LabelEncoder kernel creation improvement #16516
Merged
Conversation
This file contains 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
Signed-off-by: Aditya Goel <[email protected]>
adityagoel4512
changed the title
adityagoel4512
changed the title
|
Closes #16575 |
adityagoel4512
changed the title
|
@baijumeswani not sure if you are the right person to ask, but would it be possible to get a review on this? |
baijumeswani
reviewed
Jul 3, 2023
|
/azp run Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline, Linux QNN CI Pipeline |
|
/azp run Windows CPU CI Pipeline, Windows GPU CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows ARM64 QNN CI Pipeline, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, orttraining-ortmodule-distributed, ONNX Runtime React Native CI Pipeline |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
Azure Pipelines successfully started running 8 pipeline(s). |
|
@baijumeswani looks like the CI has passed |
baijumeswani
approved these changes
Jul 5, 2023
|
Thank you for your contribution. |
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Outdated suggestions cannot be applied.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.
Description
This PR updates the initialisation of the
_mapinLabelEncoder_2to be more memory efficient.std::unordered_maptoabsl::flat_hash_map. The latter has a more compact layout and doesn't have the overhead of maintaining reference validity likestd::unordered_map, which is a feature we do not need here since we only initialise_maponce at creation and then perform lookups duingcompute. Abseil is already used extensively within onnxruntime.Motivation and Context
For very large lookups, the LabelEncoder's kernel creation can require more RAM than necessary. These simple changes in
_mapinitialisation improve initialisation speed and memory allocated.