[llvm] [AMDGPU] Fix implicit $vcc operands after parsing MIR (PR #87781)
Jay Foad via llvm-commits
llvm-commits at lists.llvm.org
Fri Apr 5 07:03:07 PDT 2024
================
@@ -586,7 +586,7 @@ name: dpp_reg_sequence_both_combined
tracksRegLiveness: true
body: |
bb.0:
- liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+ liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vcc_lo
----------------
jayfoad wrote:
In wave32 mode we reserve $vcc, so implicit uses of $vcc did not need a corresponding def. Now these uses are being converted to $vcc_lo, which is not reserved, so we do need to supply a def.
https://github.com/llvm/llvm-project/pull/87781
More information about the llvm-commits
mailing list