[ET-VK] Modify quantized linear naive shader to linearly dispatch work to improve performance. #10116
Conversation
…k to improve performance. This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10116
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d63d430 with merge base 047bbc7 ( 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: D72862490 |
…ispatch work to improve performance." This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D72862490 |
…ispatch work to improve performance." This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D72862490 |
…ispatch work to improve performance." This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D72862490 |
…ispatch work to improve performance." This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D72862490 |
…ispatch work to improve performance." This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D72862490 |
…k to improve performance. Pull Request resolved: pytorch/executorch#10116 This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance. ghstack-source-id: 278469605 @exported-using-ghexport Differential Revision: [D72862490](https://our.internmc.facebook.com/intern/diff/D72862490/)
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
Stack from ghstack (oldest at bottom):
This diff changes naive quantized linear mat mul op to use push constant instead of uniform buffers and change dispatch pattern to linear to improve performance.
Differential Revision: D72862490