[Optimization] Use int32 instead of int64 for indexing tensor wrappers.#167
Draft
daniellegillai wants to merge 11 commits into
Draft
[Optimization] Use int32 instead of int64 for indexing tensor wrappers.#167daniellegillai wants to merge 11 commits into
daniellegillai wants to merge 11 commits into
Conversation
…tion to operators accordingly
zacharyvincze
requested changes
Jun 26, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Operators can see a speedup when image indexing and stride calculations are done in int32 rather than int64.
Technical Details
Templatized the ImageWrapper, BorderWrapper, and InterpolationWrapper classes so that the type they use for index/stride calculations can be controlled to be int32_t or int64_t. Currently all operators but CvtColor have a hard limit, checked with validation, that they must fit in int32 (they will not fall back to int64_t otherwise). CvtColor is adaptive: will choose int32 for the wrapper type if it can fit, and otherwise falls back to int64_t.
Tests
Existing ctests all still pass.
Benchmark with batch size 128 on Resize throws an exception because it is too large to fit with int32.