[llvm] [AMDGPU] Move WWM register pre-allocation to during regalloc (PR #70618)

Christudasan Devadasan via llvm-commits llvm-commits at lists.llvm.org
Sun Nov 5 23:44:46 PST 2023


cdevadas wrote:

> > Skipping AMDGPU::SI_SPILL_S32_TO_VGPR & AMDGPU::SI_RESTORE_S32_FROM_VGPR here is the right thing. Because they are meant to be allocated during RA. BTW, why SI_RESTORE_S32_FROM_VGPR isn't included here?
> 
> SI_RESTORE_S32_FROM_VGPR is not included here because it does not define any VGPRs, so WWM pre-allocate will ignore it as-is.

Ok.

https://github.com/llvm/llvm-project/pull/70618


More information about the llvm-commits mailing list