[Clang][AVX512][intrinsics] continue completing missing set intrinsics

Differential Revision: http://reviews.llvm.org/D20160

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@270047 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Headers/avx512fintrin.h b/lib/Headers/avx512fintrin.h
index 54dc534f552117d31f4adf6fd1973a64a224991f..b97308ffced5574549a0e7df731b5e54eeec5f6b 100644 (file)
--- a/lib/Headers/avx512fintrin.h
+++ b/lib/Headers/avx512fintrin.h
@@ -8983,6 +8983,21 @@ _mm512_mask_set1_epi64 (__m512i __O, __mmask8 __M, long long __A)
                  __M);
 }
 
+static __inline __m512i __DEFAULT_FN_ATTRS
+_mm512_set_epi32 (int __A, int __B, int __C, int __D,
+     int __E, int __F, int __G, int __H,
+     int __I, int __J, int __K, int __L,
+     int __M, int __N, int __O, int __P)
+{
+  return __extension__ (__m512i)(__v16si)
+  { __P, __O, __N, __M, __L, __K, __J, __I,
+    __H, __G, __F, __E, __D, __C, __B, __A };
+}
+
+#define _mm512_setr_epi32(e0,e1,e2,e3,e4,e5,e6,e7,           \
+       e8,e9,e10,e11,e12,e13,e14,e15)          \
+  _mm512_set_epi32(e15,e14,e13,e12,e11,e10,e9,e8,e7,e6,e5,e4,e3,e2,e1,e0)
+  
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_set_epi64 (long long __A, long long __B, long long __C,
      long long __D, long long __E, long long __F,
@@ -8992,6 +9007,9 @@ _mm512_set_epi64 (long long __A, long long __B, long long __C,
   { __H, __G, __F, __E, __D, __C, __B, __A };
 }
 
+#define _mm512_setr_epi64(e0,e1,e2,e3,e4,e5,e6,e7)           \
+  _mm512_set_epi64(e7,e6,e5,e4,e3,e2,e1,e0)
+
 static __inline__ __m512d __DEFAULT_FN_ATTRS
 _mm512_set_pd (double __A, double __B, double __C, double __D,
         double __E, double __F, double __G, double __H)
@@ -9000,6 +9018,9 @@ _mm512_set_pd (double __A, double __B, double __C, double __D,
   { __H, __G, __F, __E, __D, __C, __B, __A };
 }
 
+#define _mm512_setr_pd(e0,e1,e2,e3,e4,e5,e6,e7)              \
+  _mm512_set_pd(e7,e6,e5,e4,e3,e2,e1,e0)
+
 static __inline__ __m512 __DEFAULT_FN_ATTRS
 _mm512_set_ps (float __A, float __B, float __C, float __D,
         float __E, float __F, float __G, float __H,
@@ -9011,6 +9032,9 @@ _mm512_set_ps (float __A, float __B, float __C, float __D,
     __H, __G, __F, __E, __D, __C, __B, __A };
 }
 
+#define _mm512_setr_ps(e0,e1,e2,e3,e4,e5,e6,e7,e8,e9,e10,e11,e12,e13,e14,e15) \
+  _mm512_set_ps(e15,e14,e13,e12,e11,e10,e9,e8,e7,e6,e5,e4,e3,e2,e1,e0)
+
 #undef __DEFAULT_FN_ATTRS
 
 #endif // __AVX512FINTRIN_H

diff --git a/test/CodeGen/avx512f-builtins.c b/test/CodeGen/avx512f-builtins.c
index 6a290edcb9c385b1f6d12dd11eaa14e2786ab53c..6ae4bb2bc15b36a6da4c13010e0b7d61965ec6ea 100644 (file)
--- a/test/CodeGen/avx512f-builtins.c
+++ b/test/CodeGen/avx512f-builtins.c
@@ -6521,6 +6521,74 @@ __m512i test_mm512_mask_set1_epi32 (__m512i __O, __mmask16 __M, int __A)
   return _mm512_mask_set1_epi32 ( __O, __M, __A);
 }
 
+__m512i test_mm512_set_epi32 (int __A, int __B, int __C, int __D,
+               int __E, int __F, int __G, int __H,
+               int __I, int __J, int __K, int __L,
+               int __M, int __N, int __O, int __P)
+{
+ //CHECK-LABLE: @test_mm512_set_epi32
+ //CHECK: insertelement{{.*}}i32 0
+    //CHECK: insertelement{{.*}}i32 1
+    //CHECK: insertelement{{.*}}i32 2
+    //CHECK: insertelement{{.*}}i32 3
+    //CHECK: insertelement{{.*}}i32 4
+    //CHECK: insertelement{{.*}}i32 5
+    //CHECK: insertelement{{.*}}i32 6
+    //CHECK: insertelement{{.*}}i32 7
+    //CHECK: insertelement{{.*}}i32 8
+    //CHECK: insertelement{{.*}}i32 9
+    //CHECK: insertelement{{.*}}i32 10
+    //CHECK: insertelement{{.*}}i32 11
+    //CHECK: insertelement{{.*}}i32 12
+    //CHECK: insertelement{{.*}}i32 13
+    //CHECK: insertelement{{.*}}i32 14
+    //CHECK: insertelement{{.*}}i32 15
+ return _mm512_set_epi32( __A, __B, __C, __D,__E, __F, __G, __H,
+              __I, __J, __K, __L,__M, __N, __O, __P);
+}
+
+__m512i test_mm512_setr_epi32 (int __A, int __B, int __C, int __D,
+               int __E, int __F, int __G, int __H,
+               int __I, int __J, int __K, int __L,
+               int __M, int __N, int __O, int __P)
+{
+    //CHECK-LABLE: @test_mm512_setr_epi32
+ //CHECK: %0 = load{{.*}}%__P.addr, align 4
+ //CHECK: %1 = load{{.*}}%__O.addr, align 4
+ //CHECK: %2 = load{{.*}}%__N.addr, align 4
+ //CHECK: %3 = load{{.*}}%__M.addr, align 4
+ //CHECK: %4 = load{{.*}}%__L.addr, align 4
+ //CHECK: %5 = load{{.*}}%__K.addr, align 4
+ //CHECK: %6 = load{{.*}}%__J.addr, align 4
+ //CHECK: %7 = load{{.*}}%__I.addr, align 4
+ //CHECK: %8 = load{{.*}}%__H.addr, align 4
+ //CHECK: %9 = load{{.*}}%__G.addr, align 4
+ //CHECK: %10 = load{{.*}}%__F.addr, align 4
+ //CHECK: %11 = load{{.*}}%__E.addr, align 4
+ //CHECK: %12 = load{{.*}}%__D.addr, align 4
+ //CHECK: %13 = load{{.*}}%__C.addr, align 4
+ //CHECK: %14 = load{{.*}}%__B.addr, align 4
+ //CHECK: %15 = load{{.*}}%__A.addr, align 4
+ //CHECK: insertelement{{.*}}i32 0
+    //CHECK: insertelement{{.*}}i32 1
+    //CHECK: insertelement{{.*}}i32 2
+    //CHECK: insertelement{{.*}}i32 3
+    //CHECK: insertelement{{.*}}i32 4
+    //CHECK: insertelement{{.*}}i32 5
+    //CHECK: insertelement{{.*}}i32 6
+    //CHECK: insertelement{{.*}}i32 7
+    //CHECK: insertelement{{.*}}i32 8
+    //CHECK: insertelement{{.*}}i32 9
+    //CHECK: insertelement{{.*}}i32 10
+    //CHECK: insertelement{{.*}}i32 11
+    //CHECK: insertelement{{.*}}i32 12
+    //CHECK: insertelement{{.*}}i32 13
+    //CHECK: insertelement{{.*}}i32 14
+    //CHECK: insertelement{{.*}}i32 15
+ return _mm512_setr_epi32( __A, __B, __C, __D,__E, __F, __G, __H,
+              __I, __J, __K, __L,__M, __N, __O, __P);
+}
+
 __m512i test_mm512_mask_set1_epi64 (__m512i __O, __mmask8 __M, long long __A)
 {
     //CHECK-LABLE: @test_mm512_mask_set1_epi64
@@ -6544,6 +6612,30 @@ __m512i test_mm512_set_epi64 (long long __A, long long __B, long long __C,
   return _mm512_set_epi64(__A, __B, __C, __D, __E, __F, __G, __H );
 }
 
+__m512i test_mm512_setr_epi64 (long long __A, long long __B, long long __C,
+                              long long __D, long long __E, long long __F,
+                              long long __G, long long __H)
+{
+    //CHECK-LABLE: @test_mm512_setr_epi64
+    //CHECK: %0 = load{{.*}}%__H.addr, align 8
+ //CHECK: %1 = load{{.*}}%__G.addr, align 8
+ //CHECK: %2 = load{{.*}}%__F.addr, align 8
+ //CHECK: %3 = load{{.*}}%__E.addr, align 8
+ //CHECK: %4 = load{{.*}}%__D.addr, align 8
+ //CHECK: %5 = load{{.*}}%__C.addr, align 8
+ //CHECK: %6 = load{{.*}}%__B.addr, align 8
+ //CHECK: %7 = load{{.*}}%__A.addr, align 8
+ //CHECK: insertelement{{.*}}i32 0
+    //CHECK: insertelement{{.*}}i32 1
+    //CHECK: insertelement{{.*}}i32 2
+    //CHECK: insertelement{{.*}}i32 3
+    //CHECK: insertelement{{.*}}i32 4
+    //CHECK: insertelement{{.*}}i32 5
+    //CHECK: insertelement{{.*}}i32 6
+    //CHECK: insertelement{{.*}}i32 7
+  return _mm512_setr_epi64(__A, __B, __C, __D, __E, __F, __G, __H );
+}
+
 __m512d test_mm512_set_pd (double __A, double __B, double __C, double __D,
                            double __E, double __F, double __G, double __H)
 {
@@ -6559,6 +6651,29 @@ __m512d test_mm512_set_pd (double __A, double __B, double __C, double __D,
   return _mm512_set_pd( __A, __B, __C, __D, __E, __F, __G, __H);
 }
 
+__m512d test_mm512_setr_pd (double __A, double __B, double __C, double __D,
+                           double __E, double __F, double __G, double __H)
+{
+    //CHECK-LABLE: @test_mm512_setr_pd
+    //CHECK: %0 = load{{.*}}%__H.addr, align 8
+ //CHECK: %1 = load{{.*}}%__G.addr, align 8
+ //CHECK: %2 = load{{.*}}%__F.addr, align 8
+ //CHECK: %3 = load{{.*}}%__E.addr, align 8
+ //CHECK: %4 = load{{.*}}%__D.addr, align 8
+ //CHECK: %5 = load{{.*}}%__C.addr, align 8
+ //CHECK: %6 = load{{.*}}%__B.addr, align 8
+ //CHECK: %7 = load{{.*}}%__A.addr, align 8
+ //CHECK: insertelement{{.*}}i32 0
+    //CHECK: insertelement{{.*}}i32 1
+    //CHECK: insertelement{{.*}}i32 2
+    //CHECK: insertelement{{.*}}i32 3
+    //CHECK: insertelement{{.*}}i32 4
+    //CHECK: insertelement{{.*}}i32 5
+    //CHECK: insertelement{{.*}}i32 6
+    //CHECK: insertelement{{.*}}i32 7
+  return _mm512_setr_pd( __A, __B, __C, __D, __E, __F, __G, __H);
+}
+
 __m512 test_mm512_set_ps (float __A, float __B, float __C, float __D,
                           float __E, float __F, float __G, float __H,
                           float __I, float __J, float __K, float __L,
@@ -6612,3 +6727,45 @@ __m512i test_mm512_maskz_abs_epi32 (__mmask16 __U, __m512i __A)
   // CHECK: @llvm.x86.avx512.mask.pabs.d.512
   return _mm512_maskz_abs_epi32 (__U,__A);
 }
+
+__m512 test_mm512_setr_ps (float __A, float __B, float __C, float __D,
+                          float __E, float __F, float __G, float __H,
+                          float __I, float __J, float __K, float __L,
+                          float __M, float __N, float __O, float __P)
+{
+    //CHECK-LABLE: @test_mm512_setr_ps
+  //CHECK: %0 = load{{.*}}%__P.addr, align 4
+  //CHECK: %1 = load{{.*}}%__O.addr, align 4
+  //CHECK: %2 = load{{.*}}%__N.addr, align 4
+  //CHECK: %3 = load{{.*}}%__M.addr, align 4
+  //CHECK: %4 = load{{.*}}%__L.addr, align 4
+  //CHECK: %5 = load{{.*}}%__K.addr, align 4
+  //CHECK: %6 = load{{.*}}%__J.addr, align 4
+  //CHECK: %7 = load{{.*}}%__I.addr, align 4
+  //CHECK: %8 = load{{.*}}%__H.addr, align 4
+  //CHECK: %9 = load{{.*}}%__G.addr, align 4
+  //CHECK: %10 = load{{.*}}%__F.addr, align 4
+  //CHECK: %11 = load{{.*}}%__E.addr, align 4
+  //CHECK: %12 = load{{.*}}%__D.addr, align 4
+  //CHECK: %13 = load{{.*}}%__C.addr, align 4
+  //CHECK: %14 = load{{.*}}%__B.addr, align 4
+  //CHECK: %15 = load{{.*}}%__A.addr, align 4
+  //CHECK: insertelement{{.*}}i32 0
+    //CHECK: insertelement{{.*}}i32 1
+    //CHECK: insertelement{{.*}}i32 2
+    //CHECK: insertelement{{.*}}i32 3
+    //CHECK: insertelement{{.*}}i32 4
+    //CHECK: insertelement{{.*}}i32 5
+    //CHECK: insertelement{{.*}}i32 6
+    //CHECK: insertelement{{.*}}i32 7
+    //CHECK: insertelement{{.*}}i32 8
+    //CHECK: insertelement{{.*}}i32 9
+    //CHECK: insertelement{{.*}}i32 10
+    //CHECK: insertelement{{.*}}i32 11
+    //CHECK: insertelement{{.*}}i32 12
+    //CHECK: insertelement{{.*}}i32 13
+    //CHECK: insertelement{{.*}}i32 14
+    //CHECK: insertelement{{.*}}i32 15
+    return _mm512_setr_ps( __A, __B, __C, __D, __E, __F, __G, __H,
+                          __I, __J, __K, __L, __M, __N, __O, __P);
+}