On Fri, Apr 22, 2022 at 4:12 PM Hongyu Wang via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Hi,
>
> Add missing macro under O0 and adjust macro format for scalf
> intrinsics.
>
Please add the corresponding intrinsic test in sse-14.c.
> Bootstrapped/regtested on x86_64-pc-linux-gnu{-m32,}.
>
> Ok for master and backport to GCC 9/10/11?
>
> gcc/ChangeLog:
>
>         PR target/105339
>         * config/i386/avx512fintrin.h (_mm512_scalef_round_pd):
>         Add parentheses for parameters and djust format.
>         (_mm512_mask_scalef_round_pd): Ditto.
>         (_mm512_maskz_scalef_round_pd): Ditto.
>         (_mm512_scalef_round_ps): Ditto.
>         (_mm512_mask_scalef_round_ps): Ditto.
>         (_mm512_maskz_scalef_round_ps): Ditto.
>         (_mm_scalef_round_sd): Use _mm_undefined_pd.
>         (_mm_scalef_round_ss): Use _mm_undefined_ps.
>         (_mm_mask_scalef_round_sd): New macro.
>         (_mm_mask_scalef_round_ss): Ditto.
>         (_mm_maskz_scalef_round_sd): Ditto.
>         (_mm_maskz_scalef_round_ss): Ditto.
> ---
>  gcc/config/i386/avx512fintrin.h | 76 ++++++++++++++++++++++++---------
>  1 file changed, 56 insertions(+), 20 deletions(-)
>
> diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
> index 29511fd2831..6dc69ff0234 100644
> --- a/gcc/config/i386/avx512fintrin.h
> +++ b/gcc/config/i386/avx512fintrin.h
> @@ -3286,31 +3286,67 @@ _mm_maskz_scalef_round_ss (__mmask8 __U, __m128 __A, 
> __m128 __B, const int __R)
>                                                       (__mmask8) __U, __R);
>  }
>  #else
> -#define _mm512_scalef_round_pd(A, B, C)            \
> -    (__m512d)__builtin_ia32_scalefpd512_mask(A, B, 
> (__v8df)_mm512_undefined_pd(), -1, C)
> -
> -#define _mm512_mask_scalef_round_pd(W, U, A, B, C) \
> -    (__m512d)__builtin_ia32_scalefpd512_mask(A, B, W, U, C)
> -
> -#define _mm512_maskz_scalef_round_pd(U, A, B, C)   \
> -    (__m512d)__builtin_ia32_scalefpd512_mask(A, B, 
> (__v8df)_mm512_setzero_pd(), U, C)
> +#define _mm512_scalef_round_pd(A, B, C)                                      
>   \
> +  ((__m512d)                                                           \
> +   __builtin_ia32_scalefpd512_mask((A), (B),                           \
> +                                  (__v8df) _mm512_undefined_pd(),      \
> +                                  -1, (C)))
> +
> +#define _mm512_mask_scalef_round_pd(W, U, A, B, C)                     \
> +  ((__m512d) __builtin_ia32_scalefpd512_mask((A), (B), (W), (U), (C)))
> +
> +#define _mm512_maskz_scalef_round_pd(U, A, B, C)                       \
> +  ((__m512d)                                                           \
> +   __builtin_ia32_scalefpd512_mask((A), (B),                           \
> +                                  (__v8df) _mm512_setzero_pd(),        \
> +                                  (U), (C)))
> +
> +#define _mm512_scalef_round_ps(A, B, C)                                      
>   \
> +  ((__m512)                                                            \
> +   __builtin_ia32_scalefps512_mask((A), (B),                           \
> +                                  (__v16sf) _mm512_undefined_ps(),     \
> +                                  -1, (C)))
> +
> +#define _mm512_mask_scalef_round_ps(W, U, A, B, C)                     \
> +  ((__m512) __builtin_ia32_scalefps512_mask((A), (B), (W), (U), (C)))
> +
> +#define _mm512_maskz_scalef_round_ps(U, A, B, C)                       \
> +  ((__m512)                                                            \
> +   __builtin_ia32_scalefps512_mask((A), (B),                           \
> +                                  (__v16sf) _mm512_setzero_ps(),       \
> +                                  (U), (C)))
> +
> +#define _mm_scalef_round_sd(A, B, C)                                   \
> +  ((__m128d)                                                           \
> +   __builtin_ia32_scalefsd_mask_round ((A), (B),                       \
> +                                      (__v2df) _mm_undefined_pd (),    \
> +                                      -1, (C)))
>
> -#define _mm512_scalef_round_ps(A, B, C)            \
> -    (__m512)__builtin_ia32_scalefps512_mask(A, B, 
> (__v16sf)_mm512_undefined_ps(), -1, C)
> +#define _mm_scalef_round_ss(A, B, C)                                   \
> +  ((__m128)                                                            \
> +   __builtin_ia32_scalefss_mask_round ((A), (B),                       \
> +                                      (__v4sf) _mm_undefined_ps (),    \
> +                                      -1, (C)))
>
> -#define _mm512_mask_scalef_round_ps(W, U, A, B, C) \
> -    (__m512)__builtin_ia32_scalefps512_mask(A, B, W, U, C)
> +#define _mm_mask_scalef_round_sd(W, U, A, B, C)                              
>   \
> +  ((__m128d)                                                           \
> +   __builtin_ia32_scalefsd_mask_round ((A), (B), (W), (U), (C)))
>
> -#define _mm512_maskz_scalef_round_ps(U, A, B, C)   \
> -    (__m512)__builtin_ia32_scalefps512_mask(A, B, 
> (__v16sf)_mm512_setzero_ps(), U, C)
> +#define _mm_mask_scalef_round_ss(W, U, A, B, C)                              
>   \
> +  ((__m128)                                                            \
> +   __builtin_ia32_scalefss_mask_round ((A), (B), (W), (U), (C)))
>
> -#define _mm_scalef_round_sd(A, B, C)            \
> -    (__m128d)__builtin_ia32_scalefsd_mask_round (A, B, \
> -       (__v2df)_mm_setzero_pd (), -1, C)
> +#define _mm_maskz_scalef_round_sd(U, A, B, C)                          \
> +  ((__m128d)                                                           \
> +   __builtin_ia32_scalefsd_mask_round ((A), (B),                       \
> +                                      (__v2df) _mm_setzero_pd (),      \
> +                                      (U), (C)))
>
> -#define _mm_scalef_round_ss(A, B, C)            \
> -    (__m128)__builtin_ia32_scalefss_mask_round (A, B, \
> -       (__v4sf)_mm_setzero_ps (), -1, C)
> +#define _mm_maskz_scalef_round_ss(U, A, B, C)                          \
> +  ((__m128)                                                            \
> +   __builtin_ia32_scalefss_mask_round ((A), (B),                       \
> +                                      (__v4sf) _mm_setzero_ps (),      \
> +                                      (W), (U), (C)))
>  #endif
>
>  #define _mm_mask_scalef_sd(W, U, A, B) \
> --
> 2.18.1
>


-- 
BR,
Hongtao

Reply via email to