summaryrefslogtreecommitdiffstats
path: root/clang/lib/Headers
diff options
context:
space:
mode:
authorAhmed Bougacha <ahmed.bougacha@gmail.com>2015-08-20 20:27:21 +0000
committerAhmed Bougacha <ahmed.bougacha@gmail.com>2015-08-20 20:27:21 +0000
commit5e354cb54796d85cda2f37de2b0b2d5fda4dc4db (patch)
treeb5c0aba45ea76eb5fec904d3fa0ba80ca43161e5 /clang/lib/Headers
parent6511eb51949b83aa7c47147313c5f31d8cd94258 (diff)
downloadbcm5719-llvm-5e354cb54796d85cda2f37de2b0b2d5fda4dc4db.tar.gz
bcm5719-llvm-5e354cb54796d85cda2f37de2b0b2d5fda4dc4db.zip
[Headers][X86] Use __builtin_shufflevector in AVX2 broadcasts.
This lets us optimize them better. We agreed to remove the intrinsics, instead of combining them later, as, at -O0, we generate the expected instructions. Plus, it's a nice cleanup. Differential Revision: http://reviews.llvm.org/D10556 llvm-svn: 245605
Diffstat (limited to 'clang/lib/Headers')
-rw-r--r--clang/lib/Headers/avx2intrin.h22
1 files changed, 11 insertions, 11 deletions
diff --git a/clang/lib/Headers/avx2intrin.h b/clang/lib/Headers/avx2intrin.h
index cfa91410a33..a5c376cca62 100644
--- a/clang/lib/Headers/avx2intrin.h
+++ b/clang/lib/Headers/avx2intrin.h
@@ -760,7 +760,7 @@ _mm256_stream_load_si256(__m256i *__V)
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_broadcastss_ps(__m128 __X)
{
- return (__m128)__builtin_ia32_vbroadcastss_ps((__v4sf)__X);
+ return (__m128)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0);
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -772,13 +772,13 @@ _mm_broadcastsd_pd(__m128d __a)
static __inline__ __m256 __DEFAULT_FN_ATTRS
_mm256_broadcastss_ps(__m128 __X)
{
- return (__m256)__builtin_ia32_vbroadcastss_ps256((__v4sf)__X);
+ return (__m256)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m256d __DEFAULT_FN_ATTRS
_mm256_broadcastsd_pd(__m128d __X)
{
- return (__m256d)__builtin_ia32_vbroadcastsd_pd256((__v2df)__X);
+ return (__m256d)__builtin_shufflevector((__v2df)__X, (__v2df)__X, 0, 0, 0, 0);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
@@ -812,50 +812,50 @@ _mm256_broadcastsi128_si256(__m128i __X)
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_broadcastb_epi8(__m128i __X)
{
- return (__m256i)__builtin_ia32_pbroadcastb256((__v16qi)__X);
+ return (__m256i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_broadcastw_epi16(__m128i __X)
{
- return (__m256i)__builtin_ia32_pbroadcastw256((__v8hi)__X);
+ return (__m256i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_broadcastd_epi32(__m128i __X)
{
- return (__m256i)__builtin_ia32_pbroadcastd256((__v4si)__X);
+ return (__m256i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
_mm256_broadcastq_epi64(__m128i __X)
{
- return (__m256i)__builtin_ia32_pbroadcastq256(__X);
+ return (__m256i)__builtin_shufflevector(__X, __X, 0, 0, 0, 0);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_broadcastb_epi8(__m128i __X)
{
- return (__m128i)__builtin_ia32_pbroadcastb128((__v16qi)__X);
+ return (__m128i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_broadcastw_epi16(__m128i __X)
{
- return (__m128i)__builtin_ia32_pbroadcastw128((__v8hi)__X);
+ return (__m128i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_broadcastd_epi32(__m128i __X)
{
- return (__m128i)__builtin_ia32_pbroadcastd128((__v4si)__X);
+ return (__m128i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_broadcastq_epi64(__m128i __X)
{
- return (__m128i)__builtin_ia32_pbroadcastq128(__X);
+ return (__m128i)__builtin_shufflevector(__X, __X, 0, 0);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS
OpenPOWER on IntegriCloud