From 89a32de2d57591006d4a5d76e664b0b01c6998dc Mon Sep 17 00:00:00 2001 From: eopXD Date: Mon, 6 Jun 2022 06:16:51 +0000 Subject: target/riscv: rvv: Add tail agnostic for vector integer merge and move instructions Signed-off-by: eop Chen Reviewed-by: Frank Chang Reviewed-by: Weiwei Li Acked-by: Alistair Francis Message-Id: <165449614532.19704.7000832880482980398-10@git.sr.ht> Signed-off-by: Alistair Francis --- target/riscv/insn_trans/trans_rvv.c.inc | 12 ++++++++---- target/riscv/vector_helper.c | 20 ++++++++++++++++++++ 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index dbe687fb73..e75a2fd196 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -2086,12 +2086,13 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a) vext_check_isa_ill(s) && /* vmv.v.v has rs2 = 0 and vm = 1 */ vext_check_sss(s, a->rd, a->rs1, 0, 1)) { - if (s->vl_eq_vlmax) { + if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), MAXSZ(s), MAXSZ(s)); } else { uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); static gen_helper_gvec_2_ptr * const fns[4] = { gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h, gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d, @@ -2126,7 +2127,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) s1 = get_gpr(s, a->rs1, EXT_SIGN); - if (s->vl_eq_vlmax) { + if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), s1); } else { @@ -2134,6 +2135,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a) TCGv_i64 s1_i64 = tcg_temp_new_i64(); TCGv_ptr dest = tcg_temp_new_ptr(); uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); static gen_helper_vmv_vx * const fns[4] = { gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h, gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, @@ -2163,7 +2165,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) /* vmv.v.i has rs2 = 0 and vm = 1 */ vext_check_ss(s, a->rd, 0, 1)) { int64_t simm = sextract64(a->rs1, 0, 5); - if (s->vl_eq_vlmax) { + if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd), MAXSZ(s), MAXSZ(s), simm); mark_vs_dirty(s); @@ -2172,6 +2174,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a) TCGv_i64 s1; TCGv_ptr dest; uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); static gen_helper_vmv_vx * const fns[4] = { gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h, gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d, @@ -2743,7 +2746,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) TCGv_i64 t1; - if (s->vl_eq_vlmax) { + if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) { t1 = tcg_temp_new_i64(); /* NaN-box f[rs1] */ do_nanbox(s, t1, cpu_fpr[a->rs1]); @@ -2755,6 +2758,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a) TCGv_ptr dest; TCGv_i32 desc; uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); static gen_helper_vmv_vx * const fns[3] = { gen_helper_vmv_v_x_h, gen_helper_vmv_v_x_w, diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index a64506bf02..128238786e 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -1969,6 +1969,9 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \ uint32_t desc) \ { \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t total_elems = vext_get_total_elems(env, desc, esz); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ for (i = env->vstart; i < vl; i++) { \ @@ -1976,6 +1979,8 @@ void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env, \ *((ETYPE *)vd + H(i)) = s1; \ } \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \ } GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t, H1) @@ -1988,12 +1993,17 @@ void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env, \ uint32_t desc) \ { \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t total_elems = vext_get_total_elems(env, desc, esz); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ for (i = env->vstart; i < vl; i++) { \ *((ETYPE *)vd + H(i)) = (ETYPE)s1; \ } \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \ } GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t, H1) @@ -2006,6 +2016,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ CPURISCVState *env, uint32_t desc) \ { \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t total_elems = vext_get_total_elems(env, desc, esz); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ for (i = env->vstart; i < vl; i++) { \ @@ -2013,6 +2026,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ *((ETYPE *)vd + H(i)) = *(vt + H(i)); \ } \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \ } GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t, H1) @@ -2025,6 +2040,9 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ void *vs2, CPURISCVState *env, uint32_t desc) \ { \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(ETYPE); \ + uint32_t total_elems = vext_get_total_elems(env, desc, esz); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ \ for (i = env->vstart; i < vl; i++) { \ @@ -2034,6 +2052,8 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, \ *((ETYPE *)vd + H(i)) = d; \ } \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \ } GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t, H1) -- cgit v1.2.3