llvm/llvm-project
Vedi su GitHubAMDGPU should handle SimplifyDemandedVectorElts for more trivial intrinsics
Open
#131.734 aperta il 18 mar 2025
backend:AMDGPUgood first issuemissed-optimization
Metriche repository
- Star
- (26.378 star)
- Metriche merge PR
- (Merge medio 1g 2h) (1000 PR mergiate in 30 g)
Descrizione
As a follow up to https://github.com/llvm/llvm-project/pull/128647, more intrinsics should be handled in SimplifyDemandedVectorElts.
This includes: Intrinsic::amdgcn_readlane, Intrinsic::amdgcn_update_dpp, Intrinsic::amdgcn_permlane16, Intrinsic::amdgcn_permlanex16, Intrinsic::amdgcn_permlane64 and Intrinsic::amdgcn_mov_dpp8
This is mostly a matter of adding the intrinsics to the switch, some boilerplate to keep the other immediate operands as they are, and adding tests similar to the ones added in #128647