diff --git a/clang/lib/Headers/__clang_cuda_device_functions.h b/clang/lib/Headers/__clang_cuda_device_functions.h
diff --git a/clang/lib/Headers/__clang_hip_cmath.h b/clang/lib/Headers/__clang_hip_cmath.h
diff --git a/clang/lib/Headers/__clang_hip_math.h b/clang/lib/Headers/__clang_hip_math.h
@@ -9,7 +9,7 @@
 #ifndef __CLANG_HIP_MATH_H__
 #define __CLANG_HIP_MATH_H__
 
-#if !defined(__HIP__)
+#if !defined(__HIP__) && !defined(__OPENMP_AMDGCN__)
 #error "This file is for HIP and OpenMP AMDGCN device compilation only."
 #endif
 
@@ -19,18 +19,30 @@
 #endif
 #include <limits.h>
 #include <stdint.h>
-#endif // __HIPCC_RTC__
+#ifdef __OPENMP_AMDGCN__
+#include <omp.h>
+#endif
+#endif // !defined(__HIPCC_RTC__)
 
 #pragma push_macro("__DEVICE__")
+
+#ifdef __OPENMP_AMDGCN__
+#define __DEVICE__ static inline __attribute__((always_inline, nothrow))
+#else
 #define __DEVICE__ static __device__ inline __attribute__((always_inline))
+#endif
 
 // A few functions return bool type starting only in C++11.
 #pragma push_macro("__RETURN_TYPE")
+#ifdef __OPENMP_AMDGCN__
+#define __RETURN_TYPE int
+#else
 #if defined(__cplusplus)
 #define __RETURN_TYPE bool
 #else
 #define __RETURN_TYPE int
 #endif
+#endif // __OPENMP_AMDGCN__
 
 #if defined (__cplusplus) && __cplusplus < 201103L
 // emulate static_assert on type sizes
@@ -249,6 +261,9 @@ float fmodf(float __x, float __y) { return __ocml_fmod_f32(__x, __y); }
 __DEVICE__
 float frexpf(float __x, int *__nptr) {
   int __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   float __r =
       __ocml_frexp_f32(__x, (__attribute__((address_space(5))) int *)&__tmp);
   *__nptr = __tmp;
@@ -334,6 +349,9 @@ long int lroundf(float __x) { return __ocml_round_f32(__x); }
 __DEVICE__
 float modff(float __x, float *__iptr) {
   float __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   float __r =
       __ocml_modf_f32(__x, (__attribute__((address_space(5))) float *)&__tmp);
   *__iptr = __tmp;
@@ -414,6 +432,9 @@ float remainderf(float __x, float __y) {
 __DEVICE__
 float remquof(float __x, float __y, int *__quo) {
   int __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   float __r = __ocml_remquo_f32(
       __x, __y, (__attribute__((address_space(5))) int *)&__tmp);
   *__quo = __tmp;
@@ -470,6 +491,9 @@ __RETURN_TYPE __signbitf(float __x) { return __ocml_signbit_f32(__x); }
 __DEVICE__
 void sincosf(float __x, float *__sinptr, float *__cosptr) {
   float __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   *__sinptr =
       __ocml_sincos_f32(__x, (__attribute__((address_space(5))) float *)&__tmp);
   *__cosptr = __tmp;
@@ -478,6 +502,9 @@ void sincosf(float __x, float *__sinptr, float *__cosptr) {
 __DEVICE__
 void sincospif(float __x, float *__sinptr, float *__cosptr) {
   float __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   *__sinptr = __ocml_sincospi_f32(
       __x, (__attribute__((address_space(5))) float *)&__tmp);
   *__cosptr = __tmp;
@@ -790,6 +817,9 @@ double fmod(double __x, double __y) { return __ocml_fmod_f64(__x, __y); }
 __DEVICE__
 double frexp(double __x, int *__nptr) {
   int __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   double __r =
       __ocml_frexp_f64(__x, (__attribute__((address_space(5))) int *)&__tmp);
   *__nptr = __tmp;
@@ -874,6 +904,9 @@ long int lround(double __x) { return __ocml_round_f64(__x); }
 __DEVICE__
 double modf(double __x, double *__iptr) {
   double __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   double __r =
       __ocml_modf_f64(__x, (__attribute__((address_space(5))) double *)&__tmp);
   *__iptr = __tmp;
@@ -962,6 +995,9 @@ double remainder(double __x, double __y) {
 __DEVICE__
 double remquo(double __x, double __y, int *__quo) {
   int __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   double __r = __ocml_remquo_f64(
       __x, __y, (__attribute__((address_space(5))) int *)&__tmp);
   *__quo = __tmp;
@@ -1020,6 +1056,9 @@ double sin(double __x) { return __ocml_sin_f64(__x); }
 __DEVICE__
 void sincos(double __x, double *__sinptr, double *__cosptr) {
   double __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   *__sinptr = __ocml_sincos_f64(
       __x, (__attribute__((address_space(5))) double *)&__tmp);
   *__cosptr = __tmp;
@@ -1028,6 +1067,9 @@ void sincos(double __x, double *__sinptr, double *__cosptr) {
 __DEVICE__
 void sincospi(double __x, double *__sinptr, double *__cosptr) {
   double __tmp;
+#ifdef __OPENMP_AMDGCN__
+#pragma omp allocate(__tmp) allocator(omp_thread_mem_alloc)
+#endif
   *__sinptr = __ocml_sincospi_f64(
       __x, (__attribute__((address_space(5))) double *)&__tmp);
   *__cosptr = __tmp;
@@ -1262,15 +1304,15 @@ float min(float __x, float __y) { return fminf(__x, __y); }
 __DEVICE__
 double min(double __x, double __y) { return fmin(__x, __y); }
 
-#if !defined(__HIPCC_RTC__)
+#if !defined(__HIPCC_RTC__) && !defined(__OPENMP_AMDGCN__)
 __host__ inline static int min(int __arg1, int __arg2) {
   return std::min(__arg1, __arg2);
 }
 
 __host__ inline static int max(int __arg1, int __arg2) {
   return std::max(__arg1, __arg2);
 }
-#endif // __HIPCC_RTC__
+#endif // !defined(__HIPCC_RTC__) && !defined(__OPENMP_AMDGCN__)
 #endif
 
 #pragma pop_macro("__DEVICE__")

diff --git a/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h b/clang/lib/Headers/openmp_wrappers/__clang_openmp_device_functions.h
@@ -14,13 +14,13 @@
 #error "This file is for OpenMP compilation only."
 #endif
 
-#pragma omp begin declare variant match(                                       \
-    device = {arch(nvptx, nvptx64)}, implementation = {extension(match_any)})
-
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+#pragma omp begin declare variant match(                                       \
+    device = {arch(nvptx, nvptx64)}, implementation = {extension(match_any)})
+
 #define __CUDA__
 #define __OPENMP_NVPTX__
 
@@ -33,11 +33,33 @@ extern "C" {
 #undef __OPENMP_NVPTX__
 #undef __CUDA__
 
-#ifdef __cplusplus
-} // extern "C"
+#pragma omp end declare variant
+
+#ifdef __AMDGCN__
+#pragma omp begin declare variant match(device = {arch(amdgcn)})
+
+// Import types which will be used by __clang_hip_libdevice_declares.h
+#ifndef __cplusplus
+#include <stdbool.h>
+#include <stdint.h>
 #endif
 
+#define __OPENMP_AMDGCN__
+#pragma push_macro("__device__")
+#define __device__
+
+/// Include declarations for libdevice functions.
+#include <__clang_hip_libdevice_declares.h>
+
+#pragma pop_macro("__device__")
+#undef __OPENMP_AMDGCN__
+
 #pragma omp end declare variant
+#endif
+
+#ifdef __cplusplus
+} // extern "C"
+#endif
 
 // Ensure we make `_ZdlPv`, aka. `operator delete(void*)` available without the
 // need to `include <new>` in C++ mode.

diff --git a/clang/lib/Headers/openmp_wrappers/cmath b/clang/lib/Headers/openmp_wrappers/cmath
@@ -75,4 +75,58 @@ __DEVICE__ float tgamma(float __x) { return ::tgammaf(__x); }
 
 #pragma omp end declare variant
 
+#ifdef __AMDGCN__
+#pragma omp begin declare variant match(device = {arch(amdgcn)})
+
+#pragma push_macro("__constant__")
+#define __constant__ __attribute__((constant))
+#define __OPENMP_AMDGCN__
+
+#include <__clang_hip_cmath.h>
+
+#pragma pop_macro("__constant__")
+#undef __OPENMP_AMDGCN__
+
+// Define overloads otherwise which are absent
+#define __DEVICE__ static constexpr __attribute__((always_inline, nothrow))
+
+__DEVICE__ float acos(float __x) { return ::acosf(__x); }
+__DEVICE__ float acosh(float __x) { return ::acoshf(__x); }
+__DEVICE__ float asin(float __x) { return ::asinf(__x); }
+__DEVICE__ float asinh(float __x) { return ::asinhf(__x); }
+__DEVICE__ float atan(float __x) { return ::atanf(__x); }
+__DEVICE__ float atan2(float __x, float __y) { return ::atan2f(__x, __y); }
+__DEVICE__ float atanh(float __x) { return ::atanhf(__x); }
+__DEVICE__ float cbrt(float __x) { return ::cbrtf(__x); }
+__DEVICE__ float cosh(float __x) { return ::coshf(__x); }
+__DEVICE__ float erf(float __x) { return ::erff(__x); }
+__DEVICE__ float erfc(float __x) { return ::erfcf(__x); }
+__DEVICE__ float exp2(float __x) { return ::exp2f(__x); }
+__DEVICE__ float expm1(float __x) { return ::expm1f(__x); }
+__DEVICE__ float fdim(float __x, float __y) { return ::fdimf(__x, __y); }
+__DEVICE__ float hypot(float __x, float __y) { return ::hypotf(__x, __y); }
+__DEVICE__ int ilogb(float __x) { return ::ilogbf(__x); }
+__DEVICE__ float ldexp(float __arg, int __exp) {
+  return ::ldexpf(__arg, __exp);
+}
+__DEVICE__ float lgamma(float __x) { return ::lgammaf(__x); }
+__DEVICE__ float log1p(float __x) { return ::log1pf(__x); }
+__DEVICE__ float logb(float __x) { return ::logbf(__x); }
+__DEVICE__ float nextafter(float __x, float __y) {
+  return ::nextafterf(__x, __y);
+}
+__DEVICE__ float remainder(float __x, float __y) {
+  return ::remainderf(__x, __y);
+}
+__DEVICE__ float scalbn(float __x, int __y) { return ::scalbnf(__x, __y); }
+__DEVICE__ float sinh(float __x) { return ::sinhf(__x); }
+__DEVICE__ float tan(float __x) { return ::tanf(__x); }
+__DEVICE__ float tanh(float __x) { return ::tanhf(__x); }
+__DEVICE__ float tgamma(float __x) { return ::tgammaf(__x); }
+
+#undef __DEVICE__
+
+#pragma omp end declare variant
+#endif // __AMDGCN__
+
 #endif
diff --git a/clang/lib/Headers/openmp_wrappers/math.h b/clang/lib/Headers/openmp_wrappers/math.h
@@ -48,4 +48,14 @@
 
 #pragma omp end declare variant
 
+#ifdef __AMDGCN__
+#pragma omp begin declare variant match(device = {arch(amdgcn)})
+
+#define __OPENMP_AMDGCN__
+#include <__clang_hip_math.h>
+#undef __OPENMP_AMDGCN__
+
+#pragma omp end declare variant
+#endif
+
 #endif
diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -74,3 +74,6 @@
 
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
 // CHECK-EMIT-LLVM-IR: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-emit-llvm"
+
+// RUN: env LIBRARY_PATH=%S/Inputs/hip_dev_lib %clang -### -target x86_64-pc-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -lm --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIB-DEVICE
+// CHECK-LIB-DEVICE: {{.*}}llvm-link{{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"
diff --git a/clang/test/Headers/Inputs/include/algorithm b/clang/test/Headers/Inputs/include/algorithm
@@ -0,0 +1,6 @@
+#pragma once
+
+namespace std {
+ template<class T> constexpr const T& min(const T& a, const T& b);
+ template<class T> constexpr const T& max(const T& a, const T& b);
+}
diff --git a/clang/test/Headers/Inputs/include/cstdlib b/clang/test/Headers/Inputs/include/cstdlib
@@ -27,3 +27,4 @@ float abs(float __x) { return fabs(__x); }
 double abs(double __x) { return fabs(__x); }
 
 }
+
diff --git a/clang/test/Headers/Inputs/include/omp.h b/clang/test/Headers/Inputs/include/omp.h
@@ -0,0 +1,21 @@
+#ifndef __OMP_H
+#define __OMP_H
+
+#if _OPENMP
+// Follows the pattern in interface.h
+// Clang sema checks this type carefully, needs to closely match that from omp.h
+typedef enum omp_allocator_handle_t {
+  omp_null_allocator = 0,
+  omp_default_mem_alloc = 1,
+  omp_large_cap_mem_alloc = 2,
+  omp_const_mem_alloc = 3,
+  omp_high_bw_mem_alloc = 4,
+  omp_low_lat_mem_alloc = 5,
+  omp_cgroup_mem_alloc = 6,
+  omp_pteam_mem_alloc = 7,
+  omp_thread_mem_alloc = 8,
+  KMP_ALLOCATOR_MAX_HANDLE = ~(0U)
+} omp_allocator_handle_t;
+#endif
+
+#endif
diff --git a/clang/test/Headers/Inputs/include/utility b/clang/test/Headers/Inputs/include/utility
@@ -0,0 +1,2 @@
+#pragma once
+
diff --git a/clang/test/Headers/amdgcn_openmp_device_math.c b/clang/test/Headers/amdgcn_openmp_device_math.c
@@ -0,0 +1,51 @@
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c -fopenmp -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-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 amdgcn-amd-amdhsa -aux-triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s --check-prefixes=CHECK-C,CHECK
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-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 amdgcn-amd-amdhsa -aux-triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s --check-prefixes=CHECK-CPP,CHECK
+
+#ifdef __cplusplus
+#include <cmath>
+#else
+#include <math.h>
+#endif
+
+void test_math_f64(double x) {
+// CHECK-LABEL: define {{.*}}test_math_f64
+#pragma omp target
+  {
+    // CHECK: call double @__ocml_sin_f64
+    double l1 = sin(x);
+    // CHECK: call double @__ocml_cos_f64
+    double l2 = cos(x);
+    // CHECK: call double @__ocml_fabs_f64
+    double l3 = fabs(x);
+  }
+}
+
+void test_math_f32(float x) {
+// CHECK-LABEL: define {{.*}}test_math_f32
+#pragma omp target
+  {
+    // CHECK-C: call double @__ocml_sin_f64
+    // CHECK-CPP: call float @__ocml_sin_f32
+    float l1 = sin(x);
+    // CHECK-C: call double @__ocml_cos_f64
+    // CHECK-CPP: call float @__ocml_cos_f32
+    float l2 = cos(x);
+    // CHECK-C: call double @__ocml_fabs_f64
+    // CHECK-CPP: call float @__ocml_fabs_f32
+    float l3 = fabs(x);
+  }
+}
+void test_math_f32_suffix(float x) {
+// CHECK-LABEL: define {{.*}}test_math_f32_suffix
+#pragma omp target
+  {
+    // CHECK: call float @__ocml_sin_f32
+    float l1 = sinf(x);
+    // CHECK: call float @__ocml_cos_f32
+    float l2 = cosf(x);
+    // CHECK: call float @__ocml_fabs_f32
+    float l3 = fabsf(x);
+  }
+}
diff --git a/clang/test/Headers/openmp_device_math_isnan.cpp b/clang/test/Headers/openmp_device_math_isnan.cpp
@@ -21,14 +21,14 @@
 double math(float f, double d) {
   double r = 0;
   // INT_RETURN: call i32 @__nv_isnanf(float
-  // AMD_INT_RETURN: call i32 @_{{.*}}isnanf(float
+  // AMD_INT_RETURN: call i32 @__ocml_isnan_f32(float
   // BOOL_RETURN: call i32 @__nv_isnanf(float
-  // AMD_BOOL_RETURN: call zeroext i1 @_{{.*}}isnanf(float
+  // AMD_BOOL_RETURN: call i32 @__ocml_isnan_f32(float
   r += std::isnan(f);
   // INT_RETURN: call i32 @__nv_isnand(double
-  // AMD_INT_RETURN: call i32 @_{{.*}}isnand(double
+  // AMD_INT_RETURN: call i32 @__ocml_isnan_f64(double
   // BOOL_RETURN: call i32 @__nv_isnand(double
-  // AMD_BOOL_RETURN: call zeroext i1 @_{{.*}}isnand(double
+  // AMD_BOOL_RETURN: call i32 @__ocml_isnan_f64(double
   r += std::isnan(d);
   return r;
 }

diff --git a/openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt b/openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
@@ -107,7 +107,7 @@ macro(add_cuda_bc_library)
   set(cu_cmd ${CLANG_TOOL}
     -xc++
     -c
-    -mllvm -openmp-opt-disable-internalization
+    -mllvm -openmp-opt-disable
     -std=c++14
     -ffreestanding
     -target amdgcn-amd-amdhsa
@@ -157,7 +157,7 @@ foreach(mcpu ${mcpus})
   add_custom_command(
     OUTPUT ${bc_libname}
     COMMAND ${LINK_TOOL} ${bc_files} | ${OPT_TOOL} --always-inline -o ${OUTPUTDIR}/${bc_libname}
-    DEPENDS ${bc_files})
+    DEPENDS ${bc_files} opt)
 
   add_custom_target(lib${libname}-${mcpu} ALL DEPENDS ${bc_libname})
Original file line number	Diff line number	Diff line change
Expand Up		@@ -27,3 +27,4 @@ float abs(float __x) { return fabs(__x); }
		double abs(double __x) { return fabs(__x); }

		}