replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Clang][AVX512]Adding set4 intrinsics 

Differential Revision: http://reviews.llvm.org/D20866

llvm-svn: 271835
This commit is contained in:
Michael Zuckerman 2016-06-05 15:43:30 +00:00
parent 64c6de4525
commit 95721ac863
2 changed files with 99 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
clang/lib/Headers/avx512fintrin.h
View File

@ -343,6 +343,49 @@ _mm512_broadcastss_ps(__m128 __X)
__f, __f, __f, __f };
}
static __inline __m512i __DEFAULT_FN_ATTRS
_mm512_set4_epi32 (int __A, int __B, int __C, int __D)
{
return (__m512i)(__v16si)
{ __D, __C, __B, __A, __D, __C, __B, __A,
__D, __C, __B, __A, __D, __C, __B, __A };
}
static __inline __m512i __DEFAULT_FN_ATTRS
_mm512_set4_epi64 (long long __A, long long __B, long long __C,
long long __D)
{
return (__m512i) (__v8di)
{ __D, __C, __B, __A, __D, __C, __B, __A };
}
static __inline __m512d __DEFAULT_FN_ATTRS
_mm512_set4_pd (double __A, double __B, double __C, double __D)
{
return (__m512d)
{ __D, __C, __B, __A, __D, __C, __B, __A };
}
static __inline __m512 __DEFAULT_FN_ATTRS
_mm512_set4_ps (float __A, float __B, float __C, float __D)
{
return (__m512)
{ __D, __C, __B, __A, __D, __C, __B, __A,
__D, __C, __B, __A, __D, __C, __B, __A };
}
#define _mm512_setr4_epi32(e0,e1,e2,e3) \
_mm512_set4_epi32(e3,e2,e1,e0)
#define _mm512_setr4_epi64(e0,e1,e2,e3) \
_mm512_set4_epi64(e3,e2,e1,e0)
#define _mm512_setr4_pd(e0,e1,e2,e3) \
_mm512_set4_pd(e3,e2,e1,e0)
#define _mm512_setr4_ps(e0,e1,e2,e3) \
_mm512_set4_ps(e3,e2,e1,e0)
static __inline__ __m512d __DEFAULT_FN_ATTRS
_mm512_broadcastsd_pd(__m128d __X)
{

56
clang/test/CodeGen/avx512f-builtins.c
View File

@ -6236,6 +6236,62 @@ __m512d test_mm512_set1_epi16(short d)
return _mm512_set1_epi16(d);
}
__m512i test_mm512_set4_epi32 (int __A, int __B, int __C, int __D)
{
// CHECK-LABEL: @test_mm512_set4_epi32
// CHECK: insertelement <16 x i32> {{.*}}, i32 15
return _mm512_set4_epi32 (__A,__B,__C,__D);
}
__m512i test_mm512_set4_epi64 (long long __A, long long __B, long long __C, long long __D)
{
// CHECK-LABEL: @test_mm512_set4_epi64
// CHECK: insertelement <8 x i64> {{.*}}, i32 7
return _mm512_set4_epi64 (__A,__B,__C,__D);
}
__m512d test_mm512_set4_pd (double __A, double __B, double __C, double __D)
{
// CHECK-LABEL: @test_mm512_set4_pd
// CHECK: insertelement <8 x double> {{.*}}, i32 7
return _mm512_set4_pd (__A,__B,__C,__D);
}
__m512 test_mm512_set4_ps (float __A, float __B, float __C, float __D)
{
// CHECK-LABEL: @test_mm512_set4_ps
// CHECK: insertelement <16 x float> {{.*}}, i32 15
return _mm512_set4_ps (__A,__B,__C,__D);
}
__m512i test_mm512_setr4_epi32(int e0, int e1, int e2, int e3)
{
// CHECK-LABEL: @test_mm512_setr4_epi32
// CHECK: insertelement <16 x i32> {{.*}}, i32 15
return _mm512_setr4_epi32(e0, e1, e2, e3);
}
__m512i test_mm512_setr4_epi64(long long e0, long long e1, long long e2, long long e3)
{
// CHECK-LABEL: @test_mm512_setr4_epi64
// CHECK: insertelement <8 x i64> {{.*}}, i32 7
return _mm512_setr4_epi64(e0, e1, e2, e3);
}
__m512i test_mm512_setr4_pd(double e0, double e1, double e2, double e3)
{
// CHECK-LABEL: @test_mm512_setr4_pd
// CHECK: insertelement <8 x double> {{.*}}, i32 7
return _mm512_setr4_pd(e0,e1,e2,e3);
}
__m512i test_mm512_setr4_ps(float e0, float e1, float e2, float e3)
{
// CHECK-LABEL: @test_mm512_setr4_ps
// CHECK: insertelement <16 x float> {{.*}}, i32 15
return _mm512_setr4_ps(e0,e1,e2,e3);
}
__m512d test_mm512_castpd256_pd512(__m256d a)
{
// CHECK-LABEL: @test_mm512_castpd256_pd512