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

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

Needs a new testcase that failed to select



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp:2018
+    if (DstBank == AMDGPU::VGPRRegBank && InsBank == AMDGPU::SGPRRegBank)
+      InReg = B.buildCopy(MRI.getType(InReg), InReg).getReg(0);
+    InsRegs.push_back(InReg);
----------------
I don't understand how this came to change the bank of an already assigned register. The bank should already be correct here? Why isn't the problem earlier in the initial bank selection?


Repository:
  rG LLVM Github Monorepo

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

https://reviews.llvm.org/D98515