[ET-VK][Op Redesign][5/n] Merge StagingNode into ExecuteNode #2260
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
We dispose of `StagingNode` in favor of functions `add_staging_to_tensor_node()` and `add_tensor_to_staging_node()`, which each create an `ExecuteNode`. Hence, we fulfill our goal of making `ExecuteNode` a final class. These `add_X_node()` are not an `OpFunction` since staging is not an operator; its purpose is specific to starting and ending Vulkan execution. Note that we can't remove `encode_copy_to_vtensor()` as it's still used in ArithmeticPrepack. The prepack refactor is next. Differential Revision: [D54445787](https://our.internmc.facebook.com/intern/diff/D54445787/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2260
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d08f6e0 with merge base 566209d ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D54445787 |
This was referenced Mar 4, 2024
SS-JIA
approved these changes
Mar 5, 2024
|
This pull request has been merged in b2862ea. |
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Outdated suggestions cannot be applied.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):
We dispose of
StagingNodein favor of functionsadd_staging_to_tensor_node()andadd_tensor_to_staging_node(), which each create anExecuteNode. Hence, we fulfill our goal of makingExecuteNodea final class. Theseadd_X_node()are not anOpFunctionsince staging is not an operator; its purpose is specific to starting and ending Vulkan execution.Note that we can't remove
encode_copy_to_vtensor()as it's still used in ArithmeticPrepack. The prepack refactor is next.Differential Revision: D54445787