Re: [PATCH v2 1/7] target/riscv: Generate nanboxed results from fp helpers

[LIU Zhiwei]

On 2020/7/24 8:28, Richard Henderson wrote:
> Make sure that all results from single-precision scalar helpers
> are properly nan-boxed to 64-bits.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>   target/riscv/internals.h  |  5 +++++
>   target/riscv/fpu_helper.c | 42 +++++++++++++++++++++------------------
>   2 files changed, 28 insertions(+), 19 deletions(-)
>
> diff --git a/target/riscv/internals.h b/target/riscv/internals.h
> index 37d33820ad..9f4ba7d617 100644
> --- a/target/riscv/internals.h
> +++ b/target/riscv/internals.h
> @@ -38,4 +38,9 @@ target_ulong fclass_d(uint64_t frs1);
>   #define SEW32 2
>   #define SEW64 3
>   
> +static inline uint64_t nanbox_s(float32 f)
> +{
> +    return f | MAKE_64BIT_MASK(32, 32);
> +}
> +
If define it here,  we can also define a more general  function with flen.

+static inline uint64_t nanbox_s(float32 f, uint32_t flen)
+{
+    return f | MAKE_64BIT_MASK(flen, 64 - flen);
+}
+

So we can reuse it in fp16 or bf16 scalar instruction and in vector 
instructions.

Reviewed-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Zhiwei
>   #endif
> diff --git a/target/riscv/fpu_helper.c b/target/riscv/fpu_helper.c
> index 4379756dc4..72541958a7 100644
> --- a/target/riscv/fpu_helper.c
> +++ b/target/riscv/fpu_helper.c
> @@ -81,10 +81,16 @@ void helper_set_rounding_mode(CPURISCVState *env, uint32_t 
> rm)
>       set_float_rounding_mode(softrm, &env->fp_status);
>   }
>   
> +static uint64_t do_fmadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
> +                           uint64_t frs3, int flags)
> +{
> +    return nanbox_s(float32_muladd(frs1, frs2, frs3, flags, &env->fp_status));
> +}
> +
>   uint64_t helper_fmadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
>                           uint64_t frs3)
>   {
> -    return float32_muladd(frs1, frs2, frs3, 0, &env->fp_status);
> +    return do_fmadd_s(env, frs1, frs2, frs3, 0);
>   }
>   
>   uint64_t helper_fmadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
> @@ -96,8 +102,7 @@ uint64_t helper_fmadd_d(CPURISCVState *env, uint64_t frs1, 
> uint64_t frs2,
>   uint64_t helper_fmsub_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
>                           uint64_t frs3)
>   {
> -    return float32_muladd(frs1, frs2, frs3, float_muladd_negate_c,
> -                          &env->fp_status);
> +    return do_fmadd_s(env, frs1, frs2, frs3, float_muladd_negate_c);
>   }
>   
>   uint64_t helper_fmsub_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
> @@ -110,8 +115,7 @@ uint64_t helper_fmsub_d(CPURISCVState *env, uint64_t frs1, 
> uint64_t frs2,
>   uint64_t helper_fnmsub_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
>                            uint64_t frs3)
>   {
> -    return float32_muladd(frs1, frs2, frs3, float_muladd_negate_product,
> -                          &env->fp_status);
> +    return do_fmadd_s(env, frs1, frs2, frs3, float_muladd_negate_product);
>   }
>   
>   uint64_t helper_fnmsub_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
> @@ -124,8 +128,8 @@ uint64_t helper_fnmsub_d(CPURISCVState *env, uint64_t frs1, 
> uint64_t frs2,
>   uint64_t helper_fnmadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
>                            uint64_t frs3)
>   {
> -    return float32_muladd(frs1, frs2, frs3, float_muladd_negate_c |
> -                          float_muladd_negate_product, &env->fp_status);
> +    return do_fmadd_s(env, frs1, frs2, frs3,
> +                      float_muladd_negate_c | float_muladd_negate_product);
>   }
>   
>   uint64_t helper_fnmadd_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2,
> @@ -137,37 +141,37 @@ uint64_t helper_fnmadd_d(CPURISCVState *env, uint64_t 
> frs1, uint64_t frs2,
>   
>   uint64_t helper_fadd_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_add(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_add(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fsub_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_sub(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_sub(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fmul_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_mul(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_mul(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fdiv_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_div(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_div(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fmin_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_minnum(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_minnum(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fmax_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   {
> -    return float32_maxnum(frs1, frs2, &env->fp_status);
> +    return nanbox_s(float32_maxnum(frs1, frs2, &env->fp_status));
>   }
>   
>   uint64_t helper_fsqrt_s(CPURISCVState *env, uint64_t frs1)
>   {
> -    return float32_sqrt(frs1, &env->fp_status);
> +    return nanbox_s(float32_sqrt(frs1, &env->fp_status));
>   }
>   
>   target_ulong helper_fle_s(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
> @@ -209,23 +213,23 @@ uint64_t helper_fcvt_lu_s(CPURISCVState *env, uint64_t 
> frs1)
>   
>   uint64_t helper_fcvt_s_w(CPURISCVState *env, target_ulong rs1)
>   {
> -    return int32_to_float32((int32_t)rs1, &env->fp_status);
> +    return nanbox_s(int32_to_float32((int32_t)rs1, &env->fp_status));
>   }
>   
>   uint64_t helper_fcvt_s_wu(CPURISCVState *env, target_ulong rs1)
>   {
> -    return uint32_to_float32((uint32_t)rs1, &env->fp_status);
> +    return nanbox_s(uint32_to_float32((uint32_t)rs1, &env->fp_status));
>   }
>   
>   #if defined(TARGET_RISCV64)
>   uint64_t helper_fcvt_s_l(CPURISCVState *env, uint64_t rs1)
>   {
> -    return int64_to_float32(rs1, &env->fp_status);
> +    return nanbox_s(int64_to_float32(rs1, &env->fp_status));
>   }
>   
>   uint64_t helper_fcvt_s_lu(CPURISCVState *env, uint64_t rs1)
>   {
> -    return uint64_to_float32(rs1, &env->fp_status);
> +    return nanbox_s(uint64_to_float32(rs1, &env->fp_status));
>   }
>   #endif
>   
> @@ -266,7 +270,7 @@ uint64_t helper_fmax_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2)
>   
>   uint64_t helper_fcvt_s_d(CPURISCVState *env, uint64_t rs1)
>   {
> -    return float64_to_float32(rs1, &env->fp_status);
> +    return nanbox_s(float64_to_float32(rs1, &env->fp_status));
>   }
>   
>   uint64_t helper_fcvt_d_s(CPURISCVState *env, uint64_t rs1)