Vendor import of clang trunk r256945:

https://llvm.org/svn/llvm-project/cfe/trunk@256945
author: dim <dim@FreeBSD.org> 2016-01-06 20:02:26 +0000
committer: dim <dim@FreeBSD.org> 2016-01-06 20:02:26 +0000
commit: fc74ff5a0792641885551a63d9ddf8cbfdf76e3c (patch)
tree: 955a1295c3fd4378a49478ad5835ca21b769417e /test/OpenMP
parent: 3176e97f130184ece0e1a21352c8124cc83ff24a (diff)
download: FreeBSD-src-fc74ff5a0792641885551a63d9ddf8cbfdf76e3c.zip
FreeBSD-src-fc74ff5a0792641885551a63d9ddf8cbfdf76e3c.tar.gz
16 files changed, 1069 insertions, 294 deletions
diff --git a/test/OpenMP/for_simd_ast_print.cpp b/test/OpenMP/for_simd_ast_print.cpp
index 725c727..d4b13ba 100644
--- a/test/OpenMP/for_simd_ast_print.cpp
+++ b/test/OpenMP/for_simd_ast_print.cpp
@@ -14,8 +14,8 @@ template<class T, class N> T reduct(T* arr, N num) {
   N myind;
   T sum = (T)0;
 // CHECK: T sum = (T)0;
-#pragma omp for simd private(myind, g_ind), linear(ind), aligned(arr)
-// CHECK-NEXT: #pragma omp for simd private(myind,g_ind) linear(ind) aligned(arr)
+#pragma omp for simd private(myind, g_ind), linear(ind), aligned(arr) ordered
+// CHECK-NEXT: #pragma omp for simd private(myind,g_ind) linear(ind) aligned(arr) ordered
   for (i = 0; i < num; ++i) {
     myind = ind;
     T cur = arr[myind];
@@ -92,8 +92,8 @@ int main (int argc, char **argv) {
   int k1=0,k2=0;
   static int *a;
 // CHECK: static int *a;
-#pragma omp for simd
-// CHECK-NEXT: #pragma omp for simd
+#pragma omp for simd ordered
+// CHECK-NEXT: #pragma omp for simd ordered
   for (int i=0; i < 2; ++i)*a=2;
 // CHECK-NEXT: for (int i = 0; i < 2; ++i)
 // CHECK-NEXT: *a = 2;
diff --git a/test/OpenMP/for_simd_codegen.cpp b/test/OpenMP/for_simd_codegen.cpp
index cc8193d..e1aa892 100644
--- a/test/OpenMP/for_simd_codegen.cpp
+++ b/test/OpenMP/for_simd_codegen.cpp
@@ -28,24 +28,24 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV:%[^,]+]],
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[SIMPLE_LOOP1_BODY:.+]], label %[[SIMPLE_LOOP1_END:[^,]+]]
   for (int i = 3; i < 32; i += 5) {
 // CHECK: [[SIMPLE_LOOP1_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV1_1:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV1_1:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
 // CHECK: [[CALC_I_1:%.+]] = mul nsw i32 [[IV1_1]], 5
 // CHECK-NEXT: [[CALC_I_2:%.+]] = add nsw i32 3, [[CALC_I_1]]
-// CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]
 // ... loop body ...
 // End of body: store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: store float [[RESULT:%.+]], float*
     a[i] = b[i] * c[i] * d[i];
-// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
-// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]
 // br label %{{.+}}, !llvm.loop !{{.+}}
   }
 // CHECK: [[SIMPLE_LOOP1_END]]
@@ -132,36 +132,36 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
 // CHECK: store i64 [[LB_VAL]], i64* [[OMP_IV3:%[^,]+]],
 
-// CHECK: [[IV3:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[IV3:%.+]] = load i64, i64* [[OMP_IV3]]
+// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP3:%.+]] = icmp ule i64 [[IV3]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP3]], label %[[SIMPLE_LOOP3_BODY:.+]], label %[[SIMPLE_LOOP3_END:[^,]+]]
   for (unsigned long long it = 2000; it >= 600; it-=400) {
 // CHECK: [[SIMPLE_LOOP3_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV3_0:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[IV3_0:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul i64 [[IV3_0]], 400
 // CHECK-NEXT: [[LC_IT_2:%.+]] = sub i64 2000, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64*
 //
 // Linear start and step are used to calculate current value of the linear variable.
-// CHECK: [[LINSTART:.+]] = load i32, i32* [[LIN_START]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[LINSTEP:.+]] = load i64, i64* [[LIN_STEP]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK-NOT: store i32 {{.+}}, i32* [[LIN_VAR]],{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[GLINSTART:.+]] = load double*, double** [[GLIN_START]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK-NEXT: [[IV3_1:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[LINSTART:.+]] = load i32, i32* [[LIN_START]]
+// CHECK: [[LINSTEP:.+]] = load i64, i64* [[LIN_STEP]]
+// CHECK-NOT: store i32 {{.+}}, i32* [[LIN_VAR]],
+// CHECK: [[GLINSTART:.+]] = load double*, double** [[GLIN_START]]
+// CHECK-NEXT: [[IV3_1:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[MUL:%.+]] = mul i64 [[IV3_1]], 1
 // CHECK: [[GEP:%.+]] = getelementptr{{.*}}[[GLINSTART]]
-// CHECK-NEXT: store double* [[GEP]], double** [[G_PTR_CUR:%[^,]+]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store double* [[GEP]], double** [[G_PTR_CUR:%[^,]+]]
     *g_ptr++ = 0.0;
-// CHECK: [[GEP_VAL:%.+]] = load double{{.*}}[[G_PTR_CUR]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: store double{{.*}}[[GEP_VAL]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[GEP_VAL:%.+]] = load double{{.*}}[[G_PTR_CUR]]
+// CHECK: store double{{.*}}[[GEP_VAL]]
     a[it + lin]++;
 // CHECK: [[FLT_INC:%.+]] = fadd float
-// CHECK-NEXT: store float [[FLT_INC]],{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[IV3_2:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store float [[FLT_INC]],
+// CHECK: [[IV3_2:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[ADD3_2:%.+]] = add i64 [[IV3_2]], 1
-// CHECK-NEXT: store i64 [[ADD3_2]], i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store i64 [[ADD3_2]], i64* [[OMP_IV3]]
   }
 // CHECK: [[SIMPLE_LOOP3_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -190,22 +190,22 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV4:%[^,]+]],
 
-// CHECK: [[IV4:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4:%.+]] = load i32, i32* [[OMP_IV4]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP4:%.+]] = icmp sle i32 [[IV4]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP4]], label %[[SIMPLE_LOOP4_BODY:.+]], label %[[SIMPLE_LOOP4_END:[^,]+]]
   for (short it = 6; it <= 20; it-=-4) {
 // CHECK: [[SIMPLE_LOOP4_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV4_0:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4_0:%.+]] = load i32, i32* [[OMP_IV4]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i32 [[IV4_0]], 4
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i32 6, [[LC_IT_1]]
 // CHECK-NEXT: [[LC_IT_3:%.+]] = trunc i32 [[LC_IT_2]] to i16
-// CHECK-NEXT: store i16 [[LC_IT_3]], i16* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK-NEXT: store i16 [[LC_IT_3]], i16*
 
-// CHECK: [[IV4_2:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4_2:%.+]] = load i32, i32* [[OMP_IV4]]
 // CHECK-NEXT: [[ADD4_2:%.+]] = add nsw i32 [[IV4_2]], 1
-// CHECK-NEXT: store i32 [[ADD4_2]], i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK-NEXT: store i32 [[ADD4_2]], i32* [[OMP_IV4]]
   }
 // CHECK: [[SIMPLE_LOOP4_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -227,22 +227,22 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV5:%[^,]+]],
 
-// CHECK: [[IV5:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5:%.+]] = load i32, i32* [[OMP_IV5]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP5:%.+]] = icmp sle i32 [[IV5]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP5]], label %[[SIMPLE_LOOP5_BODY:.+]], label %[[SIMPLE_LOOP5_END:[^,]+]]
   for (unsigned char it = 'z'; it >= 'a'; it+=-1) {
 // CHECK: [[SIMPLE_LOOP5_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV5_0:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5_0:%.+]] = load i32, i32* [[OMP_IV5]]
 // CHECK-NEXT: [[IV5_1:%.+]] = mul nsw i32 [[IV5_0]], 1
 // CHECK-NEXT: [[LC_IT_1:%.+]] = sub nsw i32 122, [[IV5_1]]
 // CHECK-NEXT: [[LC_IT_2:%.+]] = trunc i32 [[LC_IT_1]] to i8
-// CHECK-NEXT: store i8 [[LC_IT_2]], i8* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK-NEXT: store i8 [[LC_IT_2]], i8*
 
-// CHECK: [[IV5_2:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5_2:%.+]] = load i32, i32* [[OMP_IV5]]
 // CHECK-NEXT: [[ADD5_2:%.+]] = add nsw i32 [[IV5_2]], 1
-// CHECK-NEXT: store i32 [[ADD5_2]], i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK-NEXT: store i32 [[ADD5_2]], i32* [[OMP_IV5]]
   }
 // CHECK: [[SIMPLE_LOOP5_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -276,24 +276,24 @@ void simple(float *a, float *b, float *c, float *d) {
 
 // CHECK: br label %[[SIMD_LOOP7_COND:[^,]+]]
 // CHECK: [[SIMD_LOOP7_COND]]
-// CHECK-NEXT: [[IV7:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: [[IV7:%.+]] = load i64, i64* [[OMP_IV7]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP7:%.+]] = icmp sle i64 [[IV7]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP7]], label %[[SIMPLE_LOOP7_BODY:.+]], label %[[SIMPLE_LOOP7_END:[^,]+]]
   for (long long i = -10; i < 10; i += 3) {
 // CHECK: [[SIMPLE_LOOP7_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV7_0:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK: [[IV7_0:%.+]] = load i64, i64* [[OMP_IV7]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i64 [[IV7_0]], 3
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i64 -10, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
-// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],
+// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]
 // CHECK-NEXT: [[CONV:%.+]] = trunc i64 [[LC_VAL]] to i32
-// CHECK-NEXT: store i32 [[CONV]], i32* [[A_PRIV:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i32 [[CONV]], i32* [[A_PRIV:%[^,]+]],
     A = i;
-// CHECK: [[IV7_2:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK: [[IV7_2:%.+]] = load i64, i64* [[OMP_IV7]]
 // CHECK-NEXT: [[ADD7_2:%.+]] = add nsw i64 [[IV7_2]], 1
-// CHECK-NEXT: store i64 [[ADD7_2]], i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i64 [[ADD7_2]], i64* [[OMP_IV7]]
   }
 // CHECK: [[SIMPLE_LOOP7_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -329,23 +329,23 @@ void simple(float *a, float *b, float *c, float *d) {
 
 // CHECK: br label %[[SIMD_LOOP8_COND:[^,]+]]
 // CHECK: [[SIMD_LOOP8_COND]]
-// CHECK-NEXT: [[IV8:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: [[IV8:%.+]] = load i64, i64* [[OMP_IV8]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP8:%.+]] = icmp sle i64 [[IV8]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP8]], label %[[SIMPLE_LOOP8_BODY:.+]], label %[[SIMPLE_LOOP8_END:[^,]+]]
   for (long long i = -10; i < 10; i += 3) {
 // CHECK: [[SIMPLE_LOOP8_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV8_0:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK: [[IV8_0:%.+]] = load i64, i64* [[OMP_IV8]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i64 [[IV8_0]], 3
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i64 -10, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
-// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
-// CHECK: store i32 %{{.+}}, i32* [[R_PRIV]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],
+// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]
+// CHECK: store i32 %{{.+}}, i32* [[R_PRIV]],
     R *= i;
-// CHECK: [[IV8_2:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK: [[IV8_2:%.+]] = load i64, i64* [[OMP_IV8]]
 // CHECK-NEXT: [[ADD8_2:%.+]] = add nsw i64 [[IV8_2]], 1
-// CHECK-NEXT: store i64 [[ADD8_2]], i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: store i64 [[ADD8_2]], i64* [[OMP_IV8]]
   }
 // CHECK: [[SIMPLE_LOOP8_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -389,27 +389,27 @@ int templ1(T a, T *z) {
 // CHECK: store i64 [[LB_VAL]], i64* [[T1_OMP_IV:%[^,]+]],
 
 // ...
-// CHECK: [[IV:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV:%.+]] = load i64, i64* [[T1_OMP_IV]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP1:%.+]] = icmp sle i64 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP1]], label %[[T1_BODY:.+]], label %[[T1_END:[^,]+]]
 // CHECK: [[T1_BODY]]
 // Loop counters i and j updates:
-// CHECK: [[IV1:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV1:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[I_1:%.+]] = sdiv i64 [[IV1]], 4
 // CHECK-NEXT: [[I_1_MUL1:%.+]] = mul nsw i64 [[I_1]], 1
 // CHECK-NEXT: [[I_1_ADD0:%.+]] = add nsw i64 0, [[I_1_MUL1]]
 // CHECK-NEXT: [[I_2:%.+]] = trunc i64 [[I_1_ADD0]] to i32
-// CHECK-NEXT: store i32 [[I_2]], i32* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
-// CHECK: [[IV2:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i32 [[I_2]], i32*
+// CHECK: [[IV2:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[J_1:%.+]] = srem i64 [[IV2]], 4
 // CHECK-NEXT: [[J_2:%.+]] = mul nsw i64 [[J_1]], 2
 // CHECK-NEXT: [[J_2_ADD0:%.+]] = add nsw i64 0, [[J_2]]
-// CHECK-NEXT: store i64 [[J_2_ADD0]], i64* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i64 [[J_2_ADD0]], i64*
 // simd.for.inc:
-// CHECK: [[IV3:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV3:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[INC:%.+]] = add nsw i64 [[IV3]], 1
-// CHECK-NEXT: store i64 [[INC]], i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i64 [[INC]], i64* [[T1_OMP_IV]]
 // CHECK-NEXT: br label {{%.+}}
 // CHECK: [[T1_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -480,14 +480,14 @@ void iter_simple(IterDouble ia, IterDouble ib, IterDouble ic) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[IT_OMP_IV:%[^,]+]],
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}} !llvm.mem.parallel_loop_access ![[ITER_LOOP_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[IT_OMP_IV]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[IT_BODY:[^,]+]], label %[[IT_END:[^,]+]]
   for (IterDouble i = ia; i < ib; ++i) {
 // CHECK: [[IT_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i32, i32* [[IT_OMP_IV]]
 // Call of operator+ (i, IV).
 // CHECK: {{%.+}} = invoke {{.+}} @{{.*}}IterDouble{{.*}}
 // ... loop body ...
@@ -495,12 +495,12 @@ void iter_simple(IterDouble ia, IterDouble ib, IterDouble ic) {
 // Float multiply and save result.
 // CHECK: [[MULR:%.+]] = fmul double {{%.+}}, 5.000000e-01
 // CHECK-NEXT: invoke {{.+}} @{{.*}}IterDouble{{.*}}
-// CHECK: store double [[MULR:%.+]], double* [[RESULT_ADDR:%.+]], !llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: store double [[MULR:%.+]], double* [[RESULT_ADDR:%.+]]
    ++ic;
 //
-// CHECK: [[IV2:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i32, i32* [[IT_OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add nsw i32 [[IV2]], 1
-// CHECK-NEXT: store i32 [[ADD2]], i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK-NEXT: store i32 [[ADD2]], i32* [[IT_OMP_IV]]
 // br label %{{.*}}, !llvm.loop ![[ITER_LOOP_ID]]
   }
 // CHECK: [[IT_END]]
@@ -533,8 +533,8 @@ void collapsed(float *a, float *b, float *c, float *d) {
 //
   #pragma omp for simd collapse(4)
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp ule i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[COLL1_BODY:[^,]+]], label %[[COLL1_END:[^,]+]]
   for (i = 1; i < 3; i++) // 2 iterations
@@ -544,25 +544,25 @@ void collapsed(float *a, float *b, float *c, float *d) {
         {
 // CHECK: [[COLL1_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i32, i32* [[OMP_IV]]
 // Calculation of the loop counters values.
 // CHECK: [[CALC_I_1:%.+]] = udiv i32 [[IV1]], 60
 // CHECK-NEXT: [[CALC_I_1_MUL1:%.+]] = mul i32 [[CALC_I_1]], 1
 // CHECK-NEXT: [[CALC_I_2:%.+]] = add i32 1, [[CALC_I_1_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]
-// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_J_1:%.+]] = udiv i32 [[IV1_2]], 20
 // CHECK-NEXT: [[CALC_J_2:%.+]] = urem i32 [[CALC_J_1]], 3
 // CHECK-NEXT: [[CALC_J_2_MUL1:%.+]] = mul i32 [[CALC_J_2]], 1
 // CHECK-NEXT: [[CALC_J_3:%.+]] = add i32 2, [[CALC_J_2_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_J_3]], i32* [[LC_J:.+]]
-// CHECK: [[IV1_3:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_3:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_K_1:%.+]] = udiv i32 [[IV1_3]], 5
 // CHECK-NEXT: [[CALC_K_2:%.+]] = urem i32 [[CALC_K_1]], 4
 // CHECK-NEXT: [[CALC_K_2_MUL1:%.+]] = mul i32 [[CALC_K_2]], 1
 // CHECK-NEXT: [[CALC_K_3:%.+]] = add i32 3, [[CALC_K_2_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_K_3]], i32* [[LC_K:.+]]
-// CHECK: [[IV1_4:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_4:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_L_1:%.+]] = urem i32 [[IV1_4]], 5
 // CHECK-NEXT: [[CALC_L_1_MUL1:%.+]] = mul i32 [[CALC_L_1]], 1
 // CHECK-NEXT: [[CALC_L_2:%.+]] = add i32 4, [[CALC_L_1_MUL1]]
@@ -570,12 +570,12 @@ void collapsed(float *a, float *b, float *c, float *d) {
 // CHECK-NEXT: store i16 [[CALC_L_3]], i16* [[LC_L:.+]]
 // ... loop body ...
 // End of body: store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]
     float res = b[j] * c[k];
     a[i] = res * d[l];
-// CHECK: [[IV2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add i32 [[IV2]], 1
-// CHECK-NEXT: store i32 [[ADD2]], i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK-NEXT: store i32 [[ADD2]], i32* [[OMP_IV]]
 // br label %{{[^,]+}}, !llvm.loop ![[COLL1_LOOP_ID]]
 // CHECK: [[COLL1_END]]
   }
@@ -621,8 +621,8 @@ void widened(float *a, float *b, float *c, float *d) {
 //
   #pragma omp for simd collapse(2) private(globalfloat, localint)
 
-// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i64 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[WIDE1_BODY:[^,]+]], label %[[WIDE1_END:[^,]+]]
   for (i = 1; i < 3; i++) // 2 iterations
@@ -630,10 +630,10 @@ void widened(float *a, float *b, float *c, float *d) {
   {
 // CHECK: [[WIDE1_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i64, i64* [[OMP_IV]]
 // Calculation of the loop counters values...
 // CHECK: store i32 {{[^,]+}}, i32* [[LC_I:.+]]
-// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]
 // CHECK: store i16 {{[^,]+}}, i16* [[LC_J:.+]]
 // ... loop body ...
 //
@@ -642,14 +642,14 @@ void widened(float *a, float *b, float *c, float *d) {
     globalfloat = (float)j/i;
     float res = b[j] * c[j];
 // Store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]
     a[i] = res * d[i];
 // Then there's a store into private var localint:
-// CHECK: store i32 {{.+}}, i32* [[LOCALINT:%[^,]+]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: store i32 {{.+}}, i32* [[LOCALINT:%[^,]+]]
     localint = (int)j;
-// CHECK: [[IV2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i64, i64* [[OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add nsw i64 [[IV2]], 1
-// CHECK-NEXT: store i64 [[ADD2]], i64* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK-NEXT: store i64 [[ADD2]], i64* [[OMP_IV]]
 //
 // br label %{{[^,]+}}, !llvm.loop ![[WIDE1_LOOP_ID]]
 // CHECK: [[WIDE1_END]]
diff --git a/test/OpenMP/for_simd_loop_messages.cpp b/test/OpenMP/for_simd_loop_messages.cpp
index 958c7f6..afd7b0b 100644
--- a/test/OpenMP/for_simd_loop_messages.cpp
+++ b/test/OpenMP/for_simd_loop_messages.cpp
@@ -719,10 +719,18 @@ void test_loop_firstprivate_lastprivate() {
 
 void test_ordered() {
 #pragma omp parallel
-// expected-error@+1 2 {{unexpected OpenMP clause 'ordered' in directive '#pragma omp for simd'}}
 #pragma omp for simd ordered ordered // expected-error {{directive '#pragma omp for simd' cannot contain more than one 'ordered' clause}}
   for (int i = 0; i < 16; ++i)
     ;
+#pragma omp parallel
+#pragma omp for simd ordered
+  for (int i = 0; i < 16; ++i)
+    ;
+#pragma omp parallel
+// expected-error@+1 {{'ordered' clause with a parameter can not be specified in '#pragma omp for simd' directive}}
+#pragma omp for simd ordered(1)
+  for (int i = 0; i < 16; ++i)
+    ;
 }
 
 void test_nowait() {
diff --git a/test/OpenMP/nesting_of_regions.cpp b/test/OpenMP/nesting_of_regions.cpp
index 6445c6b..b2b87db 100644
--- a/test/OpenMP/nesting_of_regions.cpp
+++ b/test/OpenMP/nesting_of_regions.cpp
@@ -2060,7 +2060,7 @@ void foo() {
   }
 #pragma omp ordered
   {
-#pragma omp parallel for simd ordered //expected-error {{unexpected OpenMP clause 'ordered' in directive '#pragma omp parallel for simd'}}
+#pragma omp parallel for simd ordered
     for (int j = 0; j < 10; ++j) {
 #pragma omp ordered // expected-error {{OpenMP constructs may not be nested inside a simd region}}
       {
@@ -2070,6 +2070,16 @@ void foo() {
   }
 #pragma omp ordered
   {
+#pragma omp parallel for simd ordered
+    for (int j = 0; j < 10; ++j) {
+#pragma omp ordered simd
+      {
+        bar();
+      }
+    }
+  }
+#pragma omp ordered
+  {
 #pragma omp parallel for
     for (int i = 0; i < 10; ++i)
       ;
diff --git a/test/OpenMP/ordered_codegen.cpp b/test/OpenMP/ordered_codegen.cpp
index e77c1be..daa6211 100644
--- a/test/OpenMP/ordered_codegen.cpp
+++ b/test/OpenMP/ordered_codegen.cpp
@@ -224,6 +224,14 @@ void foo_simd(int low, int up) {
 #pragma omp ordered simd
     f[i] = 1.0;
   }
+  // CHECK: store float 0.000000e+00, float* %{{.+}}, align {{[0-9]+}}
+  // CHECK-NEXT: call void [[CAP_FUNC:@.+]](i32* %{{.+}}) #{{[0-9]+}}
+#pragma omp for simd ordered
+  for (int i = low; i < up; ++i) {
+    f[i] = 0.0;
+#pragma omp ordered simd
+    f[i] = 1.0;
+  }
 }
 
 // CHECK: define internal void [[CAP_FUNC]](i32* dereferenceable({{[0-9]+}}) %{{.+}}) #
diff --git a/test/OpenMP/parallel_for_simd_ast_print.cpp b/test/OpenMP/parallel_for_simd_ast_print.cpp
index e23c2cb..1b9415d 100644
--- a/test/OpenMP/parallel_for_simd_ast_print.cpp
+++ b/test/OpenMP/parallel_for_simd_ast_print.cpp
@@ -44,8 +44,8 @@ template<class T> struct S {
     }
     const T clen = 3;
 // CHECK: T clen = 3;
-    #pragma omp parallel for simd safelen(clen-1) simdlen(clen-1)
-// CHECK-NEXT: #pragma omp parallel for simd safelen(clen - 1) simdlen(clen - 1)
+    #pragma omp parallel for simd safelen(clen-1) simdlen(clen-1) ordered
+// CHECK-NEXT: #pragma omp parallel for simd safelen(clen - 1) simdlen(clen - 1) ordered
     for(T i = clen+2; i < 20; ++i) {
 // CHECK-NEXT: for (T i = clen + 2; i < 20; ++i) {
       v[i] = v[v-clen] + 1;
@@ -92,8 +92,8 @@ int main (int argc, char **argv) {
   int k1=0,k2=0;
   static int *a;
 // CHECK: static int *a;
-#pragma omp parallel for simd if(parallel :b)
-// CHECK-NEXT: #pragma omp parallel for simd if(parallel: b)
+#pragma omp parallel for simd if(parallel :b) ordered
+// CHECK-NEXT: #pragma omp parallel for simd if(parallel: b) ordered
   for (int i=0; i < 2; ++i)*a=2;
 // CHECK-NEXT: for (int i = 0; i < 2; ++i)
 // CHECK-NEXT: *a = 2;
diff --git a/test/OpenMP/parallel_for_simd_codegen.cpp b/test/OpenMP/parallel_for_simd_codegen.cpp
index 53f18d0..9a6ad2f 100644
--- a/test/OpenMP/parallel_for_simd_codegen.cpp
+++ b/test/OpenMP/parallel_for_simd_codegen.cpp
@@ -41,24 +41,24 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV:%[^,]+]],
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[SIMPLE_LOOP1_BODY:.+]], label %[[SIMPLE_LOOP1_END:[^,]+]]
   for (int i = 3; i < 32; i += 5) {
 // CHECK: [[SIMPLE_LOOP1_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV1_1:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV1_1:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK: [[CALC_I_1:%.+]] = mul nsw i32 [[IV1_1]], 5
 // CHECK-NEXT: [[CALC_I_2:%.+]] = add nsw i32 3, [[CALC_I_1]]
-// CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]
 // ... loop body ...
 // End of body: store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: store float [[RESULT:%.+]], float*
     a[i] = b[i] * c[i] * d[i];
-// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
-// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP1_ID]]
+// CHECK-NEXT: store i32 [[ADD1_2]], i32* [[OMP_IV]]
 // br label %{{.+}}, !llvm.loop !{{.+}}
   }
 // CHECK: [[SIMPLE_LOOP1_END]]
@@ -141,36 +141,36 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
 // CHECK: store i64 [[LB_VAL]], i64* [[OMP_IV3:%[^,]+]],
 
-// CHECK: [[IV3:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[IV3:%.+]] = load i64, i64* [[OMP_IV3]]
+// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP3:%.+]] = icmp ule i64 [[IV3]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP3]], label %[[SIMPLE_LOOP3_BODY:.+]], label %[[SIMPLE_LOOP3_END:[^,]+]]
   for (unsigned long long it = 2000; it >= 600; it-=400) {
 // CHECK: [[SIMPLE_LOOP3_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV3_0:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[IV3_0:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul i64 [[IV3_0]], 400
 // CHECK-NEXT: [[LC_IT_2:%.+]] = sub i64 2000, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64* {{.+}}
 //
 // Linear start and step are used to calculate current value of the linear variable.
-// CHECK: [[LINSTART:.+]] = load i32, i32* [[LIN_START]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[LINSTEP:.+]] = load i64, i64* [[LIN_STEP]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK-NOT: store i32 {{.+}}, i32* [[LIN_VAR]],{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[GLINSTART:.+]] = load double*, double** [[GLIN_START]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK-NEXT: [[IV3_1:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[LINSTART:.+]] = load i32, i32* [[LIN_START]]
+// CHECK: [[LINSTEP:.+]] = load i64, i64* [[LIN_STEP]]
+// CHECK-NOT: store i32 {{.+}}, i32* [[LIN_VAR]]
+// CHECK: [[GLINSTART:.+]] = load double*, double** [[GLIN_START]]
+// CHECK-NEXT: [[IV3_1:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[MUL:%.+]] = mul i64 [[IV3_1]], 1
 // CHECK: [[GEP:%.+]] = getelementptr{{.*}}[[GLINSTART]]
-// CHECK-NEXT: store double* [[GEP]], double** [[G_PTR_CUR:%[^,]+]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store double* [[GEP]], double** [[G_PTR_CUR:%[^,]+]]
     *g_ptr++ = 0.0;
-// CHECK: [[GEP_VAL:%.+]] = load double{{.*}}[[G_PTR_CUR]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: store double{{.*}}[[GEP_VAL]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK: [[GEP_VAL:%.+]] = load double{{.*}}[[G_PTR_CUR]]
+// CHECK: store double{{.*}}[[GEP_VAL]]
     a[it + lin]++;
 // CHECK: [[FLT_INC:%.+]] = fadd float
-// CHECK-NEXT: store float [[FLT_INC]],{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
-// CHECK: [[IV3_2:%.+]] = load i64, i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store float [[FLT_INC]],
+// CHECK: [[IV3_2:%.+]] = load i64, i64* [[OMP_IV3]]
 // CHECK-NEXT: [[ADD3_2:%.+]] = add i64 [[IV3_2]], 1
-// CHECK-NEXT: store i64 [[ADD3_2]], i64* [[OMP_IV3]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP3_ID]]
+// CHECK-NEXT: store i64 [[ADD3_2]], i64* [[OMP_IV3]]
   }
 // CHECK: [[SIMPLE_LOOP3_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -198,22 +198,22 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV4:%[^,]+]],
 
-// CHECK: [[IV4:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4:%.+]] = load i32, i32* [[OMP_IV4]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP4:%.+]] = icmp sle i32 [[IV4]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP4]], label %[[SIMPLE_LOOP4_BODY:.+]], label %[[SIMPLE_LOOP4_END:[^,]+]]
   for (short it = 6; it <= 20; it-=-4) {
 // CHECK: [[SIMPLE_LOOP4_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV4_0:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4_0:%.+]] = load i32, i32* [[OMP_IV4]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i32 [[IV4_0]], 4
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i32 6, [[LC_IT_1]]
 // CHECK-NEXT: [[LC_IT_3:%.+]] = trunc i32 [[LC_IT_2]] to i16
-// CHECK-NEXT: store i16 [[LC_IT_3]], i16* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK-NEXT: store i16 [[LC_IT_3]], i16*
 
-// CHECK: [[IV4_2:%.+]] = load i32, i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK: [[IV4_2:%.+]] = load i32, i32* [[OMP_IV4]]
 // CHECK-NEXT: [[ADD4_2:%.+]] = add nsw i32 [[IV4_2]], 1
-// CHECK-NEXT: store i32 [[ADD4_2]], i32* [[OMP_IV4]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP4_ID]]
+// CHECK-NEXT: store i32 [[ADD4_2]], i32* [[OMP_IV4]]
   }
 // CHECK: [[SIMPLE_LOOP4_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -234,22 +234,22 @@ void simple(float *a, float *b, float *c, float *d) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[OMP_IV5:%[^,]+]],
 
-// CHECK: [[IV5:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5:%.+]] = load i32, i32* [[OMP_IV5]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP5:%.+]] = icmp sle i32 [[IV5]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP5]], label %[[SIMPLE_LOOP5_BODY:.+]], label %[[SIMPLE_LOOP5_END:[^,]+]]
   for (unsigned char it = 'z'; it >= 'a'; it+=-1) {
 // CHECK: [[SIMPLE_LOOP5_BODY]]
 // Start of body: calculate it from IV:
-// CHECK: [[IV5_0:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5_0:%.+]] = load i32, i32* [[OMP_IV5]]
 // CHECK-NEXT: [[IV5_1:%.+]] = mul nsw i32 [[IV5_0]], 1
 // CHECK-NEXT: [[LC_IT_1:%.+]] = sub nsw i32 122, [[IV5_1]]
 // CHECK-NEXT: [[LC_IT_2:%.+]] = trunc i32 [[LC_IT_1]] to i8
-// CHECK-NEXT: store i8 [[LC_IT_2]], i8* {{.+}}, !llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK-NEXT: store i8 [[LC_IT_2]], i8* {{.+}},
 
-// CHECK: [[IV5_2:%.+]] = load i32, i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK: [[IV5_2:%.+]] = load i32, i32* [[OMP_IV5]]
 // CHECK-NEXT: [[ADD5_2:%.+]] = add nsw i32 [[IV5_2]], 1
-// CHECK-NEXT: store i32 [[ADD5_2]], i32* [[OMP_IV5]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP5_ID]]
+// CHECK-NEXT: store i32 [[ADD5_2]], i32* [[OMP_IV5]]
   }
 // CHECK: [[SIMPLE_LOOP5_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -280,24 +280,24 @@ void simple(float *a, float *b, float *c, float *d) {
 
 // CHECK: br label %[[SIMD_LOOP7_COND:[^,]+]]
 // CHECK: [[SIMD_LOOP7_COND]]
-// CHECK-NEXT: [[IV7:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: [[IV7:%.+]] = load i64, i64* [[OMP_IV7]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP7:%.+]] = icmp sle i64 [[IV7]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP7]], label %[[SIMPLE_LOOP7_BODY:.+]], label %[[SIMPLE_LOOP7_END:[^,]+]]
   for (long long i = -10; i < 10; i += 3) {
 // CHECK: [[SIMPLE_LOOP7_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV7_0:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK: [[IV7_0:%.+]] = load i64, i64* [[OMP_IV7]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i64 [[IV7_0]], 3
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i64 -10, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
-// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],
+// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]
 // CHECK-NEXT: [[CONV:%.+]] = trunc i64 [[LC_VAL]] to i32
-// CHECK-NEXT: store i32 [[CONV]], i32* [[A_PRIV:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i32 [[CONV]], i32* [[A_PRIV:%[^,]+]],
     A = i;
-// CHECK: [[IV7_2:%.+]] = load i64, i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK: [[IV7_2:%.+]] = load i64, i64* [[OMP_IV7]]
 // CHECK-NEXT: [[ADD7_2:%.+]] = add nsw i64 [[IV7_2]], 1
-// CHECK-NEXT: store i64 [[ADD7_2]], i64* [[OMP_IV7]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP7_ID]]
+// CHECK-NEXT: store i64 [[ADD7_2]], i64* [[OMP_IV7]]
   }
 // CHECK: [[SIMPLE_LOOP7_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -330,23 +330,23 @@ void simple(float *a, float *b, float *c, float *d) {
 
 // CHECK: br label %[[SIMD_LOOP8_COND:[^,]+]]
 // CHECK: [[SIMD_LOOP8_COND]]
-// CHECK-NEXT: [[IV8:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: [[IV8:%.+]] = load i64, i64* [[OMP_IV8]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP8:%.+]] = icmp sle i64 [[IV8]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP8]], label %[[SIMPLE_LOOP8_BODY:.+]], label %[[SIMPLE_LOOP8_END:[^,]+]]
   for (long long i = -10; i < 10; i += 3) {
 // CHECK: [[SIMPLE_LOOP8_BODY]]
 // Start of body: calculate i from IV:
-// CHECK: [[IV8_0:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK: [[IV8_0:%.+]] = load i64, i64* [[OMP_IV8]]
 // CHECK-NEXT: [[LC_IT_1:%.+]] = mul nsw i64 [[IV8_0]], 3
 // CHECK-NEXT: [[LC_IT_2:%.+]] = add nsw i64 -10, [[LC_IT_1]]
-// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
-// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
-// CHECK: store i32 %{{.+}}, i32* [[R_PRIV]],{{.+}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: store i64 [[LC_IT_2]], i64* [[LC:%[^,]+]],
+// CHECK-NEXT: [[LC_VAL:%.+]] = load i64, i64* [[LC]]
+// CHECK: store i32 %{{.+}}, i32* [[R_PRIV]],
     R *= i;
-// CHECK: [[IV8_2:%.+]] = load i64, i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK: [[IV8_2:%.+]] = load i64, i64* [[OMP_IV8]]
 // CHECK-NEXT: [[ADD8_2:%.+]] = add nsw i64 [[IV8_2]], 1
-// CHECK-NEXT: store i64 [[ADD8_2]], i64* [[OMP_IV8]]{{.*}}!llvm.mem.parallel_loop_access ![[SIMPLE_LOOP8_ID]]
+// CHECK-NEXT: store i64 [[ADD8_2]], i64* [[OMP_IV8]]
   }
 // CHECK: [[SIMPLE_LOOP8_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
@@ -438,14 +438,14 @@ void iter_simple(IterDouble ia, IterDouble ib, IterDouble ic) {
 // CHECK: [[LB_VAL:%.+]] = load i32, i32* [[LB]],
 // CHECK: store i32 [[LB_VAL]], i32* [[IT_OMP_IV:%[^,]+]],
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}} !llvm.mem.parallel_loop_access ![[ITER_LOOP_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[IT_OMP_IV]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[IT_BODY:[^,]+]], label %[[IT_END:[^,]+]]
   for (IterDouble i = ia; i < ib; ++i) {
 // CHECK: [[IT_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i32, i32* [[IT_OMP_IV]]
 // Call of operator+ (i, IV).
 // CHECK: {{%.+}} = invoke {{.+}} @{{.*}}IterDouble{{.*}}
 // ... loop body ...
@@ -453,12 +453,12 @@ void iter_simple(IterDouble ia, IterDouble ib, IterDouble ic) {
 // Float multiply and save result.
 // CHECK: [[MULR:%.+]] = fmul double {{%.+}}, 5.000000e-01
 // CHECK-NEXT: invoke {{.+}} @{{.*}}IterDouble{{.*}}
-// CHECK: store double [[MULR:%.+]], double* [[RESULT_ADDR:%.+]], !llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: store double [[MULR:%.+]], double* [[RESULT_ADDR:%.+]]
    ++ic;
 //
-// CHECK: [[IV2:%.+]] = load i32, i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i32, i32* [[IT_OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add nsw i32 [[IV2]], 1
-// CHECK-NEXT: store i32 [[ADD2]], i32* [[IT_OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[ITER_LOOP_ID]]
+// CHECK-NEXT: store i32 [[ADD2]], i32* [[IT_OMP_IV]]
 // br label %{{.*}}, !llvm.loop ![[ITER_LOOP_ID]]
   }
 // CHECK: [[IT_END]]
@@ -490,8 +490,8 @@ void collapsed(float *a, float *b, float *c, float *d) {
 //
   #pragma omp parallel for simd collapse(4)
 
-// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i32, i32* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i32, i32* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp ule i32 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[COLL1_BODY:[^,]+]], label %[[COLL1_END:[^,]+]]
   for (i = 1; i < 3; i++) // 2 iterations
@@ -501,25 +501,25 @@ void collapsed(float *a, float *b, float *c, float *d) {
         {
 // CHECK: [[COLL1_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i32, i32* [[OMP_IV]]
 // Calculation of the loop counters values.
 // CHECK: [[CALC_I_1:%.+]] = udiv i32 [[IV1]], 60
 // CHECK-NEXT: [[CALC_I_1_MUL1:%.+]] = mul i32 [[CALC_I_1]], 1
 // CHECK-NEXT: [[CALC_I_2:%.+]] = add i32 1, [[CALC_I_1_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_I_2]], i32* [[LC_I:.+]]
-// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_J_1:%.+]] = udiv i32 [[IV1_2]], 20
 // CHECK-NEXT: [[CALC_J_2:%.+]] = urem i32 [[CALC_J_1]], 3
 // CHECK-NEXT: [[CALC_J_2_MUL1:%.+]] = mul i32 [[CALC_J_2]], 1
 // CHECK-NEXT: [[CALC_J_3:%.+]] = add i32 2, [[CALC_J_2_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_J_3]], i32* [[LC_J:.+]]
-// CHECK: [[IV1_3:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_3:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_K_1:%.+]] = udiv i32 [[IV1_3]], 5
 // CHECK-NEXT: [[CALC_K_2:%.+]] = urem i32 [[CALC_K_1]], 4
 // CHECK-NEXT: [[CALC_K_2_MUL1:%.+]] = mul i32 [[CALC_K_2]], 1
 // CHECK-NEXT: [[CALC_K_3:%.+]] = add i32 3, [[CALC_K_2_MUL1]]
 // CHECK-NEXT: store i32 [[CALC_K_3]], i32* [[LC_K:.+]]
-// CHECK: [[IV1_4:%.+]] = load i32, i32* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV1_4:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[CALC_L_1:%.+]] = urem i32 [[IV1_4]], 5
 // CHECK-NEXT: [[CALC_L_1_MUL1:%.+]] = mul i32 [[CALC_L_1]], 1
 // CHECK-NEXT: [[CALC_L_2:%.+]] = add i32 4, [[CALC_L_1_MUL1]]
@@ -527,12 +527,12 @@ void collapsed(float *a, float *b, float *c, float *d) {
 // CHECK-NEXT: store i16 [[CALC_L_3]], i16* [[LC_L:.+]]
 // ... loop body ...
 // End of body: store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]{{.+}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]
     float res = b[j] * c[k];
     a[i] = res * d[l];
-// CHECK: [[IV2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i32, i32* [[OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add i32 [[IV2]], 1
-// CHECK-NEXT: store i32 [[ADD2]], i32* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[COLL1_LOOP_ID]]
+// CHECK-NEXT: store i32 [[ADD2]], i32* [[OMP_IV]]
 // br label %{{[^,]+}}, !llvm.loop ![[COLL1_LOOP_ID]]
 // CHECK: [[COLL1_END]]
   }
@@ -577,8 +577,8 @@ void widened(float *a, float *b, float *c, float *d) {
 //
   #pragma omp parallel for simd collapse(2) private(globalfloat, localint)
 
-// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID:[0-9]+]]
-// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV:%.+]] = load i64, i64* [[OMP_IV]]
+// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP:%.+]] = icmp sle i64 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP]], label %[[WIDE1_BODY:[^,]+]], label %[[WIDE1_END:[^,]+]]
   for (i = 1; i < 3; i++) // 2 iterations
@@ -586,10 +586,10 @@ void widened(float *a, float *b, float *c, float *d) {
   {
 // CHECK: [[WIDE1_BODY]]
 // Start of body: calculate i from index:
-// CHECK: [[IV1:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV1:%.+]] = load i64, i64* [[OMP_IV]]
 // Calculation of the loop counters values...
 // CHECK: store i32 {{[^,]+}}, i32* [[LC_I:.+]]
-// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]
 // CHECK: store i16 {{[^,]+}}, i16* [[LC_J:.+]]
 // ... loop body ...
 //
@@ -598,14 +598,14 @@ void widened(float *a, float *b, float *c, float *d) {
     globalfloat = (float)j/i;
     float res = b[j] * c[j];
 // Store into a[i]:
-// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: store float [[RESULT:%.+]], float* [[RESULT_ADDR:%.+]]
     a[i] = res * d[i];
 // Then there's a store into private var localint:
-// CHECK: store i32 {{.+}}, i32* [[LOCALINT:%[^,]+]]{{.+}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: store i32 {{.+}}, i32* [[LOCALINT:%[^,]+]]
     localint = (int)j;
-// CHECK: [[IV2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK: [[IV2:%.+]] = load i64, i64* [[OMP_IV]]
 // CHECK-NEXT: [[ADD2:%.+]] = add nsw i64 [[IV2]], 1
-// CHECK-NEXT: store i64 [[ADD2]], i64* [[OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[WIDE1_LOOP_ID]]
+// CHECK-NEXT: store i64 [[ADD2]], i64* [[OMP_IV]]
 //
 // br label %{{[^,]+}}, !llvm.loop ![[WIDE1_LOOP_ID]]
 // CHECK: [[WIDE1_END]]
@@ -636,27 +636,27 @@ void widened(float *a, float *b, float *c, float *d) {
 // CHECK: store i64 [[LB_VAL]], i64* [[T1_OMP_IV:%[^,]+]],
 
 // ...
-// CHECK: [[IV:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID:[0-9]+]]
-// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV:%.+]] = load i64, i64* [[T1_OMP_IV]]
+// CHECK-NEXT: [[UB_VAL:%.+]] = load i64, i64* [[UB]]
 // CHECK-NEXT: [[CMP1:%.+]] = icmp sle i64 [[IV]], [[UB_VAL]]
 // CHECK-NEXT: br i1 [[CMP1]], label %[[T1_BODY:.+]], label %[[T1_END:[^,]+]]
 // CHECK: [[T1_BODY]]
 // Loop counters i and j updates:
-// CHECK: [[IV1:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV1:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[I_1:%.+]] = sdiv i64 [[IV1]], 4
 // CHECK-NEXT: [[I_1_MUL1:%.+]] = mul nsw i64 [[I_1]], 1
 // CHECK-NEXT: [[I_1_ADD0:%.+]] = add nsw i64 0, [[I_1_MUL1]]
 // CHECK-NEXT: [[I_2:%.+]] = trunc i64 [[I_1_ADD0]] to i32
-// CHECK-NEXT: store i32 [[I_2]], i32* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
-// CHECK: [[IV2:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i32 [[I_2]], i32*
+// CHECK: [[IV2:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[J_1:%.+]] = srem i64 [[IV2]], 4
 // CHECK-NEXT: [[J_2:%.+]] = mul nsw i64 [[J_1]], 2
 // CHECK-NEXT: [[J_2_ADD0:%.+]] = add nsw i64 0, [[J_2]]
-// CHECK-NEXT: store i64 [[J_2_ADD0]], i64* {{%.+}}{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i64 [[J_2_ADD0]], i64*
 // simd.for.inc:
-// CHECK: [[IV3:%.+]] = load i64, i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK: [[IV3:%.+]] = load i64, i64* [[T1_OMP_IV]]
 // CHECK-NEXT: [[INC:%.+]] = add nsw i64 [[IV3]], 1
-// CHECK-NEXT: store i64 [[INC]], i64* [[T1_OMP_IV]]{{.*}}!llvm.mem.parallel_loop_access ![[T1_ID]]
+// CHECK-NEXT: store i64 [[INC]], i64*
 // CHECK-NEXT: br label {{%.+}}
 // CHECK: [[T1_END]]
 // CHECK: call void @__kmpc_for_static_fini(%ident_t* {{.+}}, i32 %{{.+}})
diff --git a/test/OpenMP/parallel_for_simd_loop_messages.cpp b/test/OpenMP/parallel_for_simd_loop_messages.cpp
index f4929d9..e5fd8c0 100644
--- a/test/OpenMP/parallel_for_simd_loop_messages.cpp
+++ b/test/OpenMP/parallel_for_simd_loop_messages.cpp
@@ -628,10 +628,16 @@ void test_loop_firstprivate_lastprivate() {
 }
 
 void test_ordered() {
-// expected-error@+1 2 {{unexpected OpenMP clause 'ordered' in directive '#pragma omp parallel for simd'}}
 #pragma omp parallel for simd ordered ordered // expected-error {{directive '#pragma omp parallel for simd' cannot contain more than one 'ordered' clause}}
   for (int i = 0; i < 16; ++i)
     ;
+#pragma omp parallel for simd ordered
+  for (int i = 0; i < 16; ++i)
+    ;
+//expected-error@+1 {{'ordered' clause with a parameter can not be specified in '#pragma omp parallel for simd' directive}}
+#pragma omp parallel for simd ordered(1)
+  for (int i = 0; i < 16; ++i)
+    ;
 }
 
 void test_nowait() {
diff --git a/test/OpenMP/parallel_for_simd_messages.cpp b/test/OpenMP/parallel_for_simd_messages.cpp
index fe14883..18f25fa 100644
--- a/test/OpenMP/parallel_for_simd_messages.cpp
+++ b/test/OpenMP/parallel_for_simd_messages.cpp
@@ -79,9 +79,15 @@ L1:
 }
 
 void test_ordered() {
-// expected-error@+1 2 {{unexpected OpenMP clause 'ordered' in directive '#pragma omp parallel for simd'}}
 #pragma omp parallel for simd ordered ordered // expected-error {{directive '#pragma omp parallel for simd' cannot contain more than one 'ordered' clause}}
   for (int i = 0; i < 16; ++i)
     ;
+#pragma omp parallel for simd ordered
+  for (int i = 0; i < 16; ++i)
+    ;
+// expected-error@+1 {{'ordered' clause with a parameter can not be specified in '#pragma omp parallel for simd' directive}}
+#pragma omp parallel for simd ordered(1)
+  for (int i = 0; i < 16; ++i)
+    ;
 }
 
diff --git a/test/OpenMP/schedule_codegen.cpp b/test/OpenMP/schedule_codegen.cpp
new file mode 100644
index 0000000..bd5ec86
--- /dev/null
+++ b/test/OpenMP/schedule_codegen.cpp
@@ -0,0 +1,194 @@
+// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm -fexceptions -fcxx-exceptions -o - %s | FileCheck %s
+
+int main() {
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for simd
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for schedule(static)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for simd schedule(static)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for schedule(static, 2)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for simd schedule(static, 2)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(auto)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(auto)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(runtime)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(runtime)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for schedule(monotonic: static)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for simd schedule(monotonic: static)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for schedule(monotonic: static, 2)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_for_static_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_for_static_fini
+#pragma omp for simd schedule(monotonic: static, 2)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(monotonic: auto)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(monotonic: auto)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(monotonic: runtime)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(monotonic: runtime)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(monotonic: guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(monotonic: guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(monotonic: dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(monotonic: dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(nonmonotonic: guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(nonmonotonic: guided)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for schedule(nonmonotonic: dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(nonmonotonic: dynamic)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(static) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for simd schedule(static) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(static, 2) ordered(1)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for simd schedule(static, 2) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(auto) ordered(1)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+#pragma omp for simd schedule(auto) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(runtime) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for simd schedule(runtime) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(guided) ordered(1)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for simd schedule(guided) ordered
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for schedule(dynamic) ordered(1)
+  for(int i = 0; i < 10; ++i);
+// CHECK: @__kmpc_dispatch_init
+// CHECK-NOT: !llvm.mem.parallel_loop_access
+// CHECK: @__kmpc_dispatch_next
+#pragma omp for simd schedule(dynamic)
+  for(int i = 0; i < 10; ++i);
+  return 0;
+}
diff --git a/test/OpenMP/target_codegen.cpp b/test/OpenMP/target_codegen.cpp
index bcefa24..c2e08d6 100644
--- a/test/OpenMP/target_codegen.cpp
+++ b/test/OpenMP/target_codegen.cpp
@@ -1,15 +1,32 @@
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
-// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// Test host codegen.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix TCHECK --check-prefix TCHECK-32
+
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
 
 // CHECK-DAG: [[TT:%.+]] = type { i64, i8 }
 // CHECK-DAG: [[S1:%.+]] = type { double }
+// CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]] }
+// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* }
+// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* }
+
+// TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}} }
 
 // We have 8 target regions, but only 7 that actually will generate offloading
 // code, only 6 will have mapped arguments, and only 4 have all-constant map
@@ -33,6 +50,27 @@
 // CHECK-DAG: @{{.*}} = private constant i8 0
 // CHECK-DAG: @{{.*}} = private constant i8 0
 
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK: @{{.+}} = constant [[ENTTY]]
+// TCHECK-NOT: @{{.+}} = constant [[ENTTY]]
+
+// Check if offloading descriptor is created.
+// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]]
+// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]]
+// CHECK: [[DEVBEGIN:@.+]] = external constant i8
+// CHECK: [[DEVEND:@.+]] = external constant i8
+// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }]
+// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }
+
+// Check target registration is registered as a Ctor.
+// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* bitcast (void (i8*)* [[REGFN:@.+]] to void ()*), i8* null }]
+
+
 template<typename tx, typename ty>
 struct TT{
   tx X;
diff --git a/test/OpenMP/target_codegen_global_capture.cpp b/test/OpenMP/target_codegen_global_capture.cpp
index 29469cd..211a3cc 100644
--- a/test/OpenMP/target_codegen_global_capture.cpp
+++ b/test/OpenMP/target_codegen_global_capture.cpp
@@ -1,9 +1,9 @@
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
-// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
diff --git a/test/OpenMP/target_codegen_registration.cpp b/test/OpenMP/target_codegen_registration.cpp
new file mode 100644
index 0000000..0c9bba6
--- /dev/null
+++ b/test/OpenMP/target_codegen_registration.cpp
@@ -0,0 +1,437 @@
+// Test host codegen.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -std=c++11 -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -std=c++11 -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
+
+// Check that no target code is emmitted if no omptests flag was provided.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK-NTARGET
+
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+// CHECK-DAG: [[SA:%.+]] = type { [4 x i32] }
+// CHECK-DAG: [[SB:%.+]] = type { [8 x i32] }
+// CHECK-DAG: [[SC:%.+]] = type { [16 x i32] }
+// CHECK-DAG: [[SD:%.+]] = type { [32 x i32] }
+// CHECK-DAG: [[SE:%.+]] = type { [64 x i32] }
+// CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] }
+// CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] }
+// CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]] }
+// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* }
+// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* }
+
+// TCHECK:    [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]] }
+
+// CHECK-DAG: [[A1:@.+]] = internal global [[SA]]
+// CHECK-DAG: [[A2:@.+]] = global [[SA]]
+// CHECK-DAG: [[B1:@.+]] = global [[SB]]
+// CHECK-DAG: [[B2:@.+]] = global [[SB]]
+// CHECK-DAG: [[C1:@.+]] = internal global [[SC]]
+// CHECK-DAG: [[D1:@.+]] = global [[SD]]
+// CHECK-DAG: [[E1:@.+]] = global [[SE]]
+// CHECK-DAG: [[T1:@.+]] = global [[ST1]]
+// CHECK-DAG: [[T2:@.+]] = global [[ST2]]
+
+// CHECK-NTARGET-DAG: [[SA:%.+]] = type { [4 x i32] }
+// CHECK-NTARGET-DAG: [[SB:%.+]] = type { [8 x i32] }
+// CHECK-NTARGET-DAG: [[SC:%.+]] = type { [16 x i32] }
+// CHECK-NTARGET-DAG: [[SD:%.+]] = type { [32 x i32] }
+// CHECK-NTARGET-DAG: [[SE:%.+]] = type { [64 x i32] }
+// CHECK-NTARGET-DAG: [[ST1:%.+]] = type { [228 x i32] }
+// CHECK-NTARGET-DAG: [[ST2:%.+]] = type { [1128 x i32] }
+// CHECK-NTARGET-NOT: type { i8*,
+// CHECK-NTARGET-NOT: type { i32,
+
+// We have 7 target regions
+
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// TCHECK-NOT: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+// CHECK-DAG: {{@.+}} = private constant i8 0
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i[[SZ]]] [i[[SZ]] 4]
+// CHECK-DAG: {{@.+}} = private unnamed_addr constant [1 x i32] [i32 128]
+
+// CHECK-NTARGET-NOT: private constant i8 0
+// CHECK-NTARGET-NOT: private unnamed_addr constant [1 x i
+
+// CHECK-DAG: [[NAMEPTR1:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME1:\.omp_offloading\.[0-9a-f]+\.[0-9a-f]+\._Z.+\.l[0-9]+\.c[0-9]+]]\00"
+// CHECK-DAG: [[ENTRY1:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR1]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR2:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME2:.+]]\00"
+// CHECK-DAG: [[ENTRY2:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR2]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR3:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME3:.+]]\00"
+// CHECK-DAG: [[ENTRY3:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR3]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR4:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME4:.+]]\00"
+// CHECK-DAG: [[ENTRY4:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR4]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR5:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME5:.+]]\00"
+// CHECK-DAG: [[ENTRY5:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR5]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR6:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME6:.+]]\00"
+// CHECK-DAG: [[ENTRY6:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR6]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR7:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME7:.+]]\00"
+// CHECK-DAG: [[ENTRY7:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR7]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR8:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME8:.+]]\00"
+// CHECK-DAG: [[ENTRY8:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR8]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR9:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME9:.+]]\00"
+// CHECK-DAG: [[ENTRY9:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR9]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR10:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME10:.+]]\00"
+// CHECK-DAG: [[ENTRY10:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR10]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR11:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME11:.+]]\00"
+// CHECK-DAG: [[ENTRY11:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR11]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// CHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00"
+// CHECK-DAG: [[ENTRY12:@.+]] = constant [[ENTTY]] { i8* @{{.*}}, i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+
+// TCHECK-DAG: [[NAMEPTR1:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME1:\.omp_offloading\.[0-9a-f]+\.[0-9a-f]+\._Z.+\.l[0-9]+\.c[0-9]+]]\00"
+// TCHECK-DAG: [[ENTRY1:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR1]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR2:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME2:.+]]\00"
+// TCHECK-DAG: [[ENTRY2:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR2]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR3:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME3:.+]]\00"
+// TCHECK-DAG: [[ENTRY3:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR3]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR4:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME4:.+]]\00"
+// TCHECK-DAG: [[ENTRY4:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR4]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR5:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME5:.+]]\00"
+// TCHECK-DAG: [[ENTRY5:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR5]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR6:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME6:.+]]\00"
+// TCHECK-DAG: [[ENTRY6:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR6]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR7:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME7:.+]]\00"
+// TCHECK-DAG: [[ENTRY7:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR7]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR8:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME8:.+]]\00"
+// TCHECK-DAG: [[ENTRY8:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR8]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR9:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME9:.+]]\00"
+// TCHECK-DAG: [[ENTRY9:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR9]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR10:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME10:.+]]\00"
+// TCHECK-DAG: [[ENTRY10:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR10]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR11:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME11:.+]]\00"
+// TCHECK-DAG: [[ENTRY11:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR11]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+// TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00"
+// TCHECK-DAG: [[ENTRY12:@.+]] = constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0 }, section ".omp_offloading.entries", align 1
+
+// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]]
+// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]]
+// CHECK: [[DEVBEGIN:@.+]] = external constant i8
+// CHECK: [[DEVEND:@.+]] = external constant i8
+// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }]
+// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }
+
+// We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function.
+// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [
+// CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null },
+// CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null },
+// CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null },
+// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* bitcast (void (i8*)* [[REGFN:@.+]] to void ()*), i8* null }]
+
+// CHECK-NTARGET: @llvm.global_ctors = appending global [3   x { i32, void ()*, i8* }] [
+
+extern int *R;
+
+struct SA {
+  int arr[4];
+  void foo() {
+    int a = *R;
+    a += 1;
+    *R = a;
+  }
+  SA() {
+    int a = *R;
+    a += 2;
+    *R = a;
+  }
+  ~SA() {
+    int a = *R;
+    a += 3;
+    *R = a;
+  }
+};
+
+struct SB {
+  int arr[8];
+  void foo() {
+    int a = *R;
+    #pragma omp target
+    a += 4;
+    *R = a;
+  }
+  SB() {
+    int a = *R;
+    a += 5;
+    *R = a;
+  }
+  ~SB() {
+    int a = *R;
+    a += 6;
+    *R = a;
+  }
+};
+
+struct SC {
+  int arr[16];
+  void foo() {
+    int a = *R;
+    a += 7;
+    *R = a;
+  }
+  SC() {
+    int a = *R;
+    #pragma omp target
+    a += 8;
+    *R = a;
+  }
+  ~SC() {
+    int a = *R;
+    a += 9;
+    *R = a;
+  }
+};
+
+struct SD {
+  int arr[32];
+  void foo() {
+    int a = *R;
+    a += 10;
+    *R = a;
+  }
+  SD() {
+    int a = *R;
+    a += 11;
+    *R = a;
+  }
+  ~SD() {
+    int a = *R;
+    #pragma omp target
+    a += 12;
+    *R = a;
+  }
+};
+
+struct SE {
+  int arr[64];
+  void foo() {
+    int a = *R;
+    #pragma omp target if(0)
+    a += 13;
+    *R = a;
+  }
+  SE() {
+    int a = *R;
+    #pragma omp target
+    a += 14;
+    *R = a;
+  }
+  ~SE() {
+    int a = *R;
+    #pragma omp target
+    a += 15;
+    *R = a;
+  }
+};
+
+template <int x>
+struct ST {
+  int arr[128 + x];
+  void foo() {
+    int a = *R;
+    #pragma omp target
+    a += 16 + x;
+    *R = a;
+  }
+  ST() {
+    int a = *R;
+    #pragma omp target
+    a += 17 + x;
+    *R = a;
+  }
+  ~ST() {
+    int a = *R;
+    #pragma omp target
+    a += 18 + x;
+    *R = a;
+  }
+};
+
+// We have to make sure we us all the target regions:
+//CHECK-DAG: define internal void @[[NAME1]](
+//CHECK-DAG: call void @[[NAME1]](
+//CHECK-DAG: define internal void @[[NAME2]](
+//CHECK-DAG: call void @[[NAME2]](
+//CHECK-DAG: define internal void @[[NAME3]](
+//CHECK-DAG: call void @[[NAME3]](
+//CHECK-DAG: define internal void @[[NAME4]](
+//CHECK-DAG: call void @[[NAME4]](
+//CHECK-DAG: define internal void @[[NAME5]](
+//CHECK-DAG: call void @[[NAME5]](
+//CHECK-DAG: define internal void @[[NAME6]](
+//CHECK-DAG: call void @[[NAME6]](
+//CHECK-DAG: define internal void @[[NAME7]](
+//CHECK-DAG: call void @[[NAME7]](
+//CHECK-DAG: define internal void @[[NAME8]](
+//CHECK-DAG: call void @[[NAME8]](
+//CHECK-DAG: define internal void @[[NAME9]](
+//CHECK-DAG: call void @[[NAME9]](
+//CHECK-DAG: define internal void @[[NAME10]](
+//CHECK-DAG: call void @[[NAME10]](
+//CHECK-DAG: define internal void @[[NAME11]](
+//CHECK-DAG: call void @[[NAME11]](
+//CHECK-DAG: define internal void @[[NAME12]](
+//CHECK-DAG: call void @[[NAME12]](
+
+//TCHECK-DAG: define void @[[NAME1]](
+//TCHECK-DAG: define void @[[NAME2]](
+//TCHECK-DAG: define void @[[NAME3]](
+//TCHECK-DAG: define void @[[NAME4]](
+//TCHECK-DAG: define void @[[NAME5]](
+//TCHECK-DAG: define void @[[NAME6]](
+//TCHECK-DAG: define void @[[NAME7]](
+//TCHECK-DAG: define void @[[NAME8]](
+//TCHECK-DAG: define void @[[NAME9]](
+//TCHECK-DAG: define void @[[NAME10]](
+//TCHECK-DAG: define void @[[NAME11]](
+//TCHECK-DAG: define void @[[NAME12]](
+
+// CHECK-NTARGET-NOT: __tgt_target
+// CHECK-NTARGET-NOT: __tgt_register_lib
+// CHECK-NTARGET-NOT: __tgt_unregister_lib
+
+// TCHECK-NOT: __tgt_target
+// TCHECK-NOT: __tgt_register_lib
+// TCHECK-NOT: __tgt_unregister_lib
+
+// We have 2 initializers with priority 500
+//CHECK: define internal void [[P500]](
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK-NOT: call void @{{.+}}()
+//CHECK:     ret void
+
+// We have 1 initializers with priority 501
+//CHECK: define internal void [[P501]](
+//CHECK:     call void @{{.+}}()
+//CHECK-NOT: call void @{{.+}}()
+//CHECK:     ret void
+
+// We have 6 initializers with default priority
+//CHECK: define internal void [[PMAX]](
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK:     call void @{{.+}}()
+//CHECK-NOT: call void @{{.+}}()
+//CHECK:     ret void
+
+// Check registration and unregistration
+
+//CHECK:     define internal void [[UNREGFN:@.+]](i8*)
+//CHECK:     call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]])
+//CHECK:     ret void
+//CHECK:     declare i32 @__tgt_unregister_lib([[DSCTY]]*)
+
+//CHECK:     define internal void [[REGFN]](i8*)
+//CHECK:     call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]])
+//CHECK:     call i32 @__cxa_atexit(void (i8*)* [[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*),
+//CHECK:     ret void
+//CHECK:     declare i32 @__tgt_register_lib([[DSCTY]]*)
+
+static __attribute__((init_priority(500))) SA a1;
+SA a2;
+SB __attribute__((init_priority(500))) b1;
+SB __attribute__((init_priority(501))) b2;
+static SC c1;
+SD d1;
+SE e1;
+ST<100> t1;
+ST<1000> t2;
+
+
+int bar(int a){
+  int r = a;
+
+  a1.foo();
+  a2.foo();
+  b1.foo();
+  b2.foo();
+  c1.foo();
+  d1.foo();
+  e1.foo();
+  t1.foo();
+  t2.foo();
+
+  #pragma omp target
+  ++r;
+
+  return r + *R;
+}
+
+// Check metadata is properly generated:
+// CHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
+// CHECK-DAG = !{i32 0, i32 [[DEVID:[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 160, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SDD2Ev", i32 210, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SEC2Ev", i32 226, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SED2Ev", i32 232, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EE3fooEv", i32 243, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EEC2Ev", i32 249, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_Z3bari", i32 352, i32 11, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EED2Ev", i32 255, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EEC2Ev", i32 249, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EED2Ev", i32 255, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EE3fooEv", i32 243, i32 13, i32 {{[0-9]}}+}
+// CHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SCC2Ev", i32 185, i32 13, i32 {{[0-9]}}+}
+
+// TCHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID:[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 160, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SDD2Ev", i32 210, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SEC2Ev", i32 226, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SED2Ev", i32 232, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EE3fooEv", i32 243, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EEC2Ev", i32 249, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_Z3bari", i32 352, i32 11, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EED2Ev", i32 255, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EEC2Ev", i32 249, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi1000EED2Ev", i32 255, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2STILi100EE3fooEv", i32 243, i32 13, i32 {{[0-9]}}+}
+// TCHECK-DAG = !{i32 0, i32 [[DEVID]], i32 [[FILEID]] !"_ZN2SCC2Ev", i32 185, i32 13, i32 {{[0-9]}}+}
+
+#endif
diff --git a/test/OpenMP/target_codegen_registration_naming.cpp b/test/OpenMP/target_codegen_registration_naming.cpp
new file mode 100644
index 0000000..6ab9bf1
--- /dev/null
+++ b/test/OpenMP/target_codegen_registration_naming.cpp
@@ -0,0 +1,66 @@
+// Test host codegen.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -omptargets=powerpc64le-ibm-linux-gnu -fopenmp-is-device -omp-host-ir-file-path %t-ppc-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-llvm %s -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s -check-prefix=TCHECK
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -emit-pch -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -o %t %s
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -omptargets=i386-pc-linux-gnu -fopenmp-is-device -omp-host-ir-file-path %t-x86-host.bc -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s -check-prefix=TCHECK
+
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+// CHECK: [[CA:%.+]] = type { i32* }
+
+// CHECK: define {{.*}}i32 @[[NNAME:.+]](i32 {{.*}}%{{.+}})
+int nested(int a){
+  // CHECK: call void @.omp_offloading.[[FILEID:[0-9a-f]+\.[0-9a-f]+]].[[NNAME]].l[[T1L:[0-9]+]].c[[T1C:[0-9]+]](
+  #pragma omp target
+    ++a;
+
+  // CHECK: call void @"[[LNAME:.+]]"([[CA]]*
+  auto F = [&](){
+    #pragma omp parallel
+    {
+      #pragma omp target
+      ++a;
+    }
+  };
+
+  F();
+
+  return a;
+}
+
+// CHECK: define {{.*}}void @.omp_offloading.[[FILEID]].[[NNAME]].l[[T1L]].c[[T1C]](
+// TCHECK: define {{.*}}void @.omp_offloading.[[FILEID:[0-9a-f]+\.[0-9a-f]+]].[[NNAME:.+]].l[[T1L:[0-9]+]].c[[T1C:[0-9]+]](
+
+// CHECK: define {{.*}}void @"[[LNAME]]"(
+// CHECK: call void {{.*}}@__kmpc_fork_call{{.+}}[[PNAME:@.+]] to
+
+// CHECK: define {{.*}}void [[PNAME]](
+// CHECK: call void @.omp_offloading.[[FILEID]].[[NNAME]].l[[T2L:[0-9]+]].c[[T2C:[0-9]+]](
+
+// CHECK: define {{.*}}void @.omp_offloading.[[FILEID]].[[NNAME]].l[[T2L]].c[[T2C]](
+// TCHECK: define {{.*}}void @.omp_offloading.[[FILEID]].[[NNAME:.+]].l[[T2L:[0-9]+]].c[[T2C:[0-9]+]](
+
+
+// Check metadata is properly generated:
+// CHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 {{[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T1L]], i32 [[T1C]], i32 {{[0-9]+}}}
+// CHECK-DAG: = !{i32 0, i32 {{[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T2L]], i32 [[T2C]], i32 {{[0-9]+}}}
+
+// TCHECK:     !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 {{[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T1L]], i32 [[T1C]], i32 {{[0-9]+}}}
+// TCHECK-DAG: = !{i32 0, i32 {{[0-9]+}}, i32 {{-?[0-9]+}}, !"[[NNAME]]", i32 [[T2L]], i32 [[T2C]], i32 {{[0-9]+}}}
+#endif
diff --git a/test/OpenMP/target_map_codegen.cpp b/test/OpenMP/target_map_codegen.cpp
index 2b24c82..942cc4c 100644
--- a/test/OpenMP/target_map_codegen.cpp
+++ b/test/OpenMP/target_map_codegen.cpp
@@ -7,12 +7,12 @@
 ///
 
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
-// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-64
-// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-32
-// RUN: %clang_cc1 -DCK1 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-32
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
+// RUN: %clang_cc1 -DCK1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-64
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-32
+// RUN: %clang_cc1 -DCK1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK1 --check-prefix CK1-32
 #ifdef CK1
 
 // CK1-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -52,12 +52,12 @@ void implicit_maps_integer (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
-// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-64
-// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-32
-// RUN: %clang_cc1 -DCK2 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-32
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
+// RUN: %clang_cc1 -DCK2 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-64
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-32
+// RUN: %clang_cc1 -DCK2 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK2 --check-prefix CK2-32
 #ifdef CK2
 
 // CK2-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -101,12 +101,12 @@ void implicit_maps_integer_reference (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK3 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-64
-// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-64
-// RUN: %clang_cc1 -DCK3 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-32
-// RUN: %clang_cc1 -DCK3 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-32
+// RUN: %clang_cc1 -DCK3 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK3 --check-prefix CK3-64
+// RUN: %clang_cc1 -DCK3 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-64
+// RUN: %clang_cc1 -DCK3 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-32
+// RUN: %clang_cc1 -DCK3 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK3 --check-prefix CK3-32
 #ifdef CK3
 
 // CK3-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -145,12 +145,12 @@ void implicit_maps_parameter (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK4 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-64
-// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-64
-// RUN: %clang_cc1 -DCK4 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-32
-// RUN: %clang_cc1 -DCK4 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-32
+// RUN: %clang_cc1 -DCK4 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK4 --check-prefix CK4-64
+// RUN: %clang_cc1 -DCK4 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-64
+// RUN: %clang_cc1 -DCK4 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-32
+// RUN: %clang_cc1 -DCK4 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK4 --check-prefix CK4-32
 #ifdef CK4
 
 // CK4-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -201,12 +201,12 @@ void implicit_maps_nested_integer (int a){
 // CK4: define internal void [[KERNELP2]](i32* {{[^,]+}}, i32* {{[^,]+}}, i32* {{[^,]+}})
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK5 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK5 --check-prefix CK5-64
-// RUN: %clang_cc1 -DCK5 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-64
-// RUN: %clang_cc1 -DCK5 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-32
-// RUN: %clang_cc1 -DCK5 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-32
+// RUN: %clang_cc1 -DCK5 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK5 --check-prefix CK5-64
+// RUN: %clang_cc1 -DCK5 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-64
+// RUN: %clang_cc1 -DCK5 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-32
+// RUN: %clang_cc1 -DCK5 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK5 --check-prefix CK5-32
 #ifdef CK5
 
 // CK5-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -252,12 +252,12 @@ void implicit_maps_nested_integer_and_enum (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK6 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK6 --check-prefix CK6-64
-// RUN: %clang_cc1 -DCK6 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-64
-// RUN: %clang_cc1 -DCK6 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-32
-// RUN: %clang_cc1 -DCK6 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-32
+// RUN: %clang_cc1 -DCK6 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK6 --check-prefix CK6-64
+// RUN: %clang_cc1 -DCK6 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-64
+// RUN: %clang_cc1 -DCK6 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-32
+// RUN: %clang_cc1 -DCK6 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK6 --check-prefix CK6-32
 #ifdef CK6
 // CK6-DAG: [[GBL:@Gi]] = global i32 0
 // CK6-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -298,12 +298,12 @@ void implicit_maps_host_global (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK7 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK7 --check-prefix CK7-64
-// RUN: %clang_cc1 -DCK7 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-64
-// RUN: %clang_cc1 -DCK7 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-32
-// RUN: %clang_cc1 -DCK7 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-32
+// RUN: %clang_cc1 -DCK7 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK7 --check-prefix CK7-64
+// RUN: %clang_cc1 -DCK7 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-64
+// RUN: %clang_cc1 -DCK7 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-32
+// RUN: %clang_cc1 -DCK7 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK7  --check-prefix CK7-32
 #ifdef CK7
 
 // For a 32-bit targets, the value doesn't fit the size of the pointer,
@@ -360,12 +360,12 @@ void implicit_maps_double (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK8 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK8
-// RUN: %clang_cc1 -DCK8 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK8
-// RUN: %clang_cc1 -DCK8 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK8
-// RUN: %clang_cc1 -DCK8 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK8
+// RUN: %clang_cc1 -DCK8 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK8
+// RUN: %clang_cc1 -DCK8 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK8
+// RUN: %clang_cc1 -DCK8 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK8
+// RUN: %clang_cc1 -DCK8 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK8
 #ifdef CK8
 
 // CK8-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -404,12 +404,12 @@ void implicit_maps_float (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK9 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK9
-// RUN: %clang_cc1 -DCK9 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK9
-// RUN: %clang_cc1 -DCK9 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK9
-// RUN: %clang_cc1 -DCK9 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK9
+// RUN: %clang_cc1 -DCK9 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK9
+// RUN: %clang_cc1 -DCK9 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK9
+// RUN: %clang_cc1 -DCK9 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK9
+// RUN: %clang_cc1 -DCK9 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK9
 #ifdef CK9
 
 // CK9-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 16]
@@ -445,12 +445,12 @@ void implicit_maps_array (int a){
 // CK9: {{.+}} = getelementptr inbounds [2 x double], [2 x double]* [[REF]], i[[sz]] 0, i[[sz]] 0
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK10 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK10
-// RUN: %clang_cc1 -DCK10 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK10
-// RUN: %clang_cc1 -DCK10 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK10
-// RUN: %clang_cc1 -DCK10 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK10
+// RUN: %clang_cc1 -DCK10 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK10
+// RUN: %clang_cc1 -DCK10 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK10
+// RUN: %clang_cc1 -DCK10 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK10
+// RUN: %clang_cc1 -DCK10 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK10
 #ifdef CK10
 
 // CK10-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} {{8|4}}]
@@ -487,12 +487,12 @@ void implicit_maps_pointer (){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK11 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK11
-// RUN: %clang_cc1 -DCK11 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK11
-// RUN: %clang_cc1 -DCK11 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK11
-// RUN: %clang_cc1 -DCK11 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK11
+// RUN: %clang_cc1 -DCK11 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK11
+// RUN: %clang_cc1 -DCK11 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK11
+// RUN: %clang_cc1 -DCK11 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK11
+// RUN: %clang_cc1 -DCK11 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK11
 #ifdef CK11
 
 // CK11-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 16]
@@ -527,12 +527,12 @@ void implicit_maps_double_complex (int a){
 // CK11: {{.+}} = getelementptr inbounds { double, double }, { double, double }* [[REF]], i32 0, i32 0
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK12 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK12 --check-prefix CK12-64
-// RUN: %clang_cc1 -DCK12 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-64
-// RUN: %clang_cc1 -DCK12 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-32
-// RUN: %clang_cc1 -DCK12 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-32
+// RUN: %clang_cc1 -DCK12 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK12 --check-prefix CK12-64
+// RUN: %clang_cc1 -DCK12 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-64
+// RUN: %clang_cc1 -DCK12 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-32
+// RUN: %clang_cc1 -DCK12 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK12 --check-prefix CK12-32
 #ifdef CK12
 
 // For a 32-bit targets, the value doesn't fit the size of the pointer,
@@ -588,12 +588,12 @@ void implicit_maps_float_complex (int a){
 // CK12-32: {{.+}} = getelementptr inbounds { float, float }, { float, float }* [[REF]], i32 0, i32 0
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK13 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK13
-// RUN: %clang_cc1 -DCK13 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK13
-// RUN: %clang_cc1 -DCK13 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK13
-// RUN: %clang_cc1 -DCK13 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK13
+// RUN: %clang_cc1 -DCK13 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK13
+// RUN: %clang_cc1 -DCK13 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK13
+// RUN: %clang_cc1 -DCK13 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK13
+// RUN: %clang_cc1 -DCK13 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK13
 #ifdef CK13
 
 // We don't have a constant map size for VLAs.
@@ -658,12 +658,12 @@ void implicit_maps_variable_length_array (int a){
 // CK13: {{.+}} = getelementptr inbounds double, double* [[REF]], i[[sz]] %{{.+}}
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK14 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK14 --check-prefix CK14-64
-// RUN: %clang_cc1 -DCK14 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-64
-// RUN: %clang_cc1 -DCK14 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-32
-// RUN: %clang_cc1 -DCK14 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-32
+// RUN: %clang_cc1 -DCK14 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK14 --check-prefix CK14-64
+// RUN: %clang_cc1 -DCK14 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-64
+// RUN: %clang_cc1 -DCK14 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-32
+// RUN: %clang_cc1 -DCK14 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK14 --check-prefix CK14-32
 #ifdef CK14
 
 // CK14-DAG: [[ST:%.+]] = type { i32, double }
@@ -732,12 +732,12 @@ void implicit_maps_class (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK15 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK15 --check-prefix CK15-64
-// RUN: %clang_cc1 -DCK15 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-64
-// RUN: %clang_cc1 -DCK15 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-32
-// RUN: %clang_cc1 -DCK15 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-32
+// RUN: %clang_cc1 -DCK15 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK15 --check-prefix CK15-64
+// RUN: %clang_cc1 -DCK15 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-64
+// RUN: %clang_cc1 -DCK15 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-32
+// RUN: %clang_cc1 -DCK15 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK15 --check-prefix CK15-32
 #ifdef CK15
 
 // CK15: [[ST:%.+]] = type { i32, double, i32* }
@@ -860,12 +860,12 @@ void implicit_maps_templated_class (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK16 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK16 --check-prefix CK16-64
-// RUN: %clang_cc1 -DCK16 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-64
-// RUN: %clang_cc1 -DCK16 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-32
-// RUN: %clang_cc1 -DCK16 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-32
+// RUN: %clang_cc1 -DCK16 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK16 --check-prefix CK16-64
+// RUN: %clang_cc1 -DCK16 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-64
+// RUN: %clang_cc1 -DCK16 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-32
+// RUN: %clang_cc1 -DCK16 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK16 --check-prefix CK16-32
 #ifdef CK16
 
 // CK16-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
@@ -913,12 +913,12 @@ void implicit_maps_templated_function (int a){
 
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK17 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK17
-// RUN: %clang_cc1 -DCK17 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK17
-// RUN: %clang_cc1 -DCK17 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK17
-// RUN: %clang_cc1 -DCK17 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK17
+// RUN: %clang_cc1 -DCK17 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK17
+// RUN: %clang_cc1 -DCK17 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK17
+// RUN: %clang_cc1 -DCK17 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK17
+// RUN: %clang_cc1 -DCK17 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK17
 #ifdef CK17
 
 // CK17-DAG: [[ST:%.+]] = type { i32, double }
@@ -961,12 +961,12 @@ void implicit_maps_struct (int a){
 // CK17: {{.+}} = getelementptr inbounds [[ST]], [[ST]]* [[REF]], i32 0, i32 0
 #endif
 ///==========================================================================///
-// RUN: %clang_cc1 -DCK18 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK18 --check-prefix CK18-64
-// RUN: %clang_cc1 -DCK18 -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-64
-// RUN: %clang_cc1 -DCK18 -verify -fopenmp -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-32
-// RUN: %clang_cc1 -DCK18 -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-32
+// RUN: %clang_cc1 -DCK18 -verify -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix CK18 --check-prefix CK18-64
+// RUN: %clang_cc1 -DCK18 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-64
+// RUN: %clang_cc1 -DCK18 -verify -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-32
+// RUN: %clang_cc1 -DCK18 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -omptargets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s  --check-prefix CK18 --check-prefix CK18-32
 #ifdef CK18
 
 // CK18-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
diff --git a/test/OpenMP/target_messages.cpp b/test/OpenMP/target_messages.cpp
index ebac51a..86a9183 100644
--- a/test/OpenMP/target_messages.cpp
+++ b/test/OpenMP/target_messages.cpp
@@ -1,4 +1,6 @@
 // RUN: %clang_cc1 -verify -fopenmp -std=c++11 -o - %s
+// RUN: not %clang_cc1 -fopenmp -std=c++11 -omptargets=aaa-bbb-ccc-ddd -o - %s 2>&1 | FileCheck %s
+// CHECK: error: OpenMP target is invalid: 'aaa-bbb-ccc-ddd'
 
 void foo() {
 }
author	dim <dim@FreeBSD.org>	2016-01-06 20:02:26 +0000
committer	dim <dim@FreeBSD.org>	2016-01-06 20:02:26 +0000
commit	fc74ff5a0792641885551a63d9ddf8cbfdf76e3c (patch)
tree	955a1295c3fd4378a49478ad5835ca21b769417e /test/OpenMP
parent	3176e97f130184ece0e1a21352c8124cc83ff24a (diff)
download	FreeBSD-src-fc74ff5a0792641885551a63d9ddf8cbfdf76e3c.zip FreeBSD-src-fc74ff5a0792641885551a63d9ddf8cbfdf76e3c.tar.gz