llvm-project
3db4f5b0 - AMDGPU: Refine gfx950 xdl-write-vgpr hazard cases (#117285)

Commit
345 days ago
AMDGPU: Refine gfx950 xdl-write-vgpr hazard cases (#117285) The 2-pass XDL write VGPR, read by non-XDL SGEMM/DGEMM case was 1 wait state overly conservative. Previously, for gfx940, the XDL/non-XDL cases happened to have the same number of cycles in all cases. Now the XDL consumer case has an additional state for 2 pass sources.
Author
Parents
Loading