Re: [PATCH][x86] Update s{r,l}li intrinsics.

[Ilya Tocar <tocarip dot intel at gmail dot com>]

I'd like to backport this to 4.8/4.9
Is this ok?

On 15 Jan 17:17, Ilya Tocar wrote:
> Hi,
> Looks like new ISA doc [1] renamed srli,slli intrinsics to bsrli,bslli.
> This patch adds b* versions, while keeping old srli for backward
> compatibility.
> OK for trunk?
> 
> 1:https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf
> 
> ChangeLog:
> gcc/
> 	* config/i386/avx2intrin.h (_mm256_bslli_si256,
> 	_mm256_bsrli_si256): New.
> 	* config/i386/emmintrin.h (_mm_bsrli_si128, _mm_bslli_si128):
> 	Ditto.
> 
> testsuite/
> 	* gcc.target/i386/sse-14.c: Test new intrinsic.
> 	* gcc.target/i386/sse-22.c: Diito.
> ---
>  gcc/config/i386/avx2intrin.h           | 18 ++++++++++++++++++
>  gcc/config/i386/emmintrin.h            | 16 ++++++++++++++++
>  gcc/testsuite/gcc.target/i386/sse-14.c |  2 ++
>  gcc/testsuite/gcc.target/i386/sse-22.c |  4 ++++
>  4 files changed, 40 insertions(+)
> 
> diff --git a/gcc/config/i386/avx2intrin.h b/gcc/config/i386/avx2intrin.h
> index 669f1dc..8a30c5b 100644
> --- a/gcc/config/i386/avx2intrin.h
> +++ b/gcc/config/i386/avx2intrin.h
> @@ -645,11 +645,20 @@ _mm256_sign_epi32 (__m256i __X, __m256i __Y)
>  #ifdef __OPTIMIZE__
>  extern __inline __m256i
>  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm256_bslli_si256 (__m256i __A, const int __N)
> +{
> +  return (__m256i)__builtin_ia32_pslldqi256 (__A, __N * 8);
> +}
> +
> +extern __inline __m256i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
>  _mm256_slli_si256 (__m256i __A, const int __N)
>  {
>    return (__m256i)__builtin_ia32_pslldqi256 (__A, __N * 8);
>  }
>  #else
> +#define _mm256_bslli_si256(A, N) \
> +  ((__m256i)__builtin_ia32_pslldqi256 ((__m256i)(A), (int)(N) * 8))
>  #define _mm256_slli_si256(A, N) \
>    ((__m256i)__builtin_ia32_pslldqi256 ((__m256i)(A), (int)(N) * 8))
>  #endif
> @@ -727,11 +736,20 @@ _mm256_sra_epi32 (__m256i __A, __m128i __B)
>  #ifdef __OPTIMIZE__
>  extern __inline __m256i
>  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> +_mm256_bsrli_si256 (__m256i __A, const int __N)
> +{
> +  return (__m256i)__builtin_ia32_psrldqi256 (__A, __N * 8);
> +}
> +
> +extern __inline __m256i
> +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
>  _mm256_srli_si256 (__m256i __A, const int __N)
>  {
>    return (__m256i)__builtin_ia32_psrldqi256 (__A, __N * 8);
>  }
>  #else
> +#define _mm256_bsrli_si256(A, N) \
> +  ((__m256i)__builtin_ia32_psrldqi256 ((__m256i)(A), (int)(N) * 8))
>  #define _mm256_srli_si256(A, N) \
>    ((__m256i)__builtin_ia32_psrldqi256 ((__m256i)(A), (int)(N) * 8))
>  #endif
> diff --git a/gcc/config/i386/emmintrin.h b/gcc/config/i386/emmintrin.h
> index ad37fac..b19f05a 100644
> --- a/gcc/config/i386/emmintrin.h
> +++ b/gcc/config/i386/emmintrin.h
> @@ -1165,6 +1165,18 @@ _mm_srai_epi32 (__m128i __A, int __B)
>  
>  #ifdef __OPTIMIZE__
>  extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_bsrli_si128 (__m128i __A, const int __N)
> +{
> +  return (__m128i)__builtin_ia32_psrldqi128 (__A, __N * 8);
> +}
> +
> +extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_bslli_si128 (__m128i __A, const int __N)
> +{
> +  return (__m128i)__builtin_ia32_pslldqi128 (__A, __N * 8);
> +}
> +
> +extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
>  _mm_srli_si128 (__m128i __A, const int __N)
>  {
>    return (__m128i)__builtin_ia32_psrldqi128 (__A, __N * 8);
> @@ -1176,6 +1188,10 @@ _mm_slli_si128 (__m128i __A, const int __N)
>    return (__m128i)__builtin_ia32_pslldqi128 (__A, __N * 8);
>  }
>  #else
> +#define _mm_bsrli_si128(A, N) \
> +  ((__m128i)__builtin_ia32_psrldqi128 ((__m128i)(A), (int)(N) * 8))
> +#define _mm_bslli_si128(A, N) \
> +  ((__m128i)__builtin_ia32_pslldqi128 ((__m128i)(A), (int)(N) * 8))
>  #define _mm_srli_si128(A, N) \
>    ((__m128i)__builtin_ia32_psrldqi128 ((__m128i)(A), (int)(N) * 8))
>  #define _mm_slli_si128(A, N) \
> diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c b/gcc/testsuite/gcc.target/i386/sse-14.c
> index f3f6c5c..e8791e3 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-14.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-14.c
> @@ -601,6 +601,8 @@ test_2 (_mm_alignr_pi8, __m64, __m64, __m64, 1)
>  
>  /* emmintrin.h */
>  test_2 (_mm_shuffle_pd, __m128d, __m128d, __m128d, 1)
> +test_1 (_mm_bsrli_si128, __m128i, __m128i, 1)
> +test_1 (_mm_bslli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_srli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_slli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_extract_epi16, int, __m128i, 1)
> diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c b/gcc/testsuite/gcc.target/i386/sse-22.c
> index 0d7bd16..5735514 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-22.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-22.c
> @@ -138,6 +138,8 @@ test_1 (_mm_prefetch, void, void *, _MM_HINT_NTA)
>  #endif
>  #include <emmintrin.h>
>  test_2 (_mm_shuffle_pd, __m128d, __m128d, __m128d, 1)
> +test_1 (_mm_bsrli_si128, __m128i, __m128i, 1)
> +test_1 (_mm_bslli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_srli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_slli_si128, __m128i, __m128i, 1)
>  test_1 (_mm_extract_epi16, int, __m128i, 1)
> @@ -269,6 +271,8 @@ test_2 ( _mm256_blend_epi16, __m256i, __m256i, __m256i, 1)
>  test_1 ( _mm256_shuffle_epi32, __m256i, __m256i, 1)
>  test_1 ( _mm256_shufflehi_epi16, __m256i, __m256i, 1)
>  test_1 ( _mm256_shufflelo_epi16, __m256i, __m256i, 1)
> +test_1 ( _mm256_bslli_si256, __m256i, __m256i, 8)
> +test_1 ( _mm256_bsrli_si256, __m256i, __m256i, 8)
>  test_1 ( _mm256_slli_si256, __m256i, __m256i, 8)
>  test_1 ( _mm256_srli_si256, __m256i, __m256i, 8)
>  test_2 ( _mm_blend_epi32, __m128i, __m128i, __m128i, 1)
> -- 
> 1.8.3.1
>