qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH v6 20/61] target/riscv: vector widening integer multiply inst


From: Alistair Francis
Subject: Re: [PATCH v6 20/61] target/riscv: vector widening integer multiply instructions
Date: Wed, 25 Mar 2020 10:25:20 -0700

On Tue, Mar 17, 2020 at 8:47 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                   | 19 +++++++++
>  target/riscv/insn32.decode              |  6 +++
>  target/riscv/insn_trans/trans_rvv.inc.c |  8 ++++
>  target/riscv/vector_helper.c            | 51 +++++++++++++++++++++++++
>  4 files changed, 84 insertions(+)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index 357f149198..1704b8c512 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -591,3 +591,22 @@ DEF_HELPER_6(vrem_vx_b, void, ptr, ptr, tl, ptr, env, 
> i32)
>  DEF_HELPER_6(vrem_vx_h, void, ptr, ptr, tl, ptr, env, i32)
>  DEF_HELPER_6(vrem_vx_w, void, ptr, ptr, tl, ptr, env, i32)
>  DEF_HELPER_6(vrem_vx_d, void, ptr, ptr, tl, ptr, env, i32)
> +
> +DEF_HELPER_6(vwmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
> +DEF_HELPER_6(vwmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
> +DEF_HELPER_6(vwmulsu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index 7fb8f8fad8..ae7cfa3e28 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -379,6 +379,12 @@ vremu_vv        100010 . ..... ..... 010 ..... 1010111 
> @r_vm
>  vremu_vx        100010 . ..... ..... 110 ..... 1010111 @r_vm
>  vrem_vv         100011 . ..... ..... 010 ..... 1010111 @r_vm
>  vrem_vx         100011 . ..... ..... 110 ..... 1010111 @r_vm
> +vwmulu_vv       111000 . ..... ..... 010 ..... 1010111 @r_vm
> +vwmulu_vx       111000 . ..... ..... 110 ..... 1010111 @r_vm
> +vwmulsu_vv      111010 . ..... ..... 010 ..... 1010111 @r_vm
> +vwmulsu_vx      111010 . ..... ..... 110 ..... 1010111 @r_vm
> +vwmul_vv        111011 . ..... ..... 010 ..... 1010111 @r_vm
> +vwmul_vx        111011 . ..... ..... 110 ..... 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 ed53eaaef5..98df7e2daa 100644
> --- a/target/riscv/insn_trans/trans_rvv.inc.c
> +++ b/target/riscv/insn_trans/trans_rvv.inc.c
> @@ -1472,3 +1472,11 @@ GEN_OPIVX_TRANS(vdivu_vx, opivx_check)
>  GEN_OPIVX_TRANS(vdiv_vx, opivx_check)
>  GEN_OPIVX_TRANS(vremu_vx, opivx_check)
>  GEN_OPIVX_TRANS(vrem_vx, opivx_check)
> +
> +/* Vector Widening Integer Multiply Instructions */
> +GEN_OPIVV_WIDEN_TRANS(vwmul_vv, opivv_widen_check)
> +GEN_OPIVV_WIDEN_TRANS(vwmulu_vv, opivv_widen_check)
> +GEN_OPIVV_WIDEN_TRANS(vwmulsu_vv, opivv_widen_check)
> +GEN_OPIVX_WIDEN_TRANS(vwmul_vx)
> +GEN_OPIVX_WIDEN_TRANS(vwmulu_vx)
> +GEN_OPIVX_WIDEN_TRANS(vwmulsu_vx)
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 4fc7a08954..35c6aa8494 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -856,6 +856,18 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, 
> clearl)
>  #define OP_SUS_H int16_t, uint16_t, int16_t, uint16_t, int16_t
>  #define OP_SUS_W int32_t, uint32_t, int32_t, uint32_t, int32_t
>  #define OP_SUS_D int64_t, uint64_t, int64_t, uint64_t, int64_t
> +#define WOP_UUU_B uint16_t, uint8_t, uint8_t, uint16_t, uint16_t
> +#define WOP_UUU_H uint32_t, uint16_t, uint16_t, uint32_t, uint32_t
> +#define WOP_UUU_W uint64_t, uint32_t, uint32_t, uint64_t, uint64_t
> +#define WOP_SSS_B int16_t, int8_t, int8_t, int16_t, int16_t
> +#define WOP_SSS_H int32_t, int16_t, int16_t, int32_t, int32_t
> +#define WOP_SSS_W int64_t, int32_t, int32_t, int64_t, int64_t
> +#define WOP_SUS_B int16_t, uint8_t, int8_t, uint16_t, int16_t
> +#define WOP_SUS_H int32_t, uint16_t, int16_t, uint32_t, int32_t
> +#define WOP_SUS_W int64_t, uint32_t, int32_t, uint64_t, int64_t
> +#define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t
> +#define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t
> +#define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t
>
>  /* operation of two vector elements */
>  typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
> @@ -1815,3 +1827,42 @@ GEN_VEXT_VX(vrem_vx_b, 1, 1, clearb)
>  GEN_VEXT_VX(vrem_vx_h, 2, 2, clearh)
>  GEN_VEXT_VX(vrem_vx_w, 4, 4, clearl)
>  GEN_VEXT_VX(vrem_vx_d, 8, 8, clearq)
> +
> +/* Vector Widening Integer Multiply Instructions */
> +RVVCALL(OPIVV2, vwmul_vv_b, WOP_SSS_B, H2, H1, H1, DO_MUL)
> +RVVCALL(OPIVV2, vwmul_vv_h, WOP_SSS_H, H4, H2, H2, DO_MUL)
> +RVVCALL(OPIVV2, vwmul_vv_w, WOP_SSS_W, H8, H4, H4, DO_MUL)
> +RVVCALL(OPIVV2, vwmulu_vv_b, WOP_UUU_B, H2, H1, H1, DO_MUL)
> +RVVCALL(OPIVV2, vwmulu_vv_h, WOP_UUU_H, H4, H2, H2, DO_MUL)
> +RVVCALL(OPIVV2, vwmulu_vv_w, WOP_UUU_W, H8, H4, H4, DO_MUL)
> +RVVCALL(OPIVV2, vwmulsu_vv_b, WOP_SUS_B, H2, H1, H1, DO_MUL)
> +RVVCALL(OPIVV2, vwmulsu_vv_h, WOP_SUS_H, H4, H2, H2, DO_MUL)
> +RVVCALL(OPIVV2, vwmulsu_vv_w, WOP_SUS_W, H8, H4, H4, DO_MUL)
> +GEN_VEXT_VV(vwmul_vv_b, 1, 2, clearh)
> +GEN_VEXT_VV(vwmul_vv_h, 2, 4, clearl)
> +GEN_VEXT_VV(vwmul_vv_w, 4, 8, clearq)
> +GEN_VEXT_VV(vwmulu_vv_b, 1, 2, clearh)
> +GEN_VEXT_VV(vwmulu_vv_h, 2, 4, clearl)
> +GEN_VEXT_VV(vwmulu_vv_w, 4, 8, clearq)
> +GEN_VEXT_VV(vwmulsu_vv_b, 1, 2, clearh)
> +GEN_VEXT_VV(vwmulsu_vv_h, 2, 4, clearl)
> +GEN_VEXT_VV(vwmulsu_vv_w, 4, 8, clearq)
> +
> +RVVCALL(OPIVX2, vwmul_vx_b, WOP_SSS_B, H2, H1, DO_MUL)
> +RVVCALL(OPIVX2, vwmul_vx_h, WOP_SSS_H, H4, H2, DO_MUL)
> +RVVCALL(OPIVX2, vwmul_vx_w, WOP_SSS_W, H8, H4, DO_MUL)
> +RVVCALL(OPIVX2, vwmulu_vx_b, WOP_UUU_B, H2, H1, DO_MUL)
> +RVVCALL(OPIVX2, vwmulu_vx_h, WOP_UUU_H, H4, H2, DO_MUL)
> +RVVCALL(OPIVX2, vwmulu_vx_w, WOP_UUU_W, H8, H4, DO_MUL)
> +RVVCALL(OPIVX2, vwmulsu_vx_b, WOP_SUS_B, H2, H1, DO_MUL)
> +RVVCALL(OPIVX2, vwmulsu_vx_h, WOP_SUS_H, H4, H2, DO_MUL)
> +RVVCALL(OPIVX2, vwmulsu_vx_w, WOP_SUS_W, H8, H4, DO_MUL)
> +GEN_VEXT_VX(vwmul_vx_b, 1, 2, clearh)
> +GEN_VEXT_VX(vwmul_vx_h, 2, 4, clearl)
> +GEN_VEXT_VX(vwmul_vx_w, 4, 8, clearq)
> +GEN_VEXT_VX(vwmulu_vx_b, 1, 2, clearh)
> +GEN_VEXT_VX(vwmulu_vx_h, 2, 4, clearl)
> +GEN_VEXT_VX(vwmulu_vx_w, 4, 8, clearq)
> +GEN_VEXT_VX(vwmulsu_vx_b, 1, 2, clearh)
> +GEN_VEXT_VX(vwmulsu_vx_h, 2, 4, clearl)
> +GEN_VEXT_VX(vwmulsu_vx_w, 4, 8, clearq)
> --
> 2.23.0
>



reply via email to

[Prev in Thread] Current Thread [Next in Thread]