rs6000: Add Power10 optimization for most _mm_movemask*

Power10 ISA added `vextract*` instructions which are realized in the
`vec_extractm` instrinsic.

Use `vec_extractm` for `_mm_movemask_ps`, `_mm_movemask_pd`, and
`_mm_movemask_epi8` compatibility intrinsics, when `_ARCH_PWR10`.

2021-11-29  Paul A. Clarke  <pc@us.ibm.com>

gcc
	* config/rs6000/xmmintrin.h (_mm_movemask_ps): Use vec_extractm
	when _ARCH_PWR10.
	* config/rs6000/emmintrin.h (_mm_movemask_pd): Likewise.
	(_mm_movemask_epi8): Likewise.

diff --git a/gcc/config/rs6000/emmintrin.h b/gcc/config/rs6000/emmintrin.h
index 4125b12..c4758be 100644 (file)
--- a/gcc/config/rs6000/emmintrin.h
+++ b/gcc/config/rs6000/emmintrin.h
@@ -1233,6 +1233,9 @@ _mm_loadl_pd (__m128d __A, double const *__B)
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_pd (__m128d  __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((__v2du) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned int perm_mask =
     {
@@ -1252,6 +1255,7 @@ _mm_movemask_pd (__m128d  __A)
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */
 
@@ -2030,6 +2034,9 @@ _mm_min_epu8 (__m128i __A, __m128i __B)
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_epi8 (__m128i __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((__v16qu) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned char perm_mask =
     {
@@ -2046,6 +2053,7 @@ _mm_movemask_epi8 (__m128i __A)
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */
 

diff --git a/gcc/config/rs6000/xmmintrin.h b/gcc/config/rs6000/xmmintrin.h
index ae1a33e..4c093fd 100644 (file)
--- a/gcc/config/rs6000/xmmintrin.h
+++ b/gcc/config/rs6000/xmmintrin.h
@@ -1352,6 +1352,9 @@ _mm_storel_pi (__m64 *__P, __m128 __A)
 extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_movemask_ps (__m128  __A)
 {
+#ifdef _ARCH_PWR10
+  return vec_extractm ((vector unsigned int) __A);
+#else
   __vector unsigned long long result;
   static const __vector unsigned int perm_mask =
     {
@@ -1371,6 +1374,7 @@ _mm_movemask_ps (__m128  __A)
 #else
   return result[0];
 #endif
+#endif /* !_ARCH_PWR10 */
 }
 #endif /* _ARCH_PWR8 */