Files
llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
Alexis Engelke 01571f1b4a [CodeGen] Drop uses of BranchInst (#186391)
Largely a straight-forward replacement with occasional simplifcations.

For AMDGPU, I assumed that unconditional branches are always uniform and
therefore "simplified"/changed AMDGPUAnnotateUniformValues to only
annotate conditional branches.

Target-specific FastISel only selects conditional branches,
unconditional branches are already handled by the non-target-specific
code.
2026-03-13 21:51:38 +00:00

4.7 KiB