[PATCH] D34291: [AMDGPU] Fix illegal shrink of V_SUBB_U32 and V_ADDC_U32

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: lib/Target/AMDGPU/SIShrinkInstructions.cpp:95
       case AMDGPU::V_SUBB_U32_e64:
+        if (TII->getNamedOperand(MI, AMDGPU::OpName::src1)->isImm())
+          return false;
----------------
Can you add a test using a frame index and global address, those should have the same issue


Repository:
  rL LLVM

https://reviews.llvm.org/D34291