[llvm] [AMDGPU] Reimplement PreRARematStage stage for the GCNSchedStrategy. Early-preview, WIP. (PR #72505)

Valery Pykhtin via llvm-commits llvm-commits at lists.llvm.org
Mon Jul 20 08:13:29 PDT 2026

Previous message: [llvm] [AMDGPU] Re-fold masked hi16 pack into v_or_b32_sdwa (PR #210735)
Next message: [llvm] [SSAUpdaterBulk] Fix PHI handling in self-loop cases to prevent spurious intermediate PHIs (PR #196934)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

https://github.com/vpykhtin closed https://github.com/llvm/llvm-project/pull/72505

Previous message: [llvm] [AMDGPU] Re-fold masked hi16 pack into v_or_b32_sdwa (PR #210735)
Next message: [llvm] [SSAUpdaterBulk] Fix PHI handling in self-loop cases to prevent spurious intermediate PHIs (PR #196934)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list