[ET-VK] Migrate workgroup API for trivial cases #4061
Closed
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
This will allow us to override local workgroup sizes with #4046. ## Before ``` vTensorPtr t_out = graph.get_tensor(out); api::utils::uvec3 global_size = t_out->image_extents(); api::utils::uvec3 local_size = adaptive_work_group_size(global_size); graph.execute_nodes().emplace_back(new ExecuteNode( ..., global_size, local_size, ..., ); ``` ## After ``` graph.execute_nodes().emplace_back(new ExecuteNode( ..., graph.create_global_wg_size(out), graph.create_local_wg_size(out), ..., ); ``` Note we do not migrate cases where the global size is nontrivial (MatMul, Linear, Conv1D, Repeat) or the image isn't a ValueRef (MaxPool2D, NativeLayerNorm). We should first align on an API design for those cases. Differential Revision: [D59011492](https://our.internmc.facebook.com/intern/diff/D59011492/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4061
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 810ea6e with merge base 34fd767 ( NEW FAILURE - The following job has 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: D59011492 |
jorgep31415
added a commit
that referenced
this pull request
Jun 25, 2024
This will allow us to override local workgroup sizes with #4046. ## Before ``` vTensorPtr t_out = graph.get_tensor(out); api::utils::uvec3 global_size = t_out->image_extents(); api::utils::uvec3 local_size = adaptive_work_group_size(global_size); graph.execute_nodes().emplace_back(new ExecuteNode( ..., global_size, local_size, ..., ); ``` ## After ``` graph.execute_nodes().emplace_back(new ExecuteNode( ..., graph.create_global_wg_size(out), graph.create_local_wg_size(out), ..., ); ``` Note we do not migrate cases where the global size is nontrivial (MatMul, Linear, Conv1D, Repeat) or the image isn't a ValueRef (MaxPool2D, NativeLayerNorm). We should first align on an API design for those cases. Differential Revision: [D59011492](https://our.internmc.facebook.com/intern/diff/D59011492/) ghstack-source-id: 231549021 Pull Request resolved: #4061
nathanaelsee
approved these changes
Jun 25, 2024
|
This pull request has been merged in 1ba8946. |
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):
This will allow us to override local workgroup sizes with #4046.
Before
After
Note we do not migrate cases where the global size is nontrivial (MatMul, Linear, Conv1D, Repeat) or the image isn't a ValueRef (MaxPool2D, NativeLayerNorm). We should first align on an API design for those cases.
Differential Revision: D59011492