[PATCH] D131246: [AMDGPU] SIFixSGPRCopies refactoring

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp:640
+            // them as early as possible
+            !tryChangeVGPRtoSGPRinCopy(MI, TRI, TII)) {
+          // Collect those not changed to try them after VGPR to SGPR copies
----------------
Should not it `continue` if `tryChangeVGPRtoSGPRinCopy` returned true? It will skip the next check then, which is always false.


================
Comment at: llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp:668
+                  MI.isPHI() ? MI.getOperand(MI.getOperandNo(&MO) + 1).getMBB()
+                              : MBB;
+              MachineBasicBlock::iterator PointToInsertCopy =
----------------
Alignment is off.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D131246/new/

https://reviews.llvm.org/D131246