[llvm] [AMDGPU] Automatic conversion from wave32 to wave64 (PR #137376)

[via llvm-commits]

================
@@ -174,6 +177,9 @@ extern char &SIShrinkInstructionsLegacyID;
 void initializeSIFixSGPRCopiesLegacyPass(PassRegistry &);
 extern char &SIFixSGPRCopiesLegacyID;
 
+void initializeAMDGPUConvertWaveSizeLegacyPass(PassRegistry &);
+extern char &AMDGPUConvertWaveSizeLegacyID;
----------------
alex-t wrote:

The opt pipeline for sure as it works on the IR - not MIR. The method above was added for Legacy PM.

https://github.com/llvm/llvm-project/pull/137376