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

[Robert Imschweiler via llvm-branch-commits]

ro-i wrote:

so, I guess this needs to wait until that patch is in a released HSA version which we can then check for. Or we accept the slow fill path for now.

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