Skip to content

[ET-VK] Store unique ptr to Tensor in Value instead of inlined tensor object, to reduce Value struct size from 448 to 80 bytes. #7145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Conversation

trivedivivek
Copy link
Contributor

@trivedivivek trivedivivek commented Dec 2, 2024

… object, to reduce Value struct size from 448 to 80 bytes.

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Dec 2, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7145

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit cee5e89 with merge base 63238ab (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D66655991

trivedivivek added a commit that referenced this pull request Dec 2, 2024
… object, to reduce Value struct size from 448 to 80 bytes.

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

ghstack-source-id: 256050917
Pull Request resolved: #7145
…ined tensor object, to reduce Value struct size from 448 to 80 bytes."

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D66655991

@trivedivivek trivedivivek added the release notes: backends [DO NOT USE] Changes to any of the backend delegates label Dec 2, 2024
…ined tensor object, to reduce Value struct size from 448 to 80 bytes."

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D66655991

…ined tensor object, to reduce Value struct size from 448 to 80 bytes."

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D66655991

…ined tensor object, to reduce Value struct size from 448 to 80 bytes."

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D66655991

kirklandsign pushed a commit that referenced this pull request Dec 9, 2024
… object, to reduce Value struct size from 448 to 80 bytes.

Pull Request resolved: #7145

This diff aims to reduce the size of the Value struct in the Executorch Vulkan runtime by storing a unique pointer to the Tensor object instead of an inlined tensor object. This change reduces the size of the Value struct from 448 bytes to 80 bytes, which can improve performance and reduce memory usage.
ghstack-source-id: 256911524
@exported-using-ghexport

Differential Revision: [D66655991](https://our.internmc.facebook.com/intern/diff/D66655991/)

---------

Co-authored-by: Vivek Trivedi <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported release notes: backends [DO NOT USE] Changes to any of the backend delegates
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants