In these instructions vd is considered a source, so no overlap is allowed between vd and vs1/vs2. See:
https://github.com/riscv/riscv-isa-manual/issues/1789 Signed-off-by: Anton Blanchard <ant...@tenstorrent.com> --- target/riscv/insn_trans/trans_rvv.c.inc | 71 +++++++++++++++++++------ 1 file changed, 56 insertions(+), 15 deletions(-) diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 2741f8bd8e..715008db79 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -1505,6 +1505,16 @@ static bool opivv_widen_check(DisasContext *s, arg_rmrr *a) vext_check_dss(s, a->rd, a->rs1, a->rs2, a->vm); } +/* OPIVV with overwrite and WIDEN */ +static bool opivv_overwrite_widen_check(DisasContext *s, arg_rmrr *a) +{ + return require_rvv(s) && + vext_check_isa_ill(s) && + vext_check_dss(s, a->rd, a->rs1, a->rs2, a->vm) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs1, 1 << MAX(s->lmul, 0)) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs2, 1 << MAX(s->lmul, 0)); +} + static bool do_opivv_widen(DisasContext *s, arg_rmrr *a, gen_helper_gvec_4_ptr *fn, bool (*checkfn)(DisasContext *, arg_rmrr *)) @@ -1552,6 +1562,15 @@ static bool opivx_widen_check(DisasContext *s, arg_rmrr *a) vext_check_ds(s, a->rd, a->rs2, a->vm); } +/* OPIVX with overwrite and WIDEN */ +static bool opivx_overwrite_widen_check(DisasContext *s, arg_rmrr *a) +{ + return require_rvv(s) && + vext_check_isa_ill(s) && + vext_check_ds(s, a->rd, a->rs2, a->vm) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs2, 1 << MAX(s->lmul, 0)); +} + #define GEN_OPIVX_WIDEN_TRANS(NAME, CHECK) \ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ { \ @@ -2023,13 +2042,13 @@ GEN_OPIVX_TRANS(vmadd_vx, opivx_check) GEN_OPIVX_TRANS(vnmsub_vx, opivx_check) /* Vector Widening Integer Multiply-Add Instructions */ -GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_widen_check) -GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_widen_check) -GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx, opivx_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmacc_vx, opivx_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx, opivx_widen_check) -GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx, opivx_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmaccu_vv, opivv_overwrite_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmacc_vv, opivv_overwrite_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwmaccsu_vv, opivv_overwrite_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx, opivx_overwrite_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmacc_vx, opivx_overwrite_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx, opivx_overwrite_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx, opivx_overwrite_widen_check) /* Vector Integer Merge and Move Instructions */ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a) @@ -2370,6 +2389,18 @@ static bool opfvv_widen_check(DisasContext *s, arg_rmrr *a) vext_check_dss(s, a->rd, a->rs1, a->rs2, a->vm); } +/* Vector Widening Floating-Point Add/Subtract Instructions with overwrite */ +static bool opfvv_overwrite_widen_check(DisasContext *s, arg_rmrr *a) +{ + return require_rvv(s) && + require_rvf(s) && + require_scale_rvf(s) && + vext_check_isa_ill(s) && + vext_check_dss(s, a->rd, a->rs1, a->rs2, a->vm) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs1, 1 << MAX(s->lmul, 0)) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs2, 1 << MAX(s->lmul, 0)); +} + /* OPFVV with WIDEN */ #define GEN_OPFVV_WIDEN_TRANS(NAME, CHECK) \ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ @@ -2409,6 +2440,16 @@ static bool opfvf_widen_check(DisasContext *s, arg_rmrr *a) vext_check_ds(s, a->rd, a->rs2, a->vm); } +static bool opfvf_overwrite_widen_check(DisasContext *s, arg_rmrr *a) +{ + return require_rvv(s) && + require_rvf(s) && + require_scale_rvf(s) && + vext_check_isa_ill(s) && + vext_check_ds(s, a->rd, a->rs2, a->vm) && + !is_overlapped(a->rd, 1 << MAX(s->lmul+1, 0), a->rs2, 1 << MAX(s->lmul, 0)); +} + /* OPFVF with WIDEN */ #define GEN_OPFVF_WIDEN_TRANS(NAME, CHECK) \ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ @@ -2533,14 +2574,14 @@ GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check) GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check) /* Vector Widening Floating-Point Fused Multiply-Add Instructions */ -GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_widen_check) -GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_widen_check) -GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_widen_check) -GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_widen_check) -GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf, opfvf_widen_check) -GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf, opfvf_widen_check) -GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf, opfvf_widen_check) -GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf, opfvf_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwmacc_vv, opfvv_overwrite_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwnmacc_vv, opfvv_overwrite_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwmsac_vv, opfvv_overwrite_widen_check) +GEN_OPFVV_WIDEN_TRANS(vfwnmsac_vv, opfvv_overwrite_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwmacc_vf, opfvf_overwrite_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwnmacc_vf, opfvf_overwrite_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwmsac_vf, opfvf_overwrite_widen_check) +GEN_OPFVF_WIDEN_TRANS(vfwnmsac_vf, opfvf_overwrite_widen_check) /* Vector Floating-Point Square-Root Instruction */ -- 2.34.1
