; + int pos = index % 64; return (((uint64_t *)v0)[idx] >> pos) & 1; } @@ -277,12 +277,11 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, { uint32_t i, k; uint32_t nf = vext_nf(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, base + stride * i, nf * msz, ra, access_type); @@ -290,7 +289,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base, /* do real access */ for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -506,12 +505,11 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, uint32_t i, k; uint32_t nf = vext_nf(desc); uint32_t vm = vext_vm(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, get_index_addr(base, i, vs2), nf * msz, ra, @@ -520,7 +518,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base, /* load bytes from guest memory */ for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -604,7 +602,6 @@ vext_ldff(void *vd, void *v0, target_ulong base, { void *host; uint32_t i, k, vl = 0; - uint32_t mlen = vext_mlen(desc); uint32_t nf = vext_nf(desc); uint32_t vm = vext_vm(desc); uint32_t vlmax = vext_maxsz(desc) / esz; @@ -612,7 +609,7 @@ vext_ldff(void *vd, void *v0, target_ulong base, /* probe every access*/ for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } addr = base + nf * i * msz; @@ -653,7 +650,7 @@ ProbeSuccess: } for (i = 0; i < env->vl; i++) { k = 0; - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } while (k < nf) { @@ -784,18 +781,17 @@ vext_amo_noatomic(void *vs3, void *v0, target_ulong base, target_long addr; uint32_t wd = vext_wd(desc); uint32_t vm = vext_vm(desc); - uint32_t mlen = vext_mlen(desc); uint32_t vlmax = vext_maxsz(desc) / esz; for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_LOAD); probe_pages(env, get_index_addr(base, i, vs2), msz, ra, MMU_DATA_STORE); } for (i = 0; i < env->vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } addr = get_index_addr(base, i, vs2); @@ -911,13 +907,12 @@ static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2, opivv2_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, vs1, vs2, i); @@ -976,13 +971,12 @@ static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2, opivx2_fn fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, s1, vs2, i); @@ -1172,7 +1166,6 @@ GEN_VEXT_VX(vwsub_wx_w, 4, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -1181,7 +1174,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ *((ETYPE *)vd + H(i)) = DO_OP(s2, s1, carry); \ } \ @@ -1202,7 +1195,6 @@ GEN_VEXT_VADC_VVM(vsbc_vvm_d, uint64_t, H8, DO_VSBC, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -1210,7 +1202,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\ } \ @@ -1235,7 +1227,6 @@ GEN_VEXT_VADC_VXM(vsbc_vxm_d, uint64_t, H8, DO_VSBC, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ uint32_t i; \ @@ -1243,12 +1234,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ - vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1, carry));\ + vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1266,20 +1257,19 @@ GEN_VEXT_VMADC_VVM(vmsbc_vvm_d, uint64_t, H8, DO_MSBC) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - uint8_t carry = vext_elem_mask(v0, mlen, i); \ + uint8_t carry = vext_elem_mask(v0, i); \ \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)(target_long)s1, carry)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1353,7 +1343,6 @@ GEN_VEXT_VX(vxor_vx_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(TS1); \ @@ -1361,7 +1350,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ TS1 s1 = *((TS1 *)vs1 + HS1(i)); \ @@ -1391,7 +1380,6 @@ GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(TD); \ @@ -1399,7 +1387,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ @@ -1448,7 +1436,6 @@ GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -1457,13 +1444,13 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, DO_OP(s2, s1)); \ + vext_set_elem_mask(vd, i, DO_OP(s2, s1)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -1501,7 +1488,6 @@ GEN_VEXT_CMP_VV(vmsle_vv_d, int64_t, H8, DO_MSLE) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -1509,14 +1495,14 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)(target_long)s1)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -2078,14 +2064,13 @@ GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - ETYPE *vt = (!vext_elem_mask(v0, mlen, i) ? vs2 : vs1); \ + ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \ *((ETYPE *)vd + H(i)) = *(vt + H(i)); \ } \ CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ @@ -2100,7 +2085,6 @@ GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ uint32_t vlmax = vext_maxsz(desc) / esz; \ @@ -2108,7 +2092,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - ETYPE d = (!vext_elem_mask(v0, mlen, i) ? s2 : \ + ETYPE d = (!vext_elem_mask(v0, i) ? s2 : \ (ETYPE)(target_long)s1); \ *((ETYPE *)vd + H(i)) = d; \ } \ @@ -2146,11 +2130,11 @@ do_##NAME(void *vd, void *vs1, void *vs2, int i, \ static inline void vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, - uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + uint32_t vl, uint32_t vm, int vxrm, opivv2_rm_fn *fn) { for (uint32_t i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, vs1, vs2, i, env, vxrm); @@ -2164,26 +2148,25 @@ vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2, opivv2_rm_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; switch (env->vxrm) { case 0: /* rnu */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 0, fn); + env, vl, vm, 0, fn); break; case 1: /* rne */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 1, fn); + env, vl, vm, 1, fn); break; case 2: /* rdn */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 2, fn); + env, vl, vm, 2, fn); break; default: /* rod */ vext_vv_rm_1(vd, v0, vs1, vs2, - env, vl, vm, mlen, 3, fn); + env, vl, vm, 3, fn); break; } @@ -2266,11 +2249,11 @@ do_##NAME(void *vd, target_long s1, void *vs2, int i, \ static inline void vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2, CPURISCVState *env, - uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm, + uint32_t vl, uint32_t vm, int vxrm, opivx2_rm_fn *fn) { for (uint32_t i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } fn(vd, s1, vs2, i, env, vxrm); @@ -2284,26 +2267,25 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2, opivx2_rm_fn *fn, clear_fn *clearfn) { uint32_t vlmax = vext_maxsz(desc) / esz; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; switch (env->vxrm) { case 0: /* rnu */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 0, fn); + env, vl, vm, 0, fn); break; case 1: /* rne */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 1, fn); + env, vl, vm, 1, fn); break; case 2: /* rdn */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 2, fn); + env, vl, vm, 2, fn); break; default: /* rod */ vext_vx_rm_1(vd, v0, s1, vs2, - env, vl, vm, mlen, 3, fn); + env, vl, vm, 3, fn); break; } @@ -3188,13 +3170,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs1, vs2, i, env); \ @@ -3223,13 +3204,12 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, s1, vs2, i, env); \ @@ -3794,7 +3774,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -3803,7 +3782,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ return; \ } \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs2, i, env); \ @@ -3935,7 +3914,6 @@ GEN_VEXT_VF(vfsgnjx_vf_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -3944,14 +3922,14 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s1 = *((ETYPE *)vs1 + H(i)); \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, s1, &env->fp_status)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -3963,7 +3941,6 @@ GEN_VEXT_CMP_VV_ENV(vmfeq_vv_d, uint64_t, H8, float64_eq_quiet) void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t vlmax = vext_maxsz(desc) / sizeof(ETYPE); \ @@ -3971,14 +3948,14 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ - vext_set_elem_mask(vd, mlen, i, \ + vext_set_elem_mask(vd, i, \ DO_OP(s2, (ETYPE)s1, &env->fp_status)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -4092,13 +4069,12 @@ void HELPER(NAME)(void *vd, void *v0, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ uint32_t vlmax = vext_maxsz(desc) / ESZ; \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ do_##NAME(vd, vs2, i); \ @@ -4175,7 +4151,6 @@ GEN_VEXT_V(vfclass_v_d, 8, 8, clearq) void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t esz = sizeof(ETYPE); \ @@ -4185,7 +4160,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ for (i = 0; i < vl; i++) { \ ETYPE s2 = *((ETYPE *)vs2 + H(i)); \ *((ETYPE *)vd + H(i)) \ - = (!vm && !vext_elem_mask(v0, mlen, i) ? s2 : s1); \ + = (!vm && !vext_elem_mask(v0, i) ? s2 : s1); \ } \ CLEAR_FN(vd, vl, vl * esz, vlmax * esz); \ } @@ -4316,7 +4291,6 @@ GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl) void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -4325,7 +4299,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ \ for (i = 0; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ s1 = OP(s1, (TD)s2); \ @@ -4399,7 +4373,6 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ @@ -4408,7 +4381,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ \ for (i = 0; i < vl; i++) { \ TS2 s2 = *((TS2 *)vs2 + HS2(i)); \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ s1 = OP(s1, (TD)s2, &env->fp_status); \ @@ -4437,7 +4410,6 @@ GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, clearq) void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; @@ -4446,7 +4418,7 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, for (i = 0; i < vl; i++) { uint16_t s2 = *((uint16_t *)vs2 + H2(i)); - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } s1 = float32_add(s1, float16_to_float32(s2, true, &env->fp_status), @@ -4459,7 +4431,6 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; uint32_t i; @@ -4468,7 +4439,7 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, for (i = 0; i < vl; i++) { uint32_t s2 = *((uint32_t *)vs2 + H4(i)); - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } s1 = float64_add(s1, float32_to_float64(s2, &env->fp_status), @@ -4487,19 +4458,18 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vl = env->vl; \ uint32_t i; \ int a, b; \ \ for (i = 0; i < vl; i++) { \ - a = vext_elem_mask(vs1, mlen, i); \ - b = vext_elem_mask(vs2, mlen, i); \ - vext_set_elem_mask(vd, mlen, i, OP(b, a)); \ + a = vext_elem_mask(vs1, i); \ + b = vext_elem_mask(vs2, i); \ + vext_set_elem_mask(vd, i, OP(b, a)); \ } \ for (; i < vlmax; i++) { \ - vext_set_elem_mask(vd, mlen, i, 0); \ + vext_set_elem_mask(vd, i, 0); \ } \ } @@ -4523,14 +4493,13 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env, uint32_t desc) { target_ulong cnt = 0; - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; for (i = 0; i < vl; i++) { - if (vm || vext_elem_mask(v0, mlen, i)) { - if (vext_elem_mask(vs2, mlen, i)) { + if (vm || vext_elem_mask(v0, i)) { + if (vext_elem_mask(vs2, i)) { cnt++; } } @@ -4542,14 +4511,13 @@ target_ulong HELPER(vmpopc_m)(void *v0, void *vs2, CPURISCVState *env, target_ulong HELPER(vmfirst_m)(void *v0, void *vs2, CPURISCVState *env, uint32_t desc) { - uint32_t mlen = vext_mlen(desc); uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; for (i = 0; i < vl; i++) { - if (vm || vext_elem_mask(v0, mlen, i)) { - if (vext_elem_mask(vs2, mlen, i)) { + if (vm || vext_elem_mask(v0, i)) { + if (vext_elem_mask(vs2, i)) { return i; } } @@ -4566,39 +4534,38 @@ enum set_mask_type { static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env, uint32_t desc, enum set_mask_type type) { - uint32_t mlen = vext_mlen(desc); - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; + uint32_t vlmax = env_archcpu(env)->cfg.vlen; uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; int i; bool first_mask_bit = false; for (i = 0; i < vl; i++) { - if (!vm && !vext_elem_mask(v0, mlen, i)) { + if (!vm && !vext_elem_mask(v0, i)) { continue; } /* write a zero to all following active elements */ if (first_mask_bit) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); continue; } - if (vext_elem_mask(vs2, mlen, i)) { + if (vext_elem_mask(vs2, i)) { first_mask_bit = true; if (type == BEFORE_FIRST) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } else { - vext_set_elem_mask(vd, mlen, i, 1); + vext_set_elem_mask(vd, i, 1); } } else { if (type == ONLY_FIRST) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } else { - vext_set_elem_mask(vd, mlen, i, 1); + vext_set_elem_mask(vd, i, 1); } } } for (; i < vlmax; i++) { - vext_set_elem_mask(vd, mlen, i, 0); + vext_set_elem_mask(vd, i, 0); } } @@ -4625,19 +4592,18 @@ void HELPER(vmsof_m)(void *vd, void *v0, void *vs2, CPURISCVState *env, void HELPER(NAME)(void *vd, void *v0, void *vs2, CPURISCVState *env, \ uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t sum = 0; \ int i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = sum; \ - if (vext_elem_mask(vs2, mlen, i)) { \ + if (vext_elem_mask(vs2, i)) { \ sum++; \ } \ } \ @@ -4653,14 +4619,13 @@ GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq) #define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN) \ void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ int i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = i; \ @@ -4682,14 +4647,13 @@ GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ target_ulong offset = s1, i; \ \ for (i = offset; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \ @@ -4707,15 +4671,14 @@ GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ target_ulong offset = s1, i; \ \ for (i = 0; i < vl; ++i) { \ target_ulong j = i + offset; \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ *((ETYPE *)vd + H(i)) = j >= vlmax ? 0 : *((ETYPE *)vs2 + H(j)); \ @@ -4733,14 +4696,13 @@ GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (i == 0) { \ @@ -4762,14 +4724,13 @@ GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (i == vl - 1) { \ @@ -4792,14 +4753,13 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t index, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ index = *((ETYPE *)vs1 + H(i)); \ @@ -4822,14 +4782,13 @@ GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ uint32_t index = s1, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + if (!vm && !vext_elem_mask(v0, i)) { \ continue; \ } \ if (index >= vlmax) { \ @@ -4852,13 +4811,12 @@ GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq) void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ - uint32_t mlen = vext_mlen(desc); \ - uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \ + uint32_t vlmax = env_archcpu(env)->cfg.vlen; \ uint32_t vl = env->vl; \ uint32_t num = 0, i; \ \ for (i = 0; i < vl; i++) { \ - if (!vext_elem_mask(vs1, mlen, i)) { \ + if (!vext_elem_mask(vs1, i)) { \ continue; \ } \ *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i)); \ -- 2.17.1
next prev parent reply other threads:[~2021-02-26 3:29 UTC|newest] Thread overview: 151+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-02-26 3:17 [PATCH v7 00/75] support vector extension v1.0 frank.chang 2021-02-26 3:17 ` [PATCH v7 01/75] target/riscv: drop vector 0.7.1 and add 1.0 support frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 02/75] target/riscv: Use FIELD_EX32() to extract wd field frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 03/75] target/riscv: rvv-1.0: add mstatus VS field frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 04/75] target/riscv: rvv-1.0: add sstatus " frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 05/75] target/riscv: rvv-1.0: introduce writable misa.v field frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 06/75] target/riscv: rvv-1.0: add translation-time vector context status frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 07/75] target/riscv: rvv-1.0: remove rvv related codes from fcsr registers frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 08/75] target/riscv: rvv-1.0: add vcsr register frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 09/75] target/riscv: rvv-1.0: add vlenb register frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 10/75] target/riscv: rvv-1.0: check MSTATUS_VS when accessing vector csr registers frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` frank.chang [this message] 2021-02-26 3:17 ` [PATCH v7 11/75] target/riscv: rvv-1.0: remove MLEN calculations frank.chang 2021-02-26 3:17 ` [PATCH v7 12/75] target/riscv: rvv-1.0: add fractional LMUL frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 13/75] target/riscv: rvv-1.0: add VMA and VTA frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 14/75] target/riscv: rvv-1.0: update check functions frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:17 ` [PATCH v7 15/75] target/riscv: introduce more imm value modes in translator functions frank.chang 2021-02-26 3:17 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 16/75] target/riscv: rvv:1.0: add translation-time nan-box helper function frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 17/75] target/riscv: rvv-1.0: configure instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 18/75] target/riscv: rvv-1.0: stride load and store instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 19/75] target/riscv: rvv-1.0: index " frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 20/75] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 21/75] target/riscv: rvv-1.0: fault-only-first unit stride load frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 22/75] target/riscv: rvv-1.0: amo operations frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 23/75] target/riscv: rvv-1.0: load/store whole register instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 24/75] target/riscv: rvv-1.0: update vext_max_elems() for load/store insns frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 25/75] target/riscv: rvv-1.0: take fractional LMUL into vector max elements calculation frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 26/75] target/riscv: rvv-1.0: floating-point square-root instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 27/75] target/riscv: rvv-1.0: floating-point classify instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 28/75] target/riscv: rvv-1.0: mask population count instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 29/75] target/riscv: rvv-1.0: find-first-set mask bit instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 30/75] target/riscv: rvv-1.0: set-X-first mask bit instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 31/75] target/riscv: rvv-1.0: iota instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 32/75] target/riscv: rvv-1.0: element index instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 33/75] target/riscv: rvv-1.0: allow load element with sign-extended frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 34/75] target/riscv: rvv-1.0: register gather instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 35/75] target/riscv: rvv-1.0: integer scalar move instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 36/75] target/riscv: rvv-1.0: floating-point move instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 37/75] target/riscv: rvv-1.0: floating-point scalar move instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 38/75] target/riscv: rvv-1.0: whole register " frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 39/75] target/riscv: rvv-1.0: integer extension instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 40/75] target/riscv: rvv-1.0: single-width averaging add and subtract instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 41/75] target/riscv: rvv-1.0: single-width bit shift instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 42/75] target/riscv: rvv-1.0: integer add-with-carry/subtract-with-borrow frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 43/75] target/riscv: rvv-1.0: narrowing integer right shift instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 44/75] target/riscv: rvv-1.0: widening integer multiply-add instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 45/75] target/riscv: rvv-1.0: single-width saturating add and subtract instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 46/75] target/riscv: rvv-1.0: integer comparison instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 47/75] target/riscv: rvv-1.0: floating-point compare instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 48/75] target/riscv: rvv-1.0: mask-register logical instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 49/75] target/riscv: rvv-1.0: slide instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 50/75] target/riscv: rvv-1.0: floating-point " frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 51/75] target/riscv: rvv-1.0: narrowing fixed-point clip instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 52/75] target/riscv: rvv-1.0: single-width floating-point reduction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 53/75] target/riscv: rvv-1.0: widening floating-point reduction instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 54/75] target/riscv: rvv-1.0: single-width scaling shift instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 55/75] target/riscv: rvv-1.0: remove widening saturating scaled multiply-add frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 56/75] target/riscv: rvv-1.0: remove vmford.vv and vmford.vf frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 57/75] target/riscv: rvv-1.0: remove integer extract instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 58/75] target/riscv: rvv-1.0: floating-point min/max instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 59/75] target/riscv: introduce floating-point rounding mode enum frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 60/75] target/riscv: rvv-1.0: floating-point/integer type-convert instructions frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 61/75] target/riscv: rvv-1.0: widening floating-point/integer type-convert frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 62/75] target/riscv: add "set round to odd" rounding mode helper function frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 63/75] target/riscv: rvv-1.0: narrowing floating-point/integer type-convert frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 64/75] target/riscv: rvv-1.0: relax RV_VLEN_MAX to 1024-bits frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 65/75] target/riscv: rvv-1.0: implement vstart CSR frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 66/75] target/riscv: rvv-1.0: trigger illegal instruction exception if frm is not valid frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 67/75] target/riscv: rvv-1.0: set mstatus.SD bit when writing vector CSRs frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 68/75] target/riscv: gdb: support vector registers for rv64 & rv32 frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 69/75] target/riscv: rvv-1.0: floating-point reciprocal square-root estimate instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 70/75] target/riscv: rvv-1.0: floating-point reciprocal " frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 71/75] target/riscv: set mstatus.SD bit when writing fp CSRs frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 72/75] target/riscv: rvv-1.0: rename r2_zimm to r2_zimm11 frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 73/75] target/riscv: rvv-1.0: add vsetivli instruction frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 74/75] target/riscv: rvv-1.0: add evl parameter to vext_ldst_us() frank.chang 2021-02-26 3:18 ` frank.chang 2021-02-26 3:18 ` [PATCH v7 75/75] target/riscv: rvv-1.0: add vector unit-stride mask load/store insns frank.chang 2021-02-26 3:18 ` frank.chang
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20210226031902.23656-12-frank.chang@sifive.com \ --to=frank.chang@sifive.com \ --cc=Alistair.Francis@wdc.com \ --cc=kbastian@mail.uni-paderborn.de \ --cc=palmer@dabbelt.com \ --cc=qemu-devel@nongnu.org \ --cc=qemu-riscv@nongnu.org \ --cc=richard.henderson@linaro.org \ --cc=sagark@eecs.berkeley.edu \ --cc=zhiwei_liu@c-sky.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.