diff mbox

[x86,7/n] Replace builtins with vector extensions

Message ID alpine.DEB.2.02.1411111231500.11887@stedding.saclay.inria.fr
State New
Headers show

Commit Message

Marc Glisse Nov. 11, 2014, 11:35 a.m. UTC 
Hello,

last patch, extending == and > to size 256. Regtested as usual.

Is the branch ready to be merged into trunk?

Comments

Uros Bizjak Nov. 11, 2014, 1:17 p.m. UTC | #1 
On Tue, Nov 11, 2014 at 12:35 PM, Marc Glisse <marc.glisse@inria.fr> wrote:

> last patch, extending == and > to size 256. Regtested as usual.
>
> Is the branch ready to be merged into trunk?
>
>  2014-11-10  Marc Glisse  <marc.glisse@inria.fr>
>
>         * config/i386/emmintrin.h (_mm_cmpeq_epi8, _mm_cmpeq_epi16,
>         _mm_cmpeq_epi32, _mm_cmplt_epi8, _mm_cmplt_epi16, _mm_cmplt_epi32,
>         _mm_cmpgt_epi8, _mm_cmpgt_epi16, _mm_cmpgt_epi32): Use vector
>         extensions instead of builtins.
>         * config/i386/smmintrin.h (_mm_cmpeq_epi64, _mm_cmpgt_epi64):
>         Likewise.

OK.

Please post the complete ChangeLog and complete patch for a review and merge.

Thanks,
Uros.
diff mbox

Patch

Index: ChangeLog.x86-intrinsics-ext
===================================================================
--- ChangeLog.x86-intrinsics-ext	(revision 217319)
+++ ChangeLog.x86-intrinsics-ext	(working copy)
@@ -1,10 +1,17 @@ 
+2014-11-11  Marc Glisse  <marc.glisse@inria.fr>
+
+	* config/i386/avx2intrin.h (_mm256_cmpeq_epi8, _mm256_cmpeq_epi16,
+	_mm256_cmpeq_epi32, _mm256_cmpeq_epi64, _mm256_cmpgt_epi8,
+	_mm256_cmpgt_epi16, _mm256_cmpgt_epi32, _mm256_cmpgt_epi64):
+	Use vector extensions instead of builtins.
+
 2014-11-10  Marc Glisse  <marc.glisse@inria.fr>
 
 	* config/i386/emmintrin.h (_mm_cmpeq_epi8, _mm_cmpeq_epi16,
 	_mm_cmpeq_epi32, _mm_cmplt_epi8, _mm_cmplt_epi16, _mm_cmplt_epi32,
 	_mm_cmpgt_epi8, _mm_cmpgt_epi16, _mm_cmpgt_epi32): Use vector
 	extensions instead of builtins.
 	* config/i386/smmintrin.h (_mm_cmpeq_epi64, _mm_cmpgt_epi64):
 	Likewise.
 
 2014-11-10  Marc Glisse  <marc.glisse@inria.fr>
Index: config/i386/avx2intrin.h
===================================================================
--- config/i386/avx2intrin.h	(revision 217318)
+++ config/i386/avx2intrin.h	(working copy)
@@ -223,73 +223,70 @@  _mm256_blend_epi16 (__m256i __X, __m256i
 #else
 #define _mm256_blend_epi16(X, Y, M)					\
   ((__m256i) __builtin_ia32_pblendw256 ((__v16hi)(__m256i)(X),		\
 					(__v16hi)(__m256i)(Y), (int)(M)))
 #endif
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi8 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpeqb256 ((__v32qi)__A, (__v32qi)__B);
+  return (__m256i) ((__v32qi)__A == (__v32qi)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi16 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpeqw256 ((__v16hi)__A, (__v16hi)__B);
+  return (__m256i) ((__v16hi)__A == (__v16hi)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi32 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpeqd256 ((__v8si)__A, (__v8si)__B);
+  return (__m256i) ((__v8si)__A == (__v8si)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi64 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpeqq256 ((__v4di)__A, (__v4di)__B);
+  return (__m256i) ((__v4di)__A == (__v4di)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi8 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpgtb256 ((__v32qi)__A,
-					     (__v32qi)__B);
+  return (__m256i) ((__v32qi)__A > (__v32qi)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi16 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpgtw256 ((__v16hi)__A,
-					     (__v16hi)__B);
+  return (__m256i) ((__v16hi)__A > (__v16hi)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi32 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpgtd256 ((__v8si)__A,
-					     (__v8si)__B);
+  return (__m256i) ((__v8si)__A > (__v8si)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi64 (__m256i __A, __m256i __B)
 {
-  return (__m256i)__builtin_ia32_pcmpgtq256 ((__v4di)__A, (__v4di)__B);
+  return (__m256i) ((__v4di)__A > (__v4di)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_hadd_epi16 (__m256i __X, __m256i __Y)
 {
   return (__m256i) __builtin_ia32_phaddw256 ((__v16hi)__X,
 					     (__v16hi)__Y);
 }