[libomptarget][nfc] Add declarations of atomic functions for amdgcn

[JonChesterfield]

Summary

[libomptarget][nfc] Add declarations of atomic functions for amdgcn

This enables building more source for amdgcn. The functions are usually available
in a hip runtime header, but are duplicated here to decouple the implementation

[jdoerfert]

LGTM. See my comments below.

openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h

9

Header guards should be useful here.

35

One could have opted for a template solution but this is fine too.

[JonChesterfield]

• add header guards

[JonChesterfield]

openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h

9

Agreed, sloppy to miss them out here. Fixed.

35

This looks ugly in the header but has the attraction of mapping 1:1 onto functions defined in the support library, which may not want to implement them as explicit instantiations.

openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt

get_filename_component(devicertl_base_directory
   DIRECTORY)
 
 set(cuda_sources
   ${devicertl_base_directory}/common/src/cancel.cu
   ${devicertl_base_directory}/common/src/critical.cu)
 
 set(h_files
   ${CMAKE_CURRENT_SOURCE_DIR}/src/amdgcn_interface.h
+  ${CMAKE_CURRENT_SOURCE_DIR}/src/hip_atomics.h
   ${CMAKE_CURRENT_SOURCE_DIR}/src/target_impl.h
   ${devicertl_base_directory}/common/debug.h
   ${devicertl_base_directory}/common/device_environment.h
   ${devicertl_base_directory}/common/state-queue.h
   ${devicertl_base_directory}/common/state-queuei.h
   ${devicertl_base_directory}/common/support.h)
 
 # for both in-tree and out-of-tree build

openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h

+//===---- hip_atomics.h - Declarations of hip atomic functions ---- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef OMPTARGET_AMDGCN_HIP_ATOMICS_H
+#define OMPTARGET_AMDGCN_HIP_ATOMICS_H
+
+#include "target_impl.h"
+
+DEVICE unsigned atomicAdd(unsigned *address, unsigned val);
+DEVICE int atomicAdd(int *address, int val);
+DEVICE unsigned long long atomicAdd(unsigned long long *address,
+                                    unsigned long long val);
+
+DEVICE unsigned atomicInc(unsigned *address);
+DEVICE unsigned atomicInc(unsigned *address, unsigned max);
+DEVICE int atomicInc(int *address);
+
+DEVICE int atomicMax(int *address, int val);
+DEVICE unsigned atomicMax(unsigned *address, unsigned val);
+DEVICE unsigned long long atomicMax(unsigned long long *address,
+                                    unsigned long long val);
+
+DEVICE int atomicExch(int *address, int val);
+DEVICE unsigned atomicExch(unsigned *address, unsigned val);
+DEVICE unsigned long long atomicExch(unsigned long long *address,
+                                     unsigned long long val);
+
+DEVICE unsigned atomicCAS(unsigned *address, unsigned compare, unsigned val);
+DEVICE int atomicCAS(int *address, int compare, int val);
+DEVICE unsigned long long atomicCAS(unsigned long long *address,
+                                    unsigned long long compare,
+                                    unsigned long long val);
+
+#endif

openmp/libomptarget/deviceRTLs/amdgcn/src/target_impl.h

 #include <stdint.h>
 
 #define DEVICE __attribute__((device))
 #define INLINE inline DEVICE
 #define NOINLINE __attribute__((noinline)) DEVICE
 #define SHARED __attribute__((shared))
 #define ALIGN(N) __attribute__((aligned(N)))
 
+#include "hip_atomics.h"
+
 ////////////////////////////////////////////////////////////////////////////////
 // Kernel options
 ////////////////////////////////////////////////////////////////////////////////
 
 ////////////////////////////////////////////////////////////////////////////////
 // The following def must match the absolute limit hardwired in the host RTL
 // max number of threads per team
 #define MAX_THREADS_PER_TEAM 1024