[PATCH] D76253: [AMDGPU] Print DWARF register numbers in AMDGPUInstPrinter

[Tony Tye via Phabricator via llvm-commits]

t-tye accepted this revision.
t-tye added a comment.
This revision is now accepted and ready to land.

Minor suggestion in comment.



================
Comment at: llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp:37
+  // wave32/wave64 where using the physical register name is ambiguous: if we
+  // write e.g. `.cfi_undefined s0` we lose information about the wavefront
+  // size which we need to encode the register in the final DWARF. Ideally we
----------------
v0 would be a better example than s0 as the vector registers have wave32 and wave64 DWARF versions, but the scalar registers are the same for both modes.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76253/new/

https://reviews.llvm.org/D76253