[PATCH] D98515: [AMDGPU][GlobalISel] Stop foldInsertEltToCmpSelect from changing reg banks

[Mirko Brkusanin via Phabricator via llvm-commits]

mbrkusanin marked an inline comment as not done.
mbrkusanin added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp:1989
+    auto InsertPt = B.getInsertPt();
+    B.setInstr(MI);
+    Register Copy = B.buildCopy(MRI.getType(Reg), Reg).getReg(0);
----------------
arsenm wrote:
> setInstrAndDebugLoc
> 
> Isn't this set where you want it to be already? Can you just avoid all the iterator changes?
If we set reg banks before creating select we can avoid iterator changes.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98515/new/

https://reviews.llvm.org/D98515