[Openmp-commits] [openmp] [OpenMP][libomptarget] Enable parallel copies via multiple SDMA engines (PR #71801)

[Jan Patrick Lehr via Openmp-commits]

================
@@ -130,6 +130,45 @@ Error iterateAgentMemoryPools(hsa_agent_t Agent, CallbackTy Cb) {
                        "Error in hsa_amd_agent_iterate_memory_pools: %s");
 }
 
+/// Dispatches an asynchronous memory copy.
+/// Enables different SDMA engines for the dispatch in a round-robin fashion.
+Error asyncMemCopy(bool UseMultipleSdmaEngines, void *Dst, hsa_agent_t DstAgent,
+                   const void *Src, hsa_agent_t SrcAgent, size_t Size,
+                   uint32_t NumDepSignals, const hsa_signal_t *DepSignals,
+                   hsa_signal_t CompletionSignal) {
+  if (UseMultipleSdmaEngines) {
----------------
jplehr wrote:

This needs to be negated to maintain the current functionality per default and not rely on ROCm 5.7 functionality.

https://github.com/llvm/llvm-project/pull/71801