[Clang][AVX512]Adding set4 intrinsics

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

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@271835 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Headers/avx512fintrin.h b/lib/Headers/avx512fintrin.h
index e7b5471951cd1a88a3e702f34881cb911775b51d..523588cbaaeaa8e18d57a91ee13b862683e38027 100644 (file)
--- a/lib/Headers/avx512fintrin.h
+++ b/lib/Headers/avx512fintrin.h
@@ -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)
 {

diff --git a/test/CodeGen/avx512f-builtins.c b/test/CodeGen/avx512f-builtins.c
index 6168fbd39ffd8062fc0eed755b493f27fe7b07ad..ee9ae035b2b92c372c7bfd4e20b05207739d011b 100644 (file)
--- a/test/CodeGen/avx512f-builtins.c
+++ b/test/CodeGen/avx512f-builtins.c
@@ -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