[Openmp-commits] [llvm] [openmp] [offload] Use HSA SVM for AMDGPU shared memory (PR #215801)

[Joseph Huber via Openmp-commits]

================
@@ -3024,9 +3191,63 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
     return Plugin::success();
   }
 
+  /// Fill \p TgtPtr with the given pattern on the host. Requires \p TgtPtr to
+  /// be host accessible.
+  Error dataFillHostImpl(void *TgtPtr, const void *PatternPtr,
----------------
jhuber6 wrote:

Is this an optimization to fill via SVM? Should be a separate PR if so.

https://github.com/llvm/llvm-project/pull/215801