This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH] Fix up avx512bwintrin.h with -O0 (PR target/79932)
- From: Uros Bizjak <ubizjak at gmail dot com>
- To: Jakub Jelinek <jakub at redhat dot com>
- Cc: "gcc-patches at gcc dot gnu dot org" <gcc-patches at gcc dot gnu dot org>
- Date: Thu, 9 Mar 2017 09:37:30 +0100
- Subject: Re: [PATCH] Fix up avx512bwintrin.h with -O0 (PR target/79932)
- Authentication-results: sourceware.org; auth=none
- References: <20170307185255.GO22703@tucnak>
On Tue, Mar 7, 2017 at 7:52 PM, Jakub Jelinek <jakub@redhat.com> wrote:
> Hi!
>
> As mentioned in the PR, 6 intrinsics were only defined in section
> guarded with #ifdef __OPTIMIZE__ (unnecessarily, because the intrinsics
> don't have any immediate argument that must be constant) and without
> #defines for -O0.
>
> Fixed thusly, bootstrapped/regtested on x86_64-linux and i686-linux, ok for
> trunk?
>
> 2017-03-07 Jakub Jelinek <jakub@redhat.com>
>
> PR target/79932
> * config/i386/avx512bwintrin.h (_mm512_packs_epi32,
> _mm512_maskz_packs_epi32, _mm512_mask_packs_epi32,
> _mm512_packus_epi32, _mm512_maskz_packus_epi32,
> _mm512_mask_packus_epi32): Move definitions outside of __OPTIMIZE__
> guarded section.
>
> * gcc.target/i386/pr79932-1.c: New test.
OK for trunk and backports.
Thanks,
Uros.
> --- gcc/config/i386/avx512bwintrin.h.jj 2017-01-23 18:09:48.000000000 +0100
> +++ gcc/config/i386/avx512bwintrin.h 2017-03-07 07:47:28.900049849 +0100
> @@ -2656,6 +2656,72 @@ _mm512_cmple_epi16_mask (__m512i __X, __
> (__mmask32) -1);
> }
>
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_packs_epi32 (__m512i __A, __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi)
> + _mm512_setzero_si512 (),
> + (__mmask32) -1);
> +}
> +
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_maskz_packs_epi32 (__mmask32 __M, __m512i __A, __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi)
> + _mm512_setzero_si512 (),
> + __M);
> +}
> +
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_mask_packs_epi32 (__m512i __W, __mmask32 __M, __m512i __A,
> + __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi) __W,
> + __M);
> +}
> +
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_packus_epi32 (__m512i __A, __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi)
> + _mm512_setzero_si512 (),
> + (__mmask32) -1);
> +}
> +
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_maskz_packus_epi32 (__mmask32 __M, __m512i __A, __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi)
> + _mm512_setzero_si512 (),
> + __M);
> +}
> +
> +extern __inline __m512i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm512_mask_packus_epi32 (__m512i __W, __mmask32 __M, __m512i __A,
> + __m512i __B)
> +{
> + return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> + (__v16si) __B,
> + (__v32hi) __W,
> + __M);
> +}
> +
> #ifdef __OPTIMIZE__
> extern __inline __mmask32
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> @@ -3012,72 +3078,6 @@ _mm512_cmp_epu8_mask (__m512i __X, __m51
> }
>
> extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_packs_epi32 (__m512i __A, __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi)
> - _mm512_setzero_si512 (),
> - (__mmask32) -1);
> -}
> -
> -extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_maskz_packs_epi32 (__mmask32 __M, __m512i __A, __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi)
> - _mm512_setzero_si512 (),
> - __M);
> -}
> -
> -extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_mask_packs_epi32 (__m512i __W, __mmask32 __M, __m512i __A,
> - __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packssdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi) __W,
> - __M);
> -}
> -
> -extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_packus_epi32 (__m512i __A, __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi)
> - _mm512_setzero_si512 (),
> - (__mmask32) -1);
> -}
> -
> -extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_maskz_packus_epi32 (__mmask32 __M, __m512i __A, __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi)
> - _mm512_setzero_si512 (),
> - __M);
> -}
> -
> -extern __inline __m512i
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_mask_packus_epi32 (__m512i __W, __mmask32 __M, __m512i __A,
> - __m512i __B)
> -{
> - return (__m512i) __builtin_ia32_packusdw512_mask ((__v16si) __A,
> - (__v16si) __B,
> - (__v32hi) __W,
> - __M);
> -}
> -
> -extern __inline __m512i
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_bslli_epi128 (__m512i __A, const int __N)
> {
> --- gcc/testsuite/gcc.target/i386/pr79932-1.c.jj 2017-03-07 07:54:45.181339418 +0100
> +++ gcc/testsuite/gcc.target/i386/pr79932-1.c 2017-03-07 07:54:24.000000000 +0100
> @@ -0,0 +1,19 @@
> +/* PR target/79932 */
> +/* { dg-do compile } */
> +/* { dg-options "-O0 -mavx512bw" } */
> +
> +#include <x86intrin.h>
> +
> +__m512i a, b, c, d, e, f, g, h, i;
> +__mmask32 m;
> +
> +void
> +foo (void)
> +{
> + d = _mm512_packs_epi32 (a, b);
> + e = _mm512_maskz_packs_epi32 (m, a, b);
> + f = _mm512_mask_packs_epi32 (c, m, a, b);
> + g = _mm512_packus_epi32 (a, b);
> + h = _mm512_maskz_packus_epi32 (m, a, b);
> + i = _mm512_mask_packus_epi32 (c, m, a, b);
> +}
>
> Jakub