diff --git a/clang/lib/Headers/__clang_cuda_builtin_vars.h b/clang/lib/Headers/__clang_cuda_builtin_vars.h
--- a/clang/lib/Headers/__clang_cuda_builtin_vars.h
+++ b/clang/lib/Headers/__clang_cuda_builtin_vars.h
@@ -27,10 +27,16 @@
 // PTX output:
 //  mov.u32     %r2, %tid.x;
 
+#ifdef __OPENMP_NVPTX__
+#define __DEVICE__
+#else
+#define __DEVICE__ __attribute__((device))
+#endif
+
 #define __CUDA_DEVICE_BUILTIN(FIELD, INTRINSIC)                                \
   __declspec(property(get = __fetch_builtin_##FIELD)) unsigned int FIELD;      \
   static inline __attribute__((always_inline))                                 \
-      __attribute__((device)) unsigned int __fetch_builtin_##FIELD(void) {     \
+      __DEVICE__ unsigned int __fetch_builtin_##FIELD(void) {                  \
     return INTRINSIC;                                                          \
   }
 
@@ -44,10 +50,10 @@
 // also disallows taking address of special variables, so we disable address-of
 // operator as well.
 #define __CUDA_DISALLOW_BUILTINVAR_ACCESS(TypeName)                            \
-  __attribute__((device)) TypeName() __DELETE;                                 \
-  __attribute__((device)) TypeName(const TypeName &) __DELETE;                 \
-  __attribute__((device)) void operator=(const TypeName &) const __DELETE;     \
-  __attribute__((device)) TypeName *operator&() const __DELETE
+  __DEVICE__ TypeName() __DELETE;                                              \
+  __DEVICE__ TypeName(const TypeName &) __DELETE;                              \
+  __DEVICE__ void operator=(const TypeName &) const __DELETE;                  \
+  __DEVICE__ TypeName *operator&() const __DELETE
 
 struct __cuda_builtin_threadIdx_t {
   __CUDA_DEVICE_BUILTIN(x,__nvvm_read_ptx_sreg_tid_x());
@@ -55,8 +61,8 @@
   __CUDA_DEVICE_BUILTIN(z,__nvvm_read_ptx_sreg_tid_z());
   // threadIdx should be convertible to uint3 (in fact in nvcc, it *is* a
   // uint3).  This function is defined after we pull in vector_types.h.
-  __attribute__((device)) operator dim3() const;
-  __attribute__((device)) operator uint3() const;
+  __DEVICE__ operator dim3() const;
+  __DEVICE__ operator uint3() const;
 
 private:
   __CUDA_DISALLOW_BUILTINVAR_ACCESS(__cuda_builtin_threadIdx_t);
@@ -68,8 +74,8 @@
   __CUDA_DEVICE_BUILTIN(z,__nvvm_read_ptx_sreg_ctaid_z());
   // blockIdx should be convertible to uint3 (in fact in nvcc, it *is* a
   // uint3).  This function is defined after we pull in vector_types.h.
-  __attribute__((device)) operator dim3() const;
-  __attribute__((device)) operator uint3() const;
+  __DEVICE__ operator dim3() const;
+  __DEVICE__ operator uint3() const;
 
 private:
   __CUDA_DISALLOW_BUILTINVAR_ACCESS(__cuda_builtin_blockIdx_t);
@@ -81,8 +87,8 @@
   __CUDA_DEVICE_BUILTIN(z,__nvvm_read_ptx_sreg_ntid_z());
   // blockDim should be convertible to dim3 (in fact in nvcc, it *is* a
   // dim3).  This function is defined after we pull in vector_types.h.
-  __attribute__((device)) operator dim3() const;
-  __attribute__((device)) operator uint3() const;
+  __DEVICE__ operator dim3() const;
+  __DEVICE__ operator uint3() const;
 
 private:
   __CUDA_DISALLOW_BUILTINVAR_ACCESS(__cuda_builtin_blockDim_t);
@@ -94,15 +100,14 @@
   __CUDA_DEVICE_BUILTIN(z,__nvvm_read_ptx_sreg_nctaid_z());
   // gridDim should be convertible to dim3 (in fact in nvcc, it *is* a
   // dim3).  This function is defined after we pull in vector_types.h.
-  __attribute__((device)) operator dim3() const;
-  __attribute__((device)) operator uint3() const;
+  __DEVICE__ operator dim3() const;
+  __DEVICE__ operator uint3() const;
 
 private:
   __CUDA_DISALLOW_BUILTINVAR_ACCESS(__cuda_builtin_gridDim_t);
 };
 
-#define __CUDA_BUILTIN_VAR                                                     \
-  extern const __attribute__((device)) __attribute__((weak))
+#define __CUDA_BUILTIN_VAR extern const __DEVICE__ __attribute__((weak))
 __CUDA_BUILTIN_VAR __cuda_builtin_threadIdx_t threadIdx;
 __CUDA_BUILTIN_VAR __cuda_builtin_blockIdx_t blockIdx;
 __CUDA_BUILTIN_VAR __cuda_builtin_blockDim_t blockDim;
@@ -111,11 +116,12 @@
 // warpSize should translate to read of %WARP_SZ but there's currently no
 // builtin to do so. According to PTX v4.2 docs 'to date, all target
 // architectures have a WARP_SZ value of 32'.
-__attribute__((device)) const int warpSize = 32;
+__DEVICE__ const int warpSize = 32;
 
 #undef __CUDA_DEVICE_BUILTIN
 #undef __CUDA_BUILTIN_VAR
 #undef __CUDA_DISALLOW_BUILTINVAR_ACCESS
 #undef __DELETE
+#undef __DEVICE__
 
 #endif /* __CUDA_BUILTIN_VARS_H */
diff --git a/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h b/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h
--- a/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h
+++ b/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h
@@ -30,6 +30,13 @@
 /// Provide definitions for these functions.
 #include <__clang_cuda_device_functions.h>
 
+/// Provide definition for CUDA builtin variables.
+/// The header is using features only available in C++ so we only include it in
+/// C++ mode.
+#ifdef __cplusplus
+#include <__clang_cuda_builtin_vars.h>
+#endif
+
 #undef __OPENMP_NVPTX__
 #undef __CUDA__
 
diff --git a/clang/test/Headers/nvptx_device_cmath_functions.cpp b/clang/test/Headers/nvptx_device_cmath_functions.cpp
--- a/clang/test/Headers/nvptx_device_cmath_functions.cpp
+++ b/clang/test/Headers/nvptx_device_cmath_functions.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
 
 #include <cmath>
 #include <cstdlib>
diff --git a/clang/test/Headers/nvptx_device_cmath_functions_cxx17.cpp b/clang/test/Headers/nvptx_device_cmath_functions_cxx17.cpp
--- a/clang/test/Headers/nvptx_device_cmath_functions_cxx17.cpp
+++ b/clang/test/Headers/nvptx_device_cmath_functions_cxx17.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -std=c++17
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -std=c++17 -o - | FileCheck -check-prefix CHECK-YES %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -std=c++17 -o - | FileCheck -check-prefix CHECK-YES %s
 
 #include <cmath>
 #include <cstdlib>
diff --git a/clang/test/Headers/nvptx_device_math_complex.c b/clang/test/Headers/nvptx_device_math_complex.c
--- a/clang/test/Headers/nvptx_device_math_complex.c
+++ b/clang/test/Headers/nvptx_device_math_complex.c
@@ -2,7 +2,7 @@
 // RUN: %clang_cc1 -verify -internal-isystem %S/Inputs/include -fopenmp -x c -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
 // RUN: %clang_cc1 -verify -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -x c -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -aux-triple powerpc64le-unknown-unknown -o - | FileCheck %s
 // RUN: %clang_cc1 -verify -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -aux-triple powerpc64le-unknown-unknown -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -aux-triple powerpc64le-unknown-unknown -o - | FileCheck %s
 // expected-no-diagnostics
 
 #ifdef __cplusplus
diff --git a/clang/test/Headers/nvptx_device_math_complex.cpp b/clang/test/Headers/nvptx_device_math_complex.cpp
--- a/clang/test/Headers/nvptx_device_math_complex.cpp
+++ b/clang/test/Headers/nvptx_device_math_complex.cpp
@@ -1,6 +1,6 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -verify -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -aux-triple powerpc64le-unknown-unknown -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -aux-triple powerpc64le-unknown-unknown -o - | FileCheck %s
 // expected-no-diagnostics
 
 #include <cmath>
diff --git a/clang/test/Headers/nvptx_device_math_functions.c b/clang/test/Headers/nvptx_device_math_functions.c
--- a/clang/test/Headers/nvptx_device_math_functions.c
+++ b/clang/test/Headers/nvptx_device_math_functions.c
@@ -6,7 +6,7 @@
 // RUN: %clang_cc1 -x c -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
 // RUN: %clang_cc1 -x c -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 
 #ifdef __cplusplus
 #include <cstdlib>
diff --git a/clang/test/Headers/nvptx_device_math_functions.cpp b/clang/test/Headers/nvptx_device_math_functions.cpp
--- a/clang/test/Headers/nvptx_device_math_functions.cpp
+++ b/clang/test/Headers/nvptx_device_math_functions.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
 
 #include <cstdlib>
 #include <cmath>
diff --git a/clang/test/Headers/nvptx_device_math_functions_cxx17.cpp b/clang/test/Headers/nvptx_device_math_functions_cxx17.cpp
--- a/clang/test/Headers/nvptx_device_math_functions_cxx17.cpp
+++ b/clang/test/Headers/nvptx_device_math_functions_cxx17.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -std=c++17
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -std=c++17 -o - | FileCheck -check-prefix CHECK-YES %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -std=c++17 -o - | FileCheck -check-prefix CHECK-YES %s
 
 #include <cstdlib>
 #include <cmath>
diff --git a/clang/test/Headers/nvptx_device_math_macro.cpp b/clang/test/Headers/nvptx_device_math_macro.cpp
--- a/clang/test/Headers/nvptx_device_math_macro.cpp
+++ b/clang/test/Headers/nvptx_device_math_macro.cpp
@@ -1,6 +1,6 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 // expected-no-diagnostics
 
 #include <cmath>
diff --git a/clang/test/Headers/nvptx_device_math_modf.cpp b/clang/test/Headers/nvptx_device_math_modf.cpp
--- a/clang/test/Headers/nvptx_device_math_modf.cpp
+++ b/clang/test/Headers/nvptx_device_math_modf.cpp
@@ -1,6 +1,6 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 
 #include <cmath>
 
diff --git a/clang/test/Headers/nvptx_device_math_sin.cpp b/clang/test/Headers/nvptx_device_math_sin.cpp
--- a/clang/test/Headers/nvptx_device_math_sin.cpp
+++ b/clang/test/Headers/nvptx_device_math_sin.cpp
@@ -1,8 +1,8 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=SLOW
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=SLOW
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -ffast-math -ffp-contract=fast
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast | FileCheck %s --check-prefix=FAST
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast | FileCheck %s --check-prefix=FAST
 // expected-no-diagnostics
 
 #include <cmath>
diff --git a/clang/test/Headers/nvptx_device_math_sin_cos.cpp b/clang/test/Headers/nvptx_device_math_sin_cos.cpp
--- a/clang/test/Headers/nvptx_device_math_sin_cos.cpp
+++ b/clang/test/Headers/nvptx_device_math_sin_cos.cpp
@@ -1,6 +1,6 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 
 #include <cmath>
 
diff --git a/clang/test/Headers/nvptx_device_math_sincos.cpp b/clang/test/Headers/nvptx_device_math_sincos.cpp
--- a/clang/test/Headers/nvptx_device_math_sincos.cpp
+++ b/clang/test/Headers/nvptx_device_math_sincos.cpp
@@ -1,7 +1,7 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers         -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
-// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -DCMATH -include __clang_openmp_device_functions.h -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers         -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -DCMATH -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
 
 #ifdef CMATH
 #include <cmath>
diff --git a/clang/test/Headers/openmp_device_math_isnan.cpp b/clang/test/Headers/openmp_device_math_isnan.cpp
--- a/clang/test/Headers/openmp_device_math_isnan.cpp
+++ b/clang/test/Headers/openmp_device_math_isnan.cpp
@@ -1,11 +1,11 @@
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=BOOL_RETURN
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=BOOL_RETURN
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -ffast-math -ffp-contract=fast
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast | FileCheck %s --check-prefix=BOOL_RETURN
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast | FileCheck %s --check-prefix=BOOL_RETURN
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -DUSE_ISNAN_WITH_INT_RETURN
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -DUSE_ISNAN_WITH_INT_RETURN | FileCheck %s --check-prefix=INT_RETURN
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -DUSE_ISNAN_WITH_INT_RETURN | FileCheck %s --check-prefix=INT_RETURN
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -ffast-math -ffp-contract=fast -DUSE_ISNAN_WITH_INT_RETURN
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast -DUSE_ISNAN_WITH_INT_RETURN | FileCheck %s --check-prefix=INT_RETURN
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -fdeclspec -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast -DUSE_ISNAN_WITH_INT_RETURN | FileCheck %s --check-prefix=INT_RETURN
 // expected-no-diagnostics
 
 #include <cmath>
diff --git a/clang/test/OpenMP/assumes_include_nvptx.cpp b/clang/test/OpenMP/assumes_include_nvptx.cpp
--- a/clang/test/OpenMP/assumes_include_nvptx.cpp
+++ b/clang/test/OpenMP/assumes_include_nvptx.cpp
@@ -1,8 +1,8 @@
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown  -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fexceptions -fcxx-exceptions -aux-triple powerpc64le-unknown-unknown -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown  -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -fexceptions -fcxx-exceptions -aux-triple powerpc64le-unknown-unknown -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
diff --git a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
--- a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
+++ b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
@@ -1,8 +1,8 @@
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown  -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
-// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fexceptions -fcxx-exceptions -aux-triple powerpc64le-unknown-unknown -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown  -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -triple nvptx64-unknown-unknown -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -O1 -disable-llvm-optzns -verify -fopenmp -internal-isystem %S/../Headers/Inputs/include -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -fdeclspec -fexceptions -fcxx-exceptions -aux-triple powerpc64le-unknown-unknown -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER