[Openmp-commits] [openmp] 133db44 - [libomptarget] Implement most hip atomic functions in terms of intrinsics

[via Openmp-commits]

Author: Jon Chesterfield
Date: 2020-03-04T17:56:40Z
New Revision: 133db44996a80db957360a0b727479d4a8d4d1a2

URL: https://github.com/llvm/llvm-project/commit/133db44996a80db957360a0b727479d4a8d4d1a2
DIFF: https://github.com/llvm/llvm-project/commit/133db44996a80db957360a0b727479d4a8d4d1a2.diff

LOG: [libomptarget] Implement most hip atomic functions in terms of intrinsics

Summary:
[libomptarget] Implement hip atomic functions in terms of intrinsics

All but atomicInc can be implemented using type generic clang intrinsics.
There is not yet a corresponding intrinsic for atomicInc in clang, only one in
LLVM. This patch leaves atomicInc as an unresolved symbol.

Reviewers: jdoerfert, ABataev, hfinkel, grokos, arsenm

Reviewed By: arsenm

Subscribers: sri, saiislam, wdng, jvesely, mgorny, jfb, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D73076

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h b/openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h
index 9e0edbbbba56..df102c765925 100644
--- a/openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h
+++ b/openmp/libomptarget/deviceRTLs/amdgcn/src/hip_atomics.h
@@ -11,29 +11,32 @@
 
 #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);
-
+// inc requires an amdgcn specific intrinsic which is not yet available
 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);
+namespace {
+
+template <typename T> DEVICE T atomicAdd(T *address, T val) {
+  return __atomic_fetch_add(address, val, __ATOMIC_SEQ_CST);
+}
+
+template <typename T> DEVICE T atomicMax(T *address, T val) {
+  return __atomic_fetch_max(address, val, __ATOMIC_SEQ_CST);
+}
 
-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);
+template <typename T> DEVICE T atomicExch(T *address, T val) {
+  T r;
+  __atomic_exchange(address, &val, &r, __ATOMIC_SEQ_CST);
+  return r;
+}
 
-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);
+template <typename T> DEVICE T atomicCAS(T *address, T compare, T val) {
+  (void)__atomic_compare_exchange(address, &compare, &val, false,
+                                  __ATOMIC_SEQ_CST, __ATOMIC_RELAXED);
+  return compare;
+}
 
+} // namespace
 #endif