[PATCH v3 3/6] rs6000: Simplify some SSE4.1 "test" intrinsics

Bill Schmidt wschmidt@linux.ibm.com
Fri Aug 27 13:48:50 GMT 2021


This looks fine, recommend approval.

Thanks!
Bill

On 8/23/21 2:03 PM, Paul A. Clarke wrote:
> Copy some simple redirections from i386 <smmintrin.h>, for:
> - _mm_test_all_zeros
> - _mm_test_all_ones
> - _mm_test_mix_ones_zeros
>
> 2021-08-20  Paul A. Clarke  <pc@us.ibm.com>
>
> gcc
> 	* config/rs6000/smmintrin.h (_mm_test_all_zeros,
> 	_mm_test_all_ones, _mm_test_mix_ones_zeros): Replace.
> ---
> v3: No change.
> v2:
> - Removed "-Wno-psabi" from tests as unnecessary, per v1 review.
> - Noted testing in patch series cover letter.
>
>   gcc/config/rs6000/smmintrin.h | 30 ++++--------------------------
>   1 file changed, 4 insertions(+), 26 deletions(-)
>
> diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
> index 505fe4ce22a8..363534cb06a2 100644
> --- a/gcc/config/rs6000/smmintrin.h
> +++ b/gcc/config/rs6000/smmintrin.h
> @@ -379,34 +379,12 @@ _mm_testnzc_si128 (__m128i __A, __m128i __B)
>     return _mm_testz_si128 (__A, __B) == 0 && _mm_testc_si128 (__A, __B) == 0;
>   }
>   
> -__inline int
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_test_all_zeros (__m128i __A, __m128i __mask)
> -{
> -  const __v16qu __zero = {0};
> -  return vec_all_eq (vec_and ((__v16qu) __A, (__v16qu) __mask), __zero);
> -}
> +#define _mm_test_all_zeros(M, V) _mm_testz_si128 ((M), (V))
>   
> -__inline int
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_test_all_ones (__m128i __A)
> -{
> -  const __v16qu __ones = vec_splats ((unsigned char) 0xff);
> -  return vec_all_eq ((__v16qu) __A, __ones);
> -}
> +#define _mm_test_all_ones(V) \
> +  _mm_testc_si128 ((V), _mm_cmpeq_epi32 ((V), (V)))
>   
> -__inline int
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_test_mix_ones_zeros (__m128i __A, __m128i __mask)
> -{
> -  const __v16qu __zero = {0};
> -  const __v16qu __Amasked = vec_and ((__v16qu) __A, (__v16qu) __mask);
> -  const int any_ones = vec_any_ne (__Amasked, __zero);
> -  const __v16qu __notA = vec_nor ((__v16qu) __A, (__v16qu) __A);
> -  const __v16qu __notAmasked = vec_and ((__v16qu) __notA, (__v16qu) __mask);
> -  const int any_zeros = vec_any_ne (__notAmasked, __zero);
> -  return any_ones * any_zeros;
> -}
> +#define _mm_test_mix_ones_zeros(M, V) _mm_testnzc_si128 ((M), (V))
>   
>   extern __inline __m128i
>   __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))


More information about the Gcc-patches mailing list