[PyTorch] AOTI: cache dtypes and device types at DSO load #111820
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Calling the `aoti_torch_{device_type,dtype}` functions on
each iteration can impose high costs on overhead-bound CPU models
because they can't be inlined across a DSO boundary. If we call them
on load, we can use simple load instructions at run time.
Differential Revision: [D50563682](https://our.internmc.facebook.com/intern/diff/D50563682/)
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/111820
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 252d891 with merge base e9422b1 ( BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Oct 23, 2023
swolchok
added a commit
that referenced
this pull request
Oct 23, 2023
Calling the `aoti_torch_{device_type,dtype}` functions on
each iteration can impose high costs on overhead-bound CPU models
because they can't be inlined across a DSO boundary. If we call them
on load, we can use simple load instructions at run time.
Differential Revision: [D50563682](https://our.internmc.facebook.com/intern/diff/D50563682/)
ghstack-source-id: 204997329
Pull Request resolved: #111820
swolchok
requested review from
chenyang78 and
desertfire
and removed request for
desertfire
|
@pytorchbot merge |
Merge failedReason: This PR needs a If not, please add the To add a label, you can comment to pytorchbot, for example For more information, see Details for Dev Infra teamRaised by workflow job |
desertfire
approved these changes
Oct 24, 2023
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
xuhancn
pushed a commit
to xuhancn/pytorch
that referenced
this pull request
Nov 7, 2023
…1820) Calling the `aoti_torch_{device_type,dtype}` functions on each iteration can impose high costs on overhead-bound CPU models because they can't be inlined across a DSO boundary. If we call them on load, we can use simple load instructions at run time. Differential Revision: [D50563682](https://our.internmc.facebook.com/intern/diff/D50563682/) Pull Request resolved: pytorch#111820 Approved by: https://github.com/chenyang78, https://github.com/desertfire ghstack dependencies: pytorch#111815, pytorch#111816
Skylion007
pushed a commit
to Skylion007/pytorch
that referenced
this pull request
Nov 14, 2023
…1820) Calling the `aoti_torch_{device_type,dtype}` functions on each iteration can impose high costs on overhead-bound CPU models because they can't be inlined across a DSO boundary. If we call them on load, we can use simple load instructions at run time. Differential Revision: [D50563682](https://our.internmc.facebook.com/intern/diff/D50563682/) Pull Request resolved: pytorch#111820 Approved by: https://github.com/chenyang78, https://github.com/desertfire ghstack dependencies: pytorch#111815, pytorch#111816
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Calling the
aoti_torch_{device_type,dtype}functions oneach iteration can impose high costs on overhead-bound CPU models
because they can't be inlined across a DSO boundary. If we call them
on load, we can use simple load instructions at run time.
Differential Revision: D50563682
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler