[ET-VK][BE][ez] vTensor cleanup 2/N - remove discard_and_reallocate API
#5422
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
… API ## Context Remove the unused `discard_and_reallocate()` API. The purpose of this AP is to allow a `vTensor` instance to request a new memory allocation when being resized to a larger size than what the current memory allocation can support. This was originally intended to support unbounded dynamic shapes in the ExecuTorch Vulkan delegate, but it is unlikely that this functionality will ever be used. The reason is that re-allocating memory would require re-encoding the command buffer, which goes against the execution philosophy of the Vulkan delegate (encode command buffer once, submit repeatedly). Differential Revision: [D62878649](https://our.internmc.facebook.com/intern/diff/D62878649/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5422
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 496dbb8 with merge base e8a557c ( 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: D62878649 |
This was referenced Sep 17, 2024
Closed
jorgep31415
approved these changes
Sep 17, 2024
|
This pull request has been merged in 92adb94. |
lucylq
pushed a commit
that referenced
this pull request
Sep 17, 2024
Summary: Pull Request resolved: #5422 ## Context Remove the unused `discard_and_reallocate()` API. The purpose of this AP is to allow a `vTensor` instance to request a new memory allocation when being resized to a larger size than what the current memory allocation can support. This was originally intended to support unbounded dynamic shapes in the ExecuTorch Vulkan delegate, but it is unlikely that this functionality will ever be used. The reason is that re-allocating memory would require re-encoding the command buffer, which goes against the execution philosophy of the Vulkan delegate (encode command buffer once, submit repeatedly). ghstack-source-id: 243061031 exported-using-ghexport Reviewed By: jorgep31415 Differential Revision: D62878649 fbshipit-source-id: e293fe2dfcbbec8c615370a370db14424b971369
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):
vectypes #5423discard_and_reallocateAPI #5422vTensorandvTensorStoragein cpp file #5421Context
Remove the unused
discard_and_reallocate()API. The purpose of this AP is to allow avTensorinstance to request a new memory allocation when being resized to a larger size than what the current memory allocation can support.This was originally intended to support unbounded dynamic shapes in the ExecuTorch Vulkan delegate, but it is unlikely that this functionality will ever be used. The reason is that re-allocating memory would require re-encoding the command buffer, which goes against the execution philosophy of the Vulkan delegate (encode command buffer once, submit repeatedly).
Differential Revision: D62878649