[ET-VK] Add pass to remove copy ops #7325
Merged
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
## Context This diff prepares Vulkan to handle dim order operators. For more context, see #4873 Since Vulkan has its own internal representation of memory layout, these ops are handled by simply remove explicit memory layout transition operators from the graph and let the memory metadata tagging pass insert the necessary memory layout transitions. A new pass is added to remove such operators, largely based on QNN's `RemoveRedundancy` pass. Differential Revision: [D67180898](https://our.internmc.facebook.com/intern/diff/D67180898/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7325
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 69d6d71 with merge base 8460d42 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
SS-JIA
added a commit
that referenced
this pull request
Dec 13, 2024
## Context This diff prepares Vulkan to handle dim order operators. For more context, see #4873 Since Vulkan has its own internal representation of memory layout, these ops are handled by simply remove explicit memory layout transition operators from the graph and let the memory metadata tagging pass insert the necessary memory layout transitions. A new pass is added to remove such operators, largely based on QNN's `RemoveRedundancy` pass. Differential Revision: [D67180898](https://our.internmc.facebook.com/intern/diff/D67180898/) ghstack-source-id: 258092214 Pull Request resolved: #7325
|
This pull request was exported from Phabricator. Differential Revision: D67180898 |
jorgep31415
approved these changes
Dec 13, 2024
facebook-github-bot
merged commit 4a653db
into
gh/SS-JIA/156/base
42 of 48 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
added a commit
that referenced
this pull request
Dec 16, 2024
## Context This diff prepares Vulkan to handle dim order operators. For more context, see #4873 Since Vulkan has its own internal representation of memory layout, these ops are handled by simply remove explicit memory layout transition operators from the graph and let the memory metadata tagging pass insert the necessary memory layout transitions. A new pass is added to remove such operators, largely based on QNN's `RemoveRedundancy` pass. Differential Revision: [D67180898](https://our.internmc.facebook.com/intern/diff/D67180898/) ghstack-source-id: 258092214 Pull Request resolved: #7325 Co-authored-by: Stephen Jia <[email protected]>
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):
Context
This diff prepares Vulkan to handle dim order operators. For more context, see #4873
Since Vulkan has its own internal representation of memory layout, these ops are handled by simply remove explicit memory layout transition operators from the graph and let the memory metadata tagging pass insert the necessary memory layout transitions.
A new pass is added to remove such operators, largely based on QNN's
RemoveRedundancypass.Differential Revision: D67180898