From: Max Chou <[email protected]> When XLEN is 32 and SEW is 64, the original implementation of vslide1up.vx and vslide1down.vx helper functions fills the 32-bit value of rs1 into the first element of the destination vector register (rd), which is a 64-bit element.
This commit attempted to resolve the issue by extending the rs1 value to 64 bits during the TCG translation phase to ensure that the helper functions won't lost the higer 32 bits. Signed-off-by: Max Chou <[email protected]> Acked-by: Alistair Francis <[email protected]> Message-ID: <[email protected]> Signed-off-by: Alistair Francis <[email protected]> (cherry picked from commit 81d1885dcc4424fec6761120f6e251eb3408fb8e) Signed-off-by: Michael Tokarev <[email protected]> diff --git a/target/riscv/helper.h b/target/riscv/helper.h index e2e883151d..ddb07ca3d1 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1101,14 +1101,14 @@ DEF_HELPER_6(vslidedown_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vslidedown_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vslidedown_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vslidedown_vx_d, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32) -DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfslide1up_vf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfslide1up_vf_w, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 445a0b72a5..b8919bb824 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -3494,7 +3494,6 @@ static bool slideup_check(DisasContext *s, arg_rmrr *a) } GEN_OPIVX_TRANS(vslideup_vx, slideup_check) -GEN_OPIVX_TRANS(vslide1up_vx, slideup_check) GEN_OPIVI_TRANS(vslideup_vi, IMM_ZX, vslideup_vx, slideup_check) static bool slidedown_check(DisasContext *s, arg_rmrr *a) @@ -3505,9 +3504,56 @@ static bool slidedown_check(DisasContext *s, arg_rmrr *a) } GEN_OPIVX_TRANS(vslidedown_vx, slidedown_check) -GEN_OPIVX_TRANS(vslide1down_vx, slidedown_check) GEN_OPIVI_TRANS(vslidedown_vi, IMM_ZX, vslidedown_vx, slidedown_check) +typedef void gen_helper_vslide1_vx(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_ptr, + TCGv_env, TCGv_i32); + +#define GEN_OPIVX_VSLIDE1_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + static gen_helper_vslide1_vx * const fns[4] = { \ + gen_helper_##NAME##_b, gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, gen_helper_##NAME##_d, \ + }; \ + \ + TCGv_ptr dest, src2, mask; \ + TCGv_i64 src1; \ + TCGv_i32 desc; \ + uint32_t data = 0; \ + \ + dest = tcg_temp_new_ptr(); \ + mask = tcg_temp_new_ptr(); \ + src2 = tcg_temp_new_ptr(); \ + src1 = tcg_temp_new_i64(); \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlenb, \ + s->cfg_ptr->vlenb, data)); \ + \ + tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd)); \ + tcg_gen_addi_ptr(src2, tcg_env, vreg_ofs(s, a->rs2)); \ + tcg_gen_addi_ptr(mask, tcg_env, vreg_ofs(s, 0)); \ + tcg_gen_ext_tl_i64(src1, get_gpr(s, a->rs1, EXT_SIGN)); \ + \ + fns[s->sew](dest, mask, src1, src2, tcg_env, desc); \ + \ + tcg_gen_movi_tl(cpu_vstart, 0); \ + finalize_rvv_inst(s); \ + \ + return true; \ + } \ + return false; \ +} + +GEN_OPIVX_VSLIDE1_TRANS(vslide1up_vx, slideup_check) +GEN_OPIVX_VSLIDE1_TRANS(vslide1down_vx, slidedown_check) + /* Vector Floating-Point Slide Instructions */ static bool fslideup_check(DisasContext *s, arg_rmrr *a) { diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 1012d38c8a..559c660566 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -5169,11 +5169,11 @@ GEN_VEXT_VSLIE1UP(16, H2) GEN_VEXT_VSLIE1UP(32, H4) GEN_VEXT_VSLIE1UP(64, H8) -#define GEN_VEXT_VSLIDE1UP_VX(NAME, BITWIDTH) \ -void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ - CPURISCVState *env, uint32_t desc) \ -{ \ - vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \ +#define GEN_VEXT_VSLIDE1UP_VX(NAME, BITWIDTH) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vslide1up_##BITWIDTH(vd, v0, s1, vs2, env, desc); \ } /* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */ @@ -5220,11 +5220,11 @@ GEN_VEXT_VSLIDE1DOWN(16, H2) GEN_VEXT_VSLIDE1DOWN(32, H4) GEN_VEXT_VSLIDE1DOWN(64, H8) -#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, BITWIDTH) \ -void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2, \ - CPURISCVState *env, uint32_t desc) \ -{ \ - vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \ +#define GEN_VEXT_VSLIDE1DOWN_VX(NAME, BITWIDTH) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + vslide1down_##BITWIDTH(vd, v0, s1, vs2, env, desc); \ } /* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */ -- 2.47.3
