[OpenMP][NVPTX] Added forward declaration for atomic operations

Pretty similar to D95058, this patch added forward declaration for
CUDA atomic functions. We already have definitions with right mangled names in
internal CUDA headers so the forward declaration here can work properly.

Reviewed By: jdoerfert, JonChesterfield

Differential Revision: https://reviews.llvm.org/D95085

diff --git a/openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h b/openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h
index ba3d331..1d7b649 100644 (file)
--- a/openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h
+++ b/openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h
@@ -130,6 +130,15 @@ DEVICE int GetNumberOfThreadsInBlock();
 DEVICE unsigned GetWarpId();
 DEVICE unsigned GetLaneId();
 
+// Forward declaration of atomics. Although they're template functions, we
+// already have definitions for different types in CUDA internal headers with
+// the right mangled names.
+template <typename T> DEVICE T atomicAdd(T *address, T val);
+template <typename T> DEVICE T atomicInc(T *address, T val);
+template <typename T> DEVICE T atomicMax(T *address, T val);
+template <typename T> DEVICE T atomicExch(T *address, T val);
+template <typename T> DEVICE T atomicCAS(T *address, T compare, T val);
+
 // Atomics
 template <typename T> INLINE T __kmpc_atomic_add(T *address, T val) {
   return atomicAdd(address, val);