[ET-VK] 7/n Split dispatches between multiple command buffers. Split execute dispatch into multiple commands based on dispatch count. #12530
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
…execute dispatch into multiple commands based on dispatch count. Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
This was referenced Jul 15, 2025
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12530
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Unrelated FailureAs of commit 98c3a0f with merge base 6485e4f ( NEW FAILURES - The following jobs have failed:
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 Jul 15, 2025
facebook-github-bot
added
the
CLA Signed
This was referenced Jul 15, 2025
trivedivivek
added a commit
that referenced
this pull request
Jul 15, 2025
…execute dispatch into multiple commands based on dispatch count. Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) ghstack-source-id: 296448618 Pull Request resolved: #12530
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Jul 16, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 ghstack-source-id: 296562132 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Jul 31, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 ghstack-source-id: 296562132 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Aug 3, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 This diff, splits the execute dispatch into multiple commands based on the dispatch count. This allows for concurrent CPU and GPU execution. The modifications involve adding a counter `encoded_node_count` to track the number of encoded nodes and submitting a new command buffer to the GPU every 64 nodes. ghstack-source-id: 300371355 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Aug 4, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 This diff, splits the execute dispatch into multiple commands based on the dispatch count. This allows for concurrent CPU and GPU execution. The modifications involve adding a counter `encoded_node_count` to track the number of encoded nodes and submitting a new command buffer to the GPU every 64 nodes. ghstack-source-id: 300461757 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
SS-JIA
approved these changes
Aug 4, 2025
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Aug 4, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 This diff, splits the execute dispatch into multiple commands based on the dispatch count. This allows for concurrent CPU and GPU execution. The modifications involve adding a counter `encoded_node_count` to track the number of encoded nodes and submitting a new command buffer to the GPU every 64 nodes. ghstack-source-id: 300533803 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
trivedivivek
added
the
release notes: vulkan
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Aug 4, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 This diff, splits the execute dispatch into multiple commands based on the dispatch count. This allows for concurrent CPU and GPU execution. The modifications involve adding a counter `encoded_node_count` to track the number of encoded nodes and submitting a new command buffer to the GPU every 64 nodes. ghstack-source-id: 300544775 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
…ers. Split execute dispatch into multiple commands based on dispatch count." Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/) [ghstack-poisoned]
trivedivivek
added a commit
that referenced
this pull request
Aug 4, 2025
…execute dispatch into multiple commands based on dispatch count. Pull Request resolved: #12530 This diff, splits the execute dispatch into multiple commands based on the dispatch count. This allows for concurrent CPU and GPU execution. The modifications involve adding a counter `encoded_node_count` to track the number of encoded nodes and submitting a new command buffer to the GPU every 64 nodes. ghstack-source-id: 300616853 @exported-using-ghexport Differential Revision: [D78360039](https://our.internmc.facebook.com/intern/diff/D78360039/)
|
This pull request was exported from Phabricator. Differential Revision: D78360039 |
facebook-github-bot
merged commit 00779dd
into
gh/trivedivivek/127/base
100 of 105 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
trivedivivek
added a commit
that referenced
this pull request
Aug 5, 2025
…execute dispatch into multiple commands based on dispatch count. (#13118) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #12530 by @trivedivivek ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/orig @diff-train-skip-merge Co-authored-by: Vivek Trivedi <[email protected]>
agrima1304
pushed a commit
to agrima1304/executorch
that referenced
this pull request
Aug 26, 2025
…execute dispatch into multiple commands based on dispatch count. (pytorch#13118) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: pytorch#12530 by @trivedivivek ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/127/orig @diff-train-skip-merge 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
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):
Differential Revision: D78360039