rs6000: Add support for SSE4.1 "floor" intrinsics

2021-07-30  Paul A. Clarke  <pc@us.ibm.com>

gcc
	* config/rs6000/smmintrin.h (_mm_floor_pd, _mm_floor_ps,
	_mm_floor_sd, _mm_floor_ss): New.

diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
index 919627b..0145b92 100644 (file)
--- a/gcc/config/rs6000/smmintrin.h
+++ b/gcc/config/rs6000/smmintrin.h
@@ -248,6 +248,22 @@ _mm_ceil_sd (__m128d __A, __m128d __B)
   return (__m128d) __r;
 }
 
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_floor_pd (__m128d __A)
+{
+  return (__m128d) vec_floor ((__v2df) __A);
+}
+
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_floor_sd (__m128d __A, __m128d __B)
+{
+  __v2df __r = vec_floor ((__v2df) __B);
+  __r[1] = ((__v2df) __A)[1];
+  return (__m128d) __r;
+}
+
 __inline __m128
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm_ceil_ps (__m128 __A)
@@ -264,4 +280,20 @@ _mm_ceil_ss (__m128 __A, __m128 __B)
   return __r;
 }
 
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_floor_ps (__m128 __A)
+{
+  return (__m128) vec_floor ((__v4sf) __A);
+}
+
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_floor_ss (__m128 __A, __m128 __B)
+{
+  __v4sf __r = (__v4sf) __A;
+  __r[0] = __builtin_floor (((__v4sf) __B)[0]);
+  return __r;
+}
+
 #endif