QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Alistair Francis <alistair23@gmail.com>
To: LIU Zhiwei <zhiwei_liu@c-sky.com>
Cc: guoren@linux.alibaba.com,
	"open list:RISC-V" <qemu-riscv@nongnu.org>,
	Richard Henderson <richard.henderson@linaro.org>,
	"qemu-devel@nongnu.org Developers" <qemu-devel@nongnu.org>,
	wxy194768@alibaba-inc.com,
	Chih-Min Chao <chihmin.chao@sifive.com>,
	wenmeng_zhang@c-sky.com, Palmer Dabbelt <palmer@dabbelt.com>
Subject: Re: [PATCH v6 10/61] target/riscv: vector single-width integer add and subtract
Date: Fri, 20 Mar 2020 11:31:37 -0700
Message-ID: <CAKmqyKPATrb1KG24Pz_wm9Kb7cnuixgMV5OHzMP_PN+5zM-YkA@mail.gmail.com> (raw)
In-Reply-To: <20200317150653.9008-11-zhiwei_liu@c-sky.com>

On Tue, Mar 17, 2020 at 8:27 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                   |  21 ++
>  target/riscv/insn32.decode              |  10 +
>  target/riscv/insn_trans/trans_rvv.inc.c | 251 ++++++++++++++++++++++++
>  target/riscv/vector_helper.c            | 149 ++++++++++++++
>  4 files changed, 431 insertions(+)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index 70a4b05f75..e73701d4bb 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -269,3 +269,24 @@ DEF_HELPER_6(vamominw_v_w,  void, ptr, ptr, tl, ptr, env, i32)
>  DEF_HELPER_6(vamomaxw_v_w,  void, ptr, ptr, tl, ptr, env, i32)
>  DEF_HELPER_6(vamominuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
>  DEF_HELPER_6(vamomaxuw_v_w, void, ptr, ptr, tl, ptr, env, i32)
> +
> +DEF_HELPER_6(vadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vsub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vrsub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vrsub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vrsub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vrsub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index 1330703720..d1034a0e61 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -44,6 +44,7 @@
>  &u    imm rd
>  &shift     shamt rs1 rd
>  &atomic    aq rl rs2 rs1 rd
> +&rmrr      vm rd rs1 rs2
>  &rwdvm     vm wd rd rs1 rs2
>  &r2nfvm    vm rd rs1 nf
>  &rnfvm     vm rd rs1 rs2 nf
> @@ -68,6 +69,7 @@
>  @r2      .......   ..... ..... ... ..... ....... %rs1 %rd
>  @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
>  @r_nfvm  ... ... vm:1 ..... ..... ... ..... ....... &rnfvm %nf %rs2 %rs1 %rd
> +@r_vm    ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd
>  @r_wdvm  ..... wd:1 vm:1 ..... ..... ... ..... ....... &rwdvm %rs2 %rs1 %rd
>  @r2_zimm . zimm:11  ..... ... ..... ....... %rs1 %rd
>
> @@ -275,5 +277,13 @@ vamominuw_v     11000 . . ..... ..... 110 ..... 0101111 @r_wdvm
>  vamomaxuw_v     11100 . . ..... ..... 110 ..... 0101111 @r_wdvm
>
>  # *** new major opcode OP-V ***
> +vadd_vv         000000 . ..... ..... 000 ..... 1010111 @r_vm
> +vadd_vx         000000 . ..... ..... 100 ..... 1010111 @r_vm
> +vadd_vi         000000 . ..... ..... 011 ..... 1010111 @r_vm
> +vsub_vv         000010 . ..... ..... 000 ..... 1010111 @r_vm
> +vsub_vx         000010 . ..... ..... 100 ..... 1010111 @r_vm
> +vrsub_vx        000011 . ..... ..... 100 ..... 1010111 @r_vm
> +vrsub_vi        000011 . ..... ..... 011 ..... 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 a8722ed9d2..c68f6ffe3b 100644
> --- a/target/riscv/insn_trans/trans_rvv.inc.c
> +++ b/target/riscv/insn_trans/trans_rvv.inc.c
> @@ -740,3 +740,254 @@ GEN_VEXT_TRANS(vamomaxd_v, 15, rwdvm, amo_op, amo_check)
>  GEN_VEXT_TRANS(vamominud_v, 16, rwdvm, amo_op, amo_check)
>  GEN_VEXT_TRANS(vamomaxud_v, 17, rwdvm, amo_op, amo_check)
>  #endif
> +
> +/*
> + *** Vector Integer Arithmetic Instructions
> + */
> +#define MAXSZ(s) (s->vlen >> (3 - s->lmul))
> +
> +static bool opivv_check(DisasContext *s, arg_rmrr *a)
> +{
> +    return (vext_check_isa_ill(s) &&
> +            vext_check_overlap_mask(s, a->rd, a->vm, false) &&
> +            vext_check_reg(s, a->rd, false) &&
> +            vext_check_reg(s, a->rs2, false) &&
> +            vext_check_reg(s, a->rs1, false));
> +}
> +
> +typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
> +                        uint32_t, uint32_t, uint32_t);
> +
> +static inline bool
> +do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
> +              gen_helper_gvec_4_ptr *fn)
> +{
> +    if (!opivv_check(s, a)) {
> +        return false;
> +    }
> +
> +    if (a->vm && s->vl_eq_vlmax) {
> +        gvec_fn(s->sew, vreg_ofs(s, a->rd),
> +            vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1),
> +            MAXSZ(s), MAXSZ(s));
> +    } else {
> +        uint32_t data = 0;
> +
> +        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
> +        data = FIELD_DP32(data, VDATA, VM, a->vm);
> +        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
> +        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
> +            vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
> +            cpu_env, 0, s->vlen / 8, data, fn);
> +    }
> +    return true;
> +}
> +
> +/* OPIVV with GVEC IR */
> +#define GEN_OPIVV_GVEC_TRANS(NAME, SUF) \
> +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
> +{                                                                  \
> +    static gen_helper_gvec_4_ptr * const fns[4] = {                \
> +        gen_helper_##NAME##_b, gen_helper_##NAME##_h,              \
> +        gen_helper_##NAME##_w, gen_helper_##NAME##_d,              \
> +    };                                                             \
> +    return do_opivv_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]);   \
> +}
> +
> +GEN_OPIVV_GVEC_TRANS(vadd_vv, add)
> +GEN_OPIVV_GVEC_TRANS(vsub_vv, sub)
> +
> +typedef void gen_helper_opivx(TCGv_ptr, TCGv_ptr, TCGv, TCGv_ptr,
> +                              TCGv_env, TCGv_i32);
> +
> +static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
> +                        gen_helper_opivx *fn, DisasContext *s)
> +{
> +    TCGv_ptr dest, src2, mask;
> +    TCGv 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();
> +    gen_get_gpr(src1, rs1);
> +
> +    data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
> +    data = FIELD_DP32(data, VDATA, VM, vm);
> +    data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
> +    desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
> +
> +    tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd));
> +    tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2));
> +    tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
> +
> +    fn(dest, mask, src1, src2, cpu_env, desc);
> +
> +    tcg_temp_free_ptr(dest);
> +    tcg_temp_free_ptr(mask);
> +    tcg_temp_free_ptr(src2);
> +    tcg_temp_free(src1);
> +    tcg_temp_free_i32(desc);
> +    return true;
> +}
> +
> +static bool opivx_check(DisasContext *s, arg_rmrr *a)
> +{
> +    return (vext_check_isa_ill(s) &&
> +            vext_check_overlap_mask(s, a->rd, a->vm, false) &&
> +            vext_check_reg(s, a->rd, false) &&
> +            vext_check_reg(s, a->rs2, false));
> +}
> +
> +typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t, TCGv_i64,
> +                         uint32_t, uint32_t);
> +
> +static inline bool
> +do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
> +              gen_helper_opivx *fn)
> +{
> +    if (!opivx_check(s, a)) {
> +        return false;
> +    }
> +
> +    if (a->vm && s->vl_eq_vlmax) {
> +        TCGv_i64 src1 = tcg_temp_new_i64();
> +        TCGv tmp = tcg_temp_new();
> +
> +        gen_get_gpr(tmp, a->rs1);
> +        tcg_gen_ext_tl_i64(src1, tmp);
> +        gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
> +                src1, MAXSZ(s), MAXSZ(s));
> +
> +        tcg_temp_free_i64(src1);
> +        tcg_temp_free(tmp);
> +        return true;
> +    } else {
> +        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
> +    }
> +    return true;
> +}
> +
> +/* OPIVX with GVEC IR */
> +#define GEN_OPIVX_GVEC_TRANS(NAME, SUF) \
> +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
> +{                                                                  \
> +    static gen_helper_opivx * const fns[4] = {                     \
> +        gen_helper_##NAME##_b, gen_helper_##NAME##_h,              \
> +        gen_helper_##NAME##_w, gen_helper_##NAME##_d,              \
> +    };                                                             \
> +    return do_opivx_gvec(s, a, tcg_gen_gvec_##SUF, fns[s->sew]);   \
> +}
> +
> +GEN_OPIVX_GVEC_TRANS(vadd_vx, adds)
> +GEN_OPIVX_GVEC_TRANS(vsub_vx, subs)
> +
> +/* OPIVX without GVEC IR */
> +#define GEN_OPIVX_TRANS(NAME, CHECK)                                     \
> +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
> +{                                                                        \
> +    if (CHECK(s, a)) {                                                   \
> +        static gen_helper_opivx * const fns[4] = {                       \
> +            gen_helper_##NAME##_b, gen_helper_##NAME##_h,                \
> +            gen_helper_##NAME##_w, gen_helper_##NAME##_d,                \
> +        };                                                               \
> +                                                                         \
> +        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);\
> +    }                                                                    \
> +    return false;                                                        \
> +}
> +
> +GEN_OPIVX_TRANS(vrsub_vx, opivx_check)
> +
> +static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
> +                        gen_helper_opivx *fn, DisasContext *s, int zx)
> +{
> +    TCGv_ptr dest, src2, mask;
> +    TCGv src1;
> +    TCGv_i32 desc;
> +    uint32_t data = 0;
> +
> +    dest = tcg_temp_new_ptr();
> +    mask = tcg_temp_new_ptr();
> +    src2 = tcg_temp_new_ptr();
> +    if (zx) {
> +        src1 = tcg_const_tl(imm);
> +    } else {
> +        src1 = tcg_const_tl(sextract64(imm, 0, 5));
> +    }
> +    data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
> +    data = FIELD_DP32(data, VDATA, VM, vm);
> +    data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
> +    desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
> +
> +    tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, vd));
> +    tcg_gen_addi_ptr(src2, cpu_env, vreg_ofs(s, vs2));
> +    tcg_gen_addi_ptr(mask, cpu_env, vreg_ofs(s, 0));
> +
> +    fn(dest, mask, src1, src2, cpu_env, desc);
> +
> +    tcg_temp_free_ptr(dest);
> +    tcg_temp_free_ptr(mask);
> +    tcg_temp_free_ptr(src2);
> +    tcg_temp_free(src1);
> +    tcg_temp_free_i32(desc);
> +    return true;
> +}
> +
> +typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t,
> +                         uint32_t, uint32_t);
> +
> +static inline bool
> +do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
> +              gen_helper_opivx *fn, int zx)
> +{
> +    if (!opivx_check(s, a)) {
> +        return false;
> +    }
> +
> +    if (a->vm && s->vl_eq_vlmax) {
> +        if (zx) {
> +            gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
> +                    extract64(a->rs1, 0, 5), MAXSZ(s), MAXSZ(s));
> +        } else {
> +            gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
> +                    sextract64(a->rs1, 0, 5), MAXSZ(s), MAXSZ(s));
> +        }
> +    } else {
> +        return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, zx);
> +    }
> +    return true;
> +}
> +
> +/* OPIVI with GVEC IR */
> +#define GEN_OPIVI_GVEC_TRANS(NAME, ZX, OPIVX, SUF) \
> +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
> +{                                                                  \
> +    static gen_helper_opivx * const fns[4] = {                     \
> +        gen_helper_##OPIVX##_b, gen_helper_##OPIVX##_h,            \
> +        gen_helper_##OPIVX##_w, gen_helper_##OPIVX##_d,            \
> +    };                                                             \
> +    return do_opivi_gvec(s, a, tcg_gen_gvec_##SUF,                 \
> +                         fns[s->sew], ZX);                         \
> +}
> +
> +GEN_OPIVI_GVEC_TRANS(vadd_vi, 0, vadd_vx, addi)
> +
> +/* OPIVI without GVEC IR */
> +#define GEN_OPIVI_TRANS(NAME, ZX, OPIVX, CHECK)                          \
> +static bool trans_##NAME(DisasContext *s, arg_rmrr *a)                   \
> +{                                                                        \
> +    if (CHECK(s, a)) {                                                   \
> +        static gen_helper_opivx * const fns[4] = {                       \
> +            gen_helper_##OPIVX##_b, gen_helper_##OPIVX##_h,              \
> +            gen_helper_##OPIVX##_w, gen_helper_##OPIVX##_d,              \
> +        };                                                               \
> +        return opivi_trans(a->rd, a->rs1, a->rs2, a->vm,                 \
> +                fns[s->sew], s, ZX);                                     \
> +    }                                                                    \
> +    return false;                                                        \
> +}
> +
> +GEN_OPIVI_TRANS(vrsub_vi, 0, vrsub_vx, opivx_check)
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 45da43ade9..27934e291b 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -827,3 +827,152 @@ GEN_VEXT_AMO(vamominw_v_w,  int32_t,  int32_t,  idx_w, clearl)
>  GEN_VEXT_AMO(vamomaxw_v_w,  int32_t,  int32_t,  idx_w, clearl)
>  GEN_VEXT_AMO(vamominuw_v_w, uint32_t, uint32_t, idx_w, clearl)
>  GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl)
> +
> +/*
> + *** Vector Integer Arithmetic Instructions
> + */
> +
> +/* expand macro args before macro */
> +#define RVVCALL(macro, ...)  macro(__VA_ARGS__)
> +
> +/* (TD, T1, T2, TX1, TX2) */
> +#define OP_SSS_B int8_t, int8_t, int8_t, int8_t, int8_t
> +#define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
> +#define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
> +#define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
> +
> +/* operation of two vector elements */
> +typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
> +
> +#define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
> +static void do_##NAME(void *vd, void *vs1, void *vs2, int i)    \
> +{                                                               \
> +    TX1 s1 = *((T1 *)vs1 + HS1(i));                             \
> +    TX2 s2 = *((T2 *)vs2 + HS2(i));                             \
> +    *((TD *)vd + HD(i)) = OP(s2, s1);                           \
> +}
> +#define DO_SUB(N, M) (N - M)
> +#define DO_RSUB(N, M) (M - N)
> +
> +RVVCALL(OPIVV2, vadd_vv_b, OP_SSS_B, H1, H1, H1, DO_ADD)
> +RVVCALL(OPIVV2, vadd_vv_h, OP_SSS_H, H2, H2, H2, DO_ADD)
> +RVVCALL(OPIVV2, vadd_vv_w, OP_SSS_W, H4, H4, H4, DO_ADD)
> +RVVCALL(OPIVV2, vadd_vv_d, OP_SSS_D, H8, H8, H8, DO_ADD)
> +RVVCALL(OPIVV2, vsub_vv_b, OP_SSS_B, H1, H1, H1, DO_SUB)
> +RVVCALL(OPIVV2, vsub_vv_h, OP_SSS_H, H2, H2, H2, DO_SUB)
> +RVVCALL(OPIVV2, vsub_vv_w, OP_SSS_W, H4, H4, H4, DO_SUB)
> +RVVCALL(OPIVV2, vsub_vv_d, OP_SSS_D, H8, H8, H8, DO_SUB)
> +
> +static void do_vext_vv(void *vd, void *v0, void *vs1, void *vs2,
> +                       CPURISCVState *env, uint32_t desc,
> +                       uint32_t esz, uint32_t dsz,
> +                       opivv2_fn *fn, clear_fn *clearfn)
> +{
> +    uint32_t vlmax = vext_maxsz(desc) / esz;
> +    uint32_t mlen = vext_mlen(desc);
> +    uint32_t vm = vext_vm(desc);
> +    uint32_t vl = env->vl;
> +    uint32_t i;
> +
> +    if (vl == 0) {
> +        return;
> +    }
> +    for (i = 0; i < vl; i++) {
> +        if (!vm && !vext_elem_mask(v0, mlen, i)) {
> +            continue;
> +        }
> +        fn(vd, vs1, vs2, i);
> +    }
> +    clearfn(vd, vl, vl * dsz,  vlmax * dsz);
> +}
> +
> +/* generate the helpers for OPIVV */
> +#define GEN_VEXT_VV(NAME, ESZ, DSZ, CLEAR_FN)             \
> +void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
> +                  void *vs2, CPURISCVState *env,          \
> +                  uint32_t desc)                          \
> +{                                                         \
> +    do_vext_vv(vd, v0, vs1, vs2, env, desc, ESZ, DSZ,     \
> +               do_##NAME, CLEAR_FN);                      \
> +}
> +
> +GEN_VEXT_VV(vadd_vv_b, 1, 1, clearb)
> +GEN_VEXT_VV(vadd_vv_h, 2, 2, clearh)
> +GEN_VEXT_VV(vadd_vv_w, 4, 4, clearl)
> +GEN_VEXT_VV(vadd_vv_d, 8, 8, clearq)
> +GEN_VEXT_VV(vsub_vv_b, 1, 1, clearb)
> +GEN_VEXT_VV(vsub_vv_h, 2, 2, clearh)
> +GEN_VEXT_VV(vsub_vv_w, 4, 4, clearl)
> +GEN_VEXT_VV(vsub_vv_d, 8, 8, clearq)
> +
> +typedef void opivx2_fn(void *vd, target_long s1, void *vs2, int i);
> +
> +/*
> + * (T1)s1 gives the real operator type.
> + * (TX1)(T1)s1 expands the operator type of widen or narrow operations.
> + */
> +#define OPIVX2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)             \
> +static void do_##NAME(void *vd, target_long s1, void *vs2, int i)   \
> +{                                                                   \
> +    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
> +    *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1);                      \
> +}
> +
> +RVVCALL(OPIVX2, vadd_vx_b, OP_SSS_B, H1, H1, DO_ADD)
> +RVVCALL(OPIVX2, vadd_vx_h, OP_SSS_H, H2, H2, DO_ADD)
> +RVVCALL(OPIVX2, vadd_vx_w, OP_SSS_W, H4, H4, DO_ADD)
> +RVVCALL(OPIVX2, vadd_vx_d, OP_SSS_D, H8, H8, DO_ADD)
> +RVVCALL(OPIVX2, vsub_vx_b, OP_SSS_B, H1, H1, DO_SUB)
> +RVVCALL(OPIVX2, vsub_vx_h, OP_SSS_H, H2, H2, DO_SUB)
> +RVVCALL(OPIVX2, vsub_vx_w, OP_SSS_W, H4, H4, DO_SUB)
> +RVVCALL(OPIVX2, vsub_vx_d, OP_SSS_D, H8, H8, DO_SUB)
> +RVVCALL(OPIVX2, vrsub_vx_b, OP_SSS_B, H1, H1, DO_RSUB)
> +RVVCALL(OPIVX2, vrsub_vx_h, OP_SSS_H, H2, H2, DO_RSUB)
> +RVVCALL(OPIVX2, vrsub_vx_w, OP_SSS_W, H4, H4, DO_RSUB)
> +RVVCALL(OPIVX2, vrsub_vx_d, OP_SSS_D, H8, H8, DO_RSUB)
> +
> +static void do_vext_vx(void *vd, void *v0, target_long s1, void *vs2,
> +                       CPURISCVState *env, uint32_t desc,
> +                       uint32_t esz, uint32_t dsz,
> +                       opivx2_fn fn, clear_fn *clearfn)
> +{
> +    uint32_t vlmax = vext_maxsz(desc) / esz;
> +    uint32_t mlen = vext_mlen(desc);
> +    uint32_t vm = vext_vm(desc);
> +    uint32_t vl = env->vl;
> +    uint32_t i;
> +
> +    if (vl == 0) {
> +        return;
> +    }
> +    for (i = 0; i < vl; i++) {
> +        if (!vm && !vext_elem_mask(v0, mlen, i)) {
> +            continue;
> +        }
> +        fn(vd, s1, vs2, i);
> +    }
> +    clearfn(vd, vl, vl * dsz,  vlmax * dsz);
> +}
> +
> +/* generate the helpers for OPIVX */
> +#define GEN_VEXT_VX(NAME, ESZ, DSZ, CLEAR_FN)             \
> +void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
> +                  void *vs2, CPURISCVState *env,          \
> +                  uint32_t desc)                          \
> +{                                                         \
> +    do_vext_vx(vd, v0, s1, vs2, env, desc, ESZ, DSZ,      \
> +               do_##NAME, CLEAR_FN);                      \
> +}
> +
> +GEN_VEXT_VX(vadd_vx_b, 1, 1, clearb)
> +GEN_VEXT_VX(vadd_vx_h, 2, 2, clearh)
> +GEN_VEXT_VX(vadd_vx_w, 4, 4, clearl)
> +GEN_VEXT_VX(vadd_vx_d, 8, 8, clearq)
> +GEN_VEXT_VX(vsub_vx_b, 1, 1, clearb)
> +GEN_VEXT_VX(vsub_vx_h, 2, 2, clearh)
> +GEN_VEXT_VX(vsub_vx_w, 4, 4, clearl)
> +GEN_VEXT_VX(vsub_vx_d, 8, 8, clearq)
> +GEN_VEXT_VX(vrsub_vx_b, 1, 1, clearb)
> +GEN_VEXT_VX(vrsub_vx_h, 2, 2, clearh)
> +GEN_VEXT_VX(vrsub_vx_w, 4, 4, clearl)
> +GEN_VEXT_VX(vrsub_vx_d, 8, 8, clearq)
> --
> 2.23.0
>


  reply index

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-17 15:05 [PATCH v6 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 01/61] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 02/61] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 03/61] target/riscv: support vector extension csr LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 04/61] target/riscv: add vector configure instruction LIU Zhiwei
2020-03-23  6:51   ` Kito Cheng
2020-03-23  7:10     ` LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 05/61] target/riscv: add an internals.h header LIU Zhiwei
2020-03-18 23:45   ` Alistair Francis
2020-03-27 23:41   ` Richard Henderson
2020-03-17 15:05 ` [PATCH v6 06/61] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-03-18 23:54   ` Alistair Francis
2020-03-17 15:05 ` [PATCH v6 07/61] target/riscv: add vector index " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 08/61] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 09/61] target/riscv: add vector amo operations LIU Zhiwei
2020-03-19 17:01   ` Alistair Francis
2020-03-27 23:44   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 10/61] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-03-20 18:31   ` Alistair Francis [this message]
2020-03-27 23:54   ` Richard Henderson
2020-03-28 14:42     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 11/61] target/riscv: vector widening " LIU Zhiwei
2020-03-19 16:28   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-03-19 17:29   ` Alistair Francis
2020-03-28  0:00   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 13/61] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-03-20 18:34   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 14/61] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-03-19 20:10   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 15/61] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-03-20 18:43   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 16/61] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-03-25 17:32   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 17/61] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-03-20 18:49   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 18/61] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-03-25 17:36   ` Alistair Francis
2020-03-28  0:06   ` Richard Henderson
2020-03-28 15:17     ` LIU Zhiwei
2020-03-28 15:47       ` Richard Henderson
2020-03-28 16:13         ` LIU Zhiwei
2020-03-29  4:00           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 19/61] target/riscv: vector integer divide instructions LIU Zhiwei
2020-03-20 18:51   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 20/61] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-03-25 17:25   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 21/61] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-03-25 17:27   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 22/61] target/riscv: vector widening " LIU Zhiwei
2020-03-25 17:42   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 23/61] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-03-26 17:57   ` Alistair Francis
2020-03-28  0:18   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 24/61] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-03-28  0:20   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 25/61] target/riscv: vector single-width averaging " LIU Zhiwei
2020-03-19  3:46   ` LIU Zhiwei
2020-03-28  0:32     ` Richard Henderson
2020-03-28  1:07       ` LIU Zhiwei
2020-03-28  1:22         ` Richard Henderson
2020-03-28 15:37           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-03-28  1:08   ` Richard Henderson
2020-03-28 15:41     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 27/61] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-03-28  1:23   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 28/61] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-03-28  1:24   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 29/61] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-03-28  1:50   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 30/61] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 31/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 32/61] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-03-25 17:46   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 33/61] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 35/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 36/61] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-03-25 17:47   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 38/61] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 39/61] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-03-28  2:01   ` Richard Henderson
2020-03-28 15:44     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 40/61] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-03-28  2:06   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 41/61] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-03-28  3:23   ` Richard Henderson
2020-03-28 15:47     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 42/61] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 43/61] target/riscv: widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 44/61] target/riscv: narrowing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 45/61] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 46/61] target/riscv: vector wideing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 47/61] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 48/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 49/61] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 50/61] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 51/61] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 52/61] target/riscv: set-X-first " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 53/61] target/riscv: vector iota instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 54/61] target/riscv: vector element index instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 55/61] target/riscv: integer extract instruction LIU Zhiwei
2020-03-28  3:36   ` Richard Henderson
2020-03-28 16:23     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 56/61] target/riscv: integer scalar move instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 57/61] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-03-28  3:44   ` Richard Henderson
2020-03-28 16:31     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 58/61] target/riscv: vector slide instructions LIU Zhiwei
2020-03-28  3:50   ` Richard Henderson
2020-03-28 13:40   ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 59/61] target/riscv: vector register gather instruction LIU Zhiwei
2020-03-28  3:57   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 60/61] target/riscv: vector compress instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 61/61] target/riscv: configure and turn on vector extension from command line LIU Zhiwei
2020-03-25 17:49   ` Alistair Francis
2020-03-28  4:00   ` Richard Henderson
2020-03-17 20:47 ` [PATCH v6 00/61] target/riscv: support vector extension v0.7.1 no-reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAKmqyKPATrb1KG24Pz_wm9Kb7cnuixgMV5OHzMP_PN+5zM-YkA@mail.gmail.com \
    --to=alistair23@gmail.com \
    --cc=chihmin.chao@sifive.com \
    --cc=guoren@linux.alibaba.com \
    --cc=palmer@dabbelt.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-riscv@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=wenmeng_zhang@c-sky.com \
    --cc=wxy194768@alibaba-inc.com \
    --cc=zhiwei_liu@c-sky.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git