[PATCH] D120813: AMDGPU: Skip folding REG_SEQUENCE if found unknown regclasses for its users.

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIFoldOperands.cpp:1602
   unsigned OpIdx = Op - &UseMI->getOperand(0);
+  if (TII->isUnknownRegClass(*UseMI, OpIdx))
+    return false;
----------------
cdevadas wrote:
> foad wrote:
> > You could just use TargetInstrInfo::getRegClass(InstDesc, OpIdx, TRI, MF) instead of TRI->getRegClass and it would do all these checks for you already.
> We can't use that equivalent of `getRegClass` here. The call to `adjustAllocatableRegClass` inside it would change AV classes to V thereby disabling the folding in almost all valid cases.
> 
The call to `adjustAllocatableRegClass` is in the AMDGPU-specific getOpRegClass, not in the generic getRegClass.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D120813/new/

https://reviews.llvm.org/D120813