Matt Arsenault 1d0370872f AMDGPU: Expand flat atomics that may access private memory (#109407) ...

If the runtime flat address resolves to a scratch address,
64-bit atomics do not work correctly. Insert a runtime address
space check (which is quite likely to be uniform) and select between
the non-atomic and real atomic cases.

Consider noalias.addrspace metadata and avoid this expansion when
possible (we also need to consider it to avoid infinitely expanding
after adding the predication code).

2024-10-31 08:08:48 -07:00

629 KiB

Raw Blame History

View Raw