[ET-VK] Allow clone op to transfer between memory layouts and storage types #6596
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
… types ## Changes As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor. ## Context This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff. Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6596
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 17a8e1f with merge base 1972e69 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D65277710 |
…and storage types" ## Changes As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor. ## Context This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff. Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D65277710 |
…and storage types" ## Changes As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor. ## Context This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff. Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D65277710 |
junpi3
approved these changes
Oct 31, 2024
facebook-github-bot
merged commit 2ee526e
into
gh/SS-JIA/133/base
38 of 41 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
added a commit
that referenced
this pull request
Nov 1, 2024
… types (#6607) Pull Request resolved: #6596 ## Changes As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor. ## Context This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff. ghstack-source-id: 251229412 @exported-using-ghexport Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/) Co-authored-by: Stephen Jia <ssjia@meta.com>
SS-JIA
added a commit
that referenced
this pull request
Nov 1, 2024
* [ET-VK] Allow clone op to transfer between memory layouts and storage types Pull Request resolved: #6596 ## Changes As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor. ## Context This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff. ghstack-source-id: 251229412 @exported-using-ghexport Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/) * [ET-VK] Enable buffer implementation of `aten.linear` Pull Request resolved: #6597 ## Changes As title. Extend the existing buffer implementation of `matmul` to support the linear operator as well. ghstack-source-id: 251229414 @exported-using-ghexport Differential Revision: [D65277712](https://our.internmc.facebook.com/intern/diff/D65277712/) --------- Co-authored-by: Stephen Jia <ssjia@meta.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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):
aten.linear#6597Changes
As title. Extend the functionality of the
aten.cloneoperator to allow transitioning the storage type and memory layout between the input to the output tensor.Context
This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff.
Differential Revision: D65277710