[xnnpack][lite-int][graph-build] graph passes and op checking #87128
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
Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 170497840 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/87128
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit c25dc7e: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
mcr229
added a commit
that referenced
this pull request
Oct 17, 2022
Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 170497840 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! ghstack-source-id: 170652463 Pull Request resolved: #87128
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 17, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 170666250 ghstack-source-id: 170666250 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 18, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 170826268 ghstack-source-id: 170826268 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 19, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 170955754 ghstack-source-id: 170955754 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 20, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 171097281 ghstack-source-id: 171097281 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 21, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 171231761 ghstack-source-id: 171231761 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 24, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 171364139 ghstack-source-id: 171364139 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
…ing" Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! [ghstack-poisoned]
mcr229
added a commit
that referenced
this pull request
Oct 24, 2022
Pull Request resolved: #87128 Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. ghstack-source-id: 171415455 ghstack-source-id: 171415455 Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)!
Contributor
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Collaborator
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 |
Contributor
|
Hey @mcr229. |
kulinseth
pushed a commit
to kulinseth/pytorch
that referenced
this pull request
Nov 5, 2022
…h#87128) Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! Pull Request resolved: pytorch#87128 Approved by: https://github.com/salilsdesai
kulinseth
pushed a commit
to kulinseth/pytorch
that referenced
this pull request
Dec 10, 2022
…h#87128) Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation. This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us. The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable. Differential Revision: [D39838338](https://our.internmc.facebook.com/intern/diff/D39838338/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D39838338/)! Pull Request resolved: pytorch#87128 Approved by: https://github.com/salilsdesai
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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):
Beginning of building the xnnpack graph from the torchscript IR. We first massage the torchscript graph using a few graph passes that perform things such as unused self argument removal and constant propagation.
This also performs tracing for us so that the model does not have to be prepped by tracing before being lowered by us.
The other check we perform is through the torchscript IR to identify any nodes that are not lowerable/supported, and throwing an error to spit out the specific nodes that are not lowerable.
Differential Revision: D39838338
NOTE FOR REVIEWERS: This PR has internal Meta-specific changes or comments, please review them on Phabricator!