Fix reduction + () + multi-level reduction optimization (#111781) #111839
Conversation
Summary: In #111122, an optimization is introduced for reduction() + () + multi-level reduction. In this case, we make a multi-level reduction first-level reduction ranges the same as the previous reduction ranges so that the Inductor has better chances to fuse the first reduction and the first-level reduction of the multi-level reduction kernel together. There is a corner case that the multi-level reduction kernel has `keepdim=True`. In this case, ranges of the multi-level reduction kernel is not empty, and the dim info needs to be used to create the inner loader of the first-level reduction kernel. To keep the logic simple, for now we simply disable optimization when `keepdim=True`. imported-using-ghimport Test Plan: Imported from OSS Reviewed By: malfet Differential Revision: D50544876 Pulled By: ipiszy
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/111839
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 903763c with merge base 185e762 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D50544876 |
This PR needs a
|
Summary: In #111122, an optimization is introduced for reduction() + () + multi-level reduction. In this case, we make a multi-level reduction first-level reduction ranges the same as the previous reduction ranges so that the Inductor has better chances to fuse the first reduction and the first-level reduction of the multi-level reduction kernel together. There is a corner case that the multi-level reduction kernel has `keepdim=True`. In this case, ranges of the multi-level reduction kernel is not empty, and the dim info needs to be used to create the inner loader of the first-level reduction kernel. To keep the logic simple, for now we simply disable optimization when `keepdim=True`. imported-using-ghimport Test Plan: Imported from OSS Reviewed By: malfet Differential Revision: D50544876 Pulled By: ipiszy
|
This pull request was exported from Phabricator. Differential Revision: D50544876 |
2 participants
Summary:
In #111122, an optimization is introduced for reduction() + () + multi-level reduction. In this case, we make a multi-level reduction first-level reduction ranges the same as the previous reduction ranges so that the Inductor has better chances to fuse the first reduction and the first-level reduction of the multi-level reduction kernel together.
There is a corner case that the multi-level reduction kernel has
keepdim=True. In this case, ranges of the multi-level reduction kernel is not empty, and the dim info needs to be used to create the inner loader of the first-level reduction kernel. To keep the logic simple, for now we simply disable optimization whenkeepdim=True.imported-using-ghimport
Test Plan: Imported from OSS
Reviewed By: malfet
Differential Revision: D50544876
Pulled By: ipiszy
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler