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

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

gcc
	* config/rs6000/smmintrin.h (_mm_ceil_pd, _mm_ceil_ps,
	_mm_ceil_sd, _mm_ceil_ss): New.

diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
index 382f50c90c5756a0837989a83bc7a4028a6cbdc8..919627b0810a7e249fb1e09c83952b9957a41a6f 100644 (file)
--- a/gcc/config/rs6000/smmintrin.h
+++ b/gcc/config/rs6000/smmintrin.h
@@ -232,4 +232,36 @@ _mm_test_mix_ones_zeros (__m128i __A, __m128i __mask)
   return any_ones * any_zeros;
 }
 
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ceil_pd (__m128d __A)
+{
+  return (__m128d) vec_ceil ((__v2df) __A);
+}
+
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ceil_sd (__m128d __A, __m128d __B)
+{
+  __v2df __r = vec_ceil ((__v2df) __B);
+  __r[1] = ((__v2df) __A)[1];
+  return (__m128d) __r;
+}
+
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ceil_ps (__m128 __A)
+{
+  return (__m128) vec_ceil ((__v4sf) __A);
+}
+
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_ceil_ss (__m128 __A, __m128 __B)
+{
+  __v4sf __r = (__v4sf) __A;
+  __r[0] = __builtin_ceil (((__v4sf) __B)[0]);
+  return __r;
+}
+
 #endif