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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
