[PATCH] D98614: [AMDGPU] Fix shortfalls in WQM marking
Carl Ritson via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Mar 15 05:40:30 PDT 2021
critson marked an inline comment as done.
critson added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp:365
+ // Find next predecessor to process
+ unsigned Idx = 0;
+ auto PI = MBB->pred_begin() + NextPredIdx;
----------------
piotr wrote:
> To keep the original behaviour, you also need to adjust Idx here and assign it to NextPredIdx, because Idx is used after the for loop in line 377, right?
Yes, I noticed that immediately after pushing this diff.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D98614/new/
https://reviews.llvm.org/D98614
More information about the llvm-commits
mailing list