[GitHub] [tvm] vinx13 commented on a diff in pull request #14009: [MetaSchedule] Introduce Async Pipeline in MultiLevelTiling

["vinx13 (via GitHub)" <gi...@apache.org>]

vinx13 commented on code in PR #14009:
URL: https://github.com/apache/tvm/pull/14009#discussion_r1109111683


##########
src/meta_schedule/schedule_rule/multi_level_tiling.cc:
##########
@@ -115,6 +115,7 @@ std::vector<State> MultiLevelTilingNode::ApplySubRules(std::vector<State> states
   states = SubRule(std::move(states), [&](State state) { return TileLoopNest(std::move(state)); });
   states = SubRule(std::move(states), [&](State state) { return AddWriteReuse(std::move(state)); });
   states = SubRule(std::move(states), [&](State state) { return AddReadReuse(std::move(state)); });
+  states = SubRule(std::move(states), [&](State state) { return AddAsyncPipeline(std::move(state)); });

Review Comment:
   need to check target and cuda arch version



-- 
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