Index: clang/lib/Headers/__clang_hip_runtime_wrapper.h
===================================================================
--- clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -18,28 +18,6 @@
 
 #if __HIP__
 
-#if !defined(__HIPCC_RTC__)
-#include <cmath>
-#include <cstdlib>
-#include <stdlib.h>
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #define __host__ __attribute__((host))
 #define __device__ __attribute__((device))
 #define __global__ __attribute__((global))
@@ -68,24 +46,58 @@
 }
 #endif //__cplusplus
 
+typedef __SIZE_TYPE__ __hip_size_t;
+
+#ifdef __cplusplus
+extern "C" {
+#endif //__cplusplus
+
 #if __HIP_ENABLE_DEVICE_MALLOC__
-extern "C" __device__ void *__hip_malloc(size_t __size);
-extern "C" __device__ void *__hip_free(void *__ptr);
-static inline __device__ void *malloc(size_t __size) {
+__device__ void *__hip_malloc(__hip_size_t __size);
+__device__ void *__hip_free(void *__ptr);
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   return __hip_malloc(__size);
 }
-static inline __device__ void *free(void *__ptr) { return __hip_free(__ptr); }
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
+  return __hip_free(__ptr);
+}
 #else
-static inline __device__ void *malloc(size_t __size) {
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
   return nullptr;
 }
-static inline __device__ void *free(void *__ptr) {
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
   return nullptr;
 }
 #endif
 
+#ifdef __cplusplus
+} // extern "C"
+#endif //__cplusplus
+
+#if !defined(__HIPCC_RTC__)
+#include <cmath>
+#include <cstdlib>
+#include <stdlib.h>
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 
Index: clang/test/Headers/hip-header.hip
===================================================================
--- clang/test/Headers/hip-header.hip
+++ clang/test/Headers/hip-header.hip
@@ -26,6 +26,13 @@
 // RUN:   -target-cpu gfx906 -emit-llvm %s -fcuda-is-device -o - \
 // RUN:   -D__HIPCC_RTC__ -std=c++14 | FileCheck -check-prefixes=CHECK,CXX14 %s
 
+// RUN: %clang_cc1 -include __clang_hip_runtime_wrapper.h \
+// RUN:   -internal-isystem %S/../../lib/Headers/cuda_wrappers \
+// RUN:   -internal-isystem %S/Inputs/include \
+// RUN:   -triple amdgcn-amd-amdhsa -aux-triple x86_64-unknown-unknown \
+// RUN:   -target-cpu gfx906 -emit-llvm %s -fcuda-is-device -o - \
+// RUN:   -D__HIPCC_RTC__ | FileCheck -check-prefixes=MALLOCFREE %s
+
 // expected-no-diagnostics
 
 // Check support for pure and deleted virtual functions
@@ -115,3 +122,15 @@
 
   return r ;
 }
+
+// Check that device malloc and free do not conflict with std headers.
+#include <cstdlib>
+// MALLOCFREE-LABEL: define{{.*}}@_Z11test_malloc
+__device__ void test_malloc(void *a) {
+  a = malloc(42);
+}
+
+// MALLOCFREE-LABEL: define{{.*}}@_Z9test_free
+__device__ void test_free(void *a) {
+  free(a);
+}