Re: [PATCH v8 42/62] target/riscv: vector floating-point merge instructions

[Alistair Francis]

On Thu, May 21, 2020 at 4:09 AM LIU Zhiwei <zhiwei_liu@c-sky.com> wrote:
>
> Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Alistair

> ---
>  target/riscv/helper.h                   |  4 +++
>  target/riscv/insn32.decode              |  2 ++
>  target/riscv/insn_trans/trans_rvv.inc.c | 38 +++++++++++++++++++++++++
>  target/riscv/vector_helper.c            | 24 ++++++++++++++++
>  4 files changed, 68 insertions(+)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index 23b268df90..21054cc957 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -994,3 +994,7 @@ DEF_HELPER_6(vmford_vf_d, void, ptr, ptr, i64, ptr, env, 
> i32)
>  DEF_HELPER_5(vfclass_v_h, void, ptr, ptr, ptr, env, i32)
>  DEF_HELPER_5(vfclass_v_w, void, ptr, ptr, ptr, env, i32)
>  DEF_HELPER_5(vfclass_v_d, void, ptr, ptr, ptr, env, i32)
> +
> +DEF_HELPER_6(vfmerge_vfm_h, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfmerge_vfm_w, void, ptr, ptr, i64, ptr, env, i32)
> +DEF_HELPER_6(vfmerge_vfm_d, void, ptr, ptr, i64, ptr, env, i32)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index 23e80fe954..14cb4e2e66 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -513,6 +513,8 @@ vmfge_vf        011111 . ..... ..... 101 ..... 1010111 
> @r_vm
>  vmford_vv       011010 . ..... ..... 001 ..... 1010111 @r_vm
>  vmford_vf       011010 . ..... ..... 101 ..... 1010111 @r_vm
>  vfclass_v       100011 . ..... 10000 001 ..... 1010111 @r2_vm
> +vfmerge_vfm     010111 0 ..... ..... 101 ..... 1010111 @r_vm_0
> +vfmv_v_f        010111 1 00000 ..... 101 ..... 1010111 @r2
>
>  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 621220e5ff..dfa2177331 100644
> --- a/target/riscv/insn_trans/trans_rvv.inc.c
> +++ b/target/riscv/insn_trans/trans_rvv.inc.c
> @@ -2177,3 +2177,41 @@ GEN_OPFVF_TRANS(vmford_vf, opfvf_cmp_check)
>
>  /* Vector Floating-Point Classify Instruction */
>  GEN_OPFV_TRANS(vfclass_v, opfv_check)
> +
> +/* Vector Floating-Point Merge Instruction */
> +GEN_OPFVF_TRANS(vfmerge_vfm,  opfvf_check)
> +
> +static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
> +{
> +    if (vext_check_isa_ill(s) &&
> +        vext_check_reg(s, a->rd, false) &&
> +        (s->sew != 0)) {
> +
> +        if (s->vl_eq_vlmax) {
> +            tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
> +                                 MAXSZ(s), MAXSZ(s), cpu_fpr[a->rs1]);
> +        } else {
> +            TCGv_ptr dest;
> +            TCGv_i32 desc;
> +            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
> +            static gen_helper_vmv_vx * const fns[3] = {
> +                gen_helper_vmv_v_x_h,
> +                gen_helper_vmv_v_x_w,
> +                gen_helper_vmv_v_x_d,
> +            };
> +            TCGLabel *over = gen_new_label();
> +            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
> +
> +            dest = tcg_temp_new_ptr();
> +            desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
> +            tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd));
> +            fns[s->sew - 1](dest, cpu_fpr[a->rs1], cpu_env, desc);
> +
> +            tcg_temp_free_ptr(dest);
> +            tcg_temp_free_i32(desc);
> +            gen_set_label(over);
> +        }
> +        return true;
> +    }
> +    return false;
> +}
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 63d8873c0a..018293570d 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -4193,3 +4193,27 @@ RVVCALL(OPIVV1, vfclass_v_d, OP_UU_D, H8, H8, fclass_d)
>  GEN_VEXT_V(vfclass_v_h, 2, 2, clearh)
>  GEN_VEXT_V(vfclass_v_w, 4, 4, clearl)
>  GEN_VEXT_V(vfclass_v_d, 8, 8, clearq)
> +
> +/* Vector Floating-Point Merge Instruction */
> +#define GEN_VFMERGE_VF(NAME, ETYPE, H, CLEAR_FN)              \
> +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);                             \
> +    uint32_t vlmax = vext_maxsz(desc) / esz;                  \
> +    uint32_t i;                                               \
> +                                                              \
> +    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);  \
> +    }                                                         \
> +    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                  \
> +}
> +
> +GEN_VFMERGE_VF(vfmerge_vfm_h, int16_t, H2, clearh)
> +GEN_VFMERGE_VF(vfmerge_vfm_w, int32_t, H4, clearl)
> +GEN_VFMERGE_VF(vfmerge_vfm_d, int64_t, H8, clearq)
> --
> 2.23.0
>
>