[gcc r12-2643] rs6000: Add support for SSE4.1 "ceil" intrinsics

[gcc r12-2643] rs6000: Add support for SSE4.1 "ceil" intrinsics

[Paul Clarke]

https://gcc.gnu.org/g:bd9a8737d478f7f1d01a9d5f1cc4309ffbb53103

commit r12-2643-gbd9a8737d478f7f1d01a9d5f1cc4309ffbb53103
Author: Paul A. Clarke <pc@us.ibm.com>
Date:   Thu Jul 1 17:04:51 2021 -0500

    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:
---
 gcc/config/rs6000/smmintrin.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
index 382f50c90c5..919627b0810 100644
--- 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