You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "junrushao (via GitHub)" <gi...@apache.org> on 2023/02/28 08:57:06 UTC
[GitHub] [tvm] junrushao commented on a diff in pull request #14143: [Fix][MetaSchedule] Fix redundant stages in async pipeline for mlt
junrushao commented on code in PR #14143:
URL: https://github.com/apache/tvm/pull/14143#discussion_r1119747707
##########
src/meta_schedule/schedule_rule/multi_level_tiling.cc:
##########
@@ -96,7 +96,9 @@ void MultiLevelTilingNode::InitializeWithTuneContext(const TuneContext& context)
if (std::stoi(sm) >= 80) {
// only stage = 4 & 5 is tested. all integer that is bigger than 2
// is theoretically feasible, but no guarantee for great performance.
- this->stages.insert(this->stages.end(), {4, 5});
+ this->stages = {4, 5};
+ } else {
+ this->stages.clear();
Review Comment:
let's set the default value of `this->stages` to empty vector
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org