Index: lib/Driver/ToolChains/Clang.cpp
===================================================================
--- lib/Driver/ToolChains/Clang.cpp
+++ lib/Driver/ToolChains/Clang.cpp
@@ -1166,7 +1166,7 @@
     }
 
     CmdArgs.push_back("-include");
-    CmdArgs.push_back("__clang_openmp_math.h");
+    CmdArgs.push_back("__clang_openmp_math_declares.h");
   }
 
   // Add -i* options, and automatically translate to
Index: lib/Headers/CMakeLists.txt
===================================================================
--- lib/Headers/CMakeLists.txt
+++ lib/Headers/CMakeLists.txt
@@ -132,6 +132,7 @@
   openmp_wrappers/math.h
   openmp_wrappers/cmath
   openmp_wrappers/__clang_openmp_math.h
+  openmp_wrappers/__clang_openmp_math_declares.h
 )
 
 set(output_dir ${LLVM_LIBRARY_OUTPUT_INTDIR}/clang/${CLANG_VERSION}/include)
Index: lib/Headers/__clang_cuda_math_forward_declares.h
===================================================================
--- lib/Headers/__clang_cuda_math_forward_declares.h
+++ lib/Headers/__clang_cuda_math_forward_declares.h
@@ -27,11 +27,20 @@
   static __inline__ __attribute__((always_inline)) __attribute__((device))
 #endif
 
-__DEVICE__ double abs(double);
-__DEVICE__ float abs(float);
-__DEVICE__ int abs(int);
+#ifndef _OPENMP
+__DEVICE__ long abs(long);
+__DEVICE__ long long abs(long long);
+#else
+#ifndef __cplusplus
 __DEVICE__ long abs(long);
 __DEVICE__ long long abs(long long);
+#endif
+#endif
+__DEVICE__ int abs(int);
+__DEVICE__ long labs(long);
+__DEVICE__ long long llabs(long long);
+__DEVICE__ double abs(double);
+__DEVICE__ float abs(float);
 __DEVICE__ double acos(double);
 __DEVICE__ float acos(float);
 __DEVICE__ double acosh(double);
@@ -117,12 +126,10 @@
 __DEVICE__ bool isnormal(float);
 __DEVICE__ bool isunordered(double, double);
 __DEVICE__ bool isunordered(float, float);
-__DEVICE__ long labs(long);
 __DEVICE__ double ldexp(double, int);
 __DEVICE__ float ldexp(float, int);
 __DEVICE__ double lgamma(double);
 __DEVICE__ float lgamma(float);
-__DEVICE__ long long llabs(long long);
 __DEVICE__ long long llrint(double);
 __DEVICE__ long long llrint(float);
 __DEVICE__ double log10(double);
Index: lib/Headers/openmp_wrappers/__clang_openmp_math.h
===================================================================
--- lib/Headers/openmp_wrappers/__clang_openmp_math.h
+++ lib/Headers/openmp_wrappers/__clang_openmp_math.h
@@ -23,15 +23,6 @@
 #define __CUDA__
 
 #if defined(__cplusplus)
-  #include <__clang_cuda_math_forward_declares.h>
-#endif
-
-/// Include declarations for libdevice functions.
-#include <__clang_cuda_libdevice_declares.h>
-/// Provide definitions for these functions.
-#include <__clang_cuda_device_functions.h>
-
-#if defined(__cplusplus)
   #include <__clang_cuda_cmath.h>
 #endif
 
Index: lib/Headers/openmp_wrappers/__clang_openmp_math_declares.h
===================================================================
--- /dev/null
+++ lib/Headers/openmp_wrappers/__clang_openmp_math_declares.h
@@ -0,0 +1,27 @@
+/*===---- __clang_openmp_math_declares.h - OpenMP math declares ------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_math_forward_declares.h>
+  #include <cstdlib>
+  #include <stdlib.h>
+#endif
+
+/// Include declarations for libdevice functions.
+#include <__clang_cuda_libdevice_declares.h>
+/// Provide definitions for these functions.
+#include <__clang_cuda_device_functions.h>
+
+#undef __CUDA__
+
+#endif
Index: lib/Headers/openmp_wrappers/cmath
===================================================================
--- lib/Headers/openmp_wrappers/cmath
+++ lib/Headers/openmp_wrappers/cmath
@@ -7,9 +7,7 @@
  *===-----------------------------------------------------------------------===
  */
 
-#ifndef __cplusplus
 #include <__clang_openmp_math.h>
-#endif
 
 #ifndef __CLANG_NO_HOST_MATH__
 #include_next <cmath>
Index: lib/Headers/openmp_wrappers/math.h
===================================================================
--- lib/Headers/openmp_wrappers/math.h
+++ lib/Headers/openmp_wrappers/math.h
@@ -7,9 +7,7 @@
  *===-----------------------------------------------------------------------===
  */
 
-#ifndef __cplusplus
 #include <__clang_openmp_math.h>
-#endif
 
 #ifndef __CLANG_NO_HOST_MATH__
 #include_next <math.h>
Index: test/Headers/Inputs/include/cstdlib
===================================================================
--- /dev/null
+++ test/Headers/Inputs/include/cstdlib
@@ -0,0 +1,2 @@
+#pragma once
+typedef __SIZE_TYPE__ size_t;
Index: test/Headers/nvptx_device_cmath_functions.c
===================================================================
--- test/Headers/nvptx_device_cmath_functions.c
+++ test/Headers/nvptx_device_cmath_functions.c
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -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_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -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_math_declares.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -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>
 
Index: test/Headers/nvptx_device_cmath_functions.cpp
===================================================================
--- test/Headers/nvptx_device_cmath_functions.cpp
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -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_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -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_math_declares.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -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>
 
Index: test/Headers/nvptx_device_math_functions.c
===================================================================
--- test/Headers/nvptx_device_math_functions.c
+++ test/Headers/nvptx_device_math_functions.c
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -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_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -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_math_declares.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -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 <math.h>
 
Index: test/Headers/nvptx_device_math_functions.cpp
===================================================================
--- test/Headers/nvptx_device_math_functions.cpp
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -4,7 +4,7 @@
 // REQUIRES: nvptx-registered-target
 
 // RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -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_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -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_math_declares.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -include cstdlib -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 <math.h>