Re: [PATCH v6 32/61] target/riscv: vector single-width floating-point multiply/divide instructions

[Alistair Francis]

On Tue, Mar 17, 2020 at 9:11 AM LIU Zhiwei <address@hidden> wrote:
>
> Signed-off-by: LIU Zhiwei <address@hidden>
> Reviewed-by: Richard Henderson <address@hidden>

Reviewed-by: Alistair Francis <address@hidden>

Alistair

> ---
>  target/riscv/helper.h                   | 16 +++++++++
>  target/riscv/insn32.decode              |  5 +++
>  target/riscv/insn_trans/trans_rvv.inc.c |  7 ++++
>  target/riscv/vector_helper.c            | 48 +++++++++++++++++++++++++
>  4 files changed, 76 insertions(+)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index 384d661283..abd0bbd2fc 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -826,3 +826,19 @@ DEF_HELPER_6(vfwadd_wf_h, void, ptr, ptr, i64, ptr, env, 
> i32)
>  DEF_HELPER_6(vfwadd_wf_w, void, ptr, ptr, i64, ptr, env, i32)
>  DEF_HELPER_6(vfwsub_wf_h, void, ptr, ptr, i64, ptr, env, i32)
>  DEF_HELPER_6(vfwsub_wf_w, void, ptr, ptr, i64, ptr, env, i32)
> +
> +DEF_HELPER_6(vfmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vfmul_vf_h, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfmul_vf_w, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfmul_vf_d, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfrdiv_vf_h, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfrdiv_vf_w, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfrdiv_vf_d, void, ptr, ptr, i64, ptr, env, i32)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index 68e9448842..16fd938261 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -456,6 +456,11 @@ vfwsub_vv       110010 . ..... ..... 001 ..... 1010111 
> @r_vm
>  vfwsub_vf       110010 . ..... ..... 101 ..... 1010111 @r_vm
>  vfwsub_wv       110110 . ..... ..... 001 ..... 1010111 @r_vm
>  vfwsub_wf       110110 . ..... ..... 101 ..... 1010111 @r_vm
> +vfmul_vv        100100 . ..... ..... 001 ..... 1010111 @r_vm
> +vfmul_vf        100100 . ..... ..... 101 ..... 1010111 @r_vm
> +vfdiv_vv        100000 . ..... ..... 001 ..... 1010111 @r_vm
> +vfdiv_vf        100000 . ..... ..... 101 ..... 1010111 @r_vm
> +vfrdiv_vf       100001 . ..... ..... 101 ..... 1010111 @r_vm
>
>  vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
>  vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
> diff --git a/target/riscv/insn_trans/trans_rvv.inc.c 
> b/target/riscv/insn_trans/trans_rvv.inc.c
> index 5ec5debc09..f6864b42bb 100644
> --- a/target/riscv/insn_trans/trans_rvv.inc.c
> +++ b/target/riscv/insn_trans/trans_rvv.inc.c
> @@ -1910,3 +1910,10 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a) 
>                   \
>  }
>  GEN_OPFWF_WIDEN_TRANS(vfwadd_wf)
>  GEN_OPFWF_WIDEN_TRANS(vfwsub_wf)
> +
> +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
> +GEN_OPFVV_TRANS(vfmul_vv, opfvv_check)
> +GEN_OPFVV_TRANS(vfdiv_vv, opfvv_check)
> +GEN_OPFVF_TRANS(vfmul_vf,  opfvf_check)
> +GEN_OPFVF_TRANS(vfdiv_vf,  opfvf_check)
> +GEN_OPFVF_TRANS(vfrdiv_vf,  opfvf_check)
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 16ba9148fb..f5f5897d12 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -3343,3 +3343,51 @@ RVVCALL(OPFVF2, vfwsub_wf_h, WOP_WUUU_H, H4, H2, 
> vfwsubw16)
>  RVVCALL(OPFVF2, vfwsub_wf_w, WOP_WUUU_W, H8, H4, vfwsubw32)
>  GEN_VEXT_VF(vfwsub_wf_h, 2, 4, clearl)
>  GEN_VEXT_VF(vfwsub_wf_w, 4, 8, clearq)
> +
> +/* Vector Single-Width Floating-Point Multiply/Divide Instructions */
> +RVVCALL(OPFVV2, vfmul_vv_h, OP_UUU_H, H2, H2, H2, float16_mul)
> +RVVCALL(OPFVV2, vfmul_vv_w, OP_UUU_W, H4, H4, H4, float32_mul)
> +RVVCALL(OPFVV2, vfmul_vv_d, OP_UUU_D, H8, H8, H8, float64_mul)
> +GEN_VEXT_VV_ENV(vfmul_vv_h, 2, 2, clearh)
> +GEN_VEXT_VV_ENV(vfmul_vv_w, 4, 4, clearl)
> +GEN_VEXT_VV_ENV(vfmul_vv_d, 8, 8, clearq)
> +RVVCALL(OPFVF2, vfmul_vf_h, OP_UUU_H, H2, H2, float16_mul)
> +RVVCALL(OPFVF2, vfmul_vf_w, OP_UUU_W, H4, H4, float32_mul)
> +RVVCALL(OPFVF2, vfmul_vf_d, OP_UUU_D, H8, H8, float64_mul)
> +GEN_VEXT_VF(vfmul_vf_h, 2, 2, clearh)
> +GEN_VEXT_VF(vfmul_vf_w, 4, 4, clearl)
> +GEN_VEXT_VF(vfmul_vf_d, 8, 8, clearq)
> +
> +RVVCALL(OPFVV2, vfdiv_vv_h, OP_UUU_H, H2, H2, H2, float16_div)
> +RVVCALL(OPFVV2, vfdiv_vv_w, OP_UUU_W, H4, H4, H4, float32_div)
> +RVVCALL(OPFVV2, vfdiv_vv_d, OP_UUU_D, H8, H8, H8, float64_div)
> +GEN_VEXT_VV_ENV(vfdiv_vv_h, 2, 2, clearh)
> +GEN_VEXT_VV_ENV(vfdiv_vv_w, 4, 4, clearl)
> +GEN_VEXT_VV_ENV(vfdiv_vv_d, 8, 8, clearq)
> +RVVCALL(OPFVF2, vfdiv_vf_h, OP_UUU_H, H2, H2, float16_div)
> +RVVCALL(OPFVF2, vfdiv_vf_w, OP_UUU_W, H4, H4, float32_div)
> +RVVCALL(OPFVF2, vfdiv_vf_d, OP_UUU_D, H8, H8, float64_div)
> +GEN_VEXT_VF(vfdiv_vf_h, 2, 2, clearh)
> +GEN_VEXT_VF(vfdiv_vf_w, 4, 4, clearl)
> +GEN_VEXT_VF(vfdiv_vf_d, 8, 8, clearq)
> +
> +static uint16_t float16_rdiv(uint16_t a, uint16_t b, float_status *s)
> +{
> +    return float16_div(b, a, s);
> +}
> +
> +static uint32_t float32_rdiv(uint32_t a, uint32_t b, float_status *s)
> +{
> +    return float32_div(b, a, s);
> +}
> +
> +static uint64_t float64_rdiv(uint64_t a, uint64_t b, float_status *s)
> +{
> +    return float64_div(b, a, s);
> +}
> +RVVCALL(OPFVF2, vfrdiv_vf_h, OP_UUU_H, H2, H2, float16_rdiv)
> +RVVCALL(OPFVF2, vfrdiv_vf_w, OP_UUU_W, H4, H4, float32_rdiv)
> +RVVCALL(OPFVF2, vfrdiv_vf_d, OP_UUU_D, H8, H8, float64_rdiv)
> +GEN_VEXT_VF(vfrdiv_vf_h, 2, 2, clearh)
> +GEN_VEXT_VF(vfrdiv_vf_w, 4, 4, clearl)
> +GEN_VEXT_VF(vfrdiv_vf_d, 8, 8, clearq)
> --
> 2.23.0
>