[llvm] [AMDGPU] Skip VGPR deallocation for waveslot limited kernels (PR #112765)

Jay Foad via llvm-commits llvm-commits at lists.llvm.org
Mon Oct 21 02:23:37 PDT 2024


https://github.com/jayfoad approved this pull request.

I haven't tried to measure the performance impact of this myself, but the implementation LGTM.

https://github.com/llvm/llvm-project/pull/112765


More information about the llvm-commits mailing list