diff options
| author | Carl Ritson <carl.ritson@amd.com> | 2021-03-18 09:31:39 +0900 |
|---|---|---|
| committer | Carl Ritson <carl.ritson@amd.com> | 2021-03-18 10:00:41 +0900 |
| commit | 1a4bc3aba360522983692ac933b2b6daaa5f5082 (patch) | |
| tree | 7bbb4ccdfdce24e00ec64abe427b86ccabad52ce /llvm/lib/Object/XCOFFObjectFile.cpp | |
| parent | 5a8d5a2859d9bb056083b343588a2d87622e76a2 (diff) | |
| download | llvm-1a4bc3aba360522983692ac933b2b6daaa5f5082.zip llvm-1a4bc3aba360522983692ac933b2b6daaa5f5082.tar.gz llvm-1a4bc3aba360522983692ac933b2b6daaa5f5082.tar.bz2 | |
[AMDGPU] Avoid unnecessary graph visits during WQM marking
Avoid revisiting nodes with the same set of defined lanes by
using a unified visited set which integrates lanes into the key.
This retains the intent of the original code by still revisiting
a subgraph if a different set of lanes is defined and hence
marking might progress differently.
Note: default size of the visited set has been confirmed to
cover >99% of invocations in large array of test shaders.
Reviewed By: piotr
Differential Revision: https://reviews.llvm.org/D98772
Diffstat (limited to 'llvm/lib/Object/XCOFFObjectFile.cpp')
0 files changed, 0 insertions, 0 deletions