Fix issue w/ DML batched readback size#28680
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
Copilot encountered an error: Your billing is not configured or you have Copilot licenses from multiple standalone organizations or enterprises. To use premium requests, select a billing entity via the GitHub site, under Settings > Copilot > Features.
adrastogi
marked this pull request as ready for review
May 27, 2026 15:55
fdwr
previously approved these changes
Jun 4, 2026
Wrap HResultToStatus return per intrafile convention (one parameter per line) and indent the ReadbackFromGpu call inside the ORT_TRY block. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes DML batched GPU readback sizing to avoid uint32_t aggregate wraparound, which could undersize the D3D12 readback. Adds checked size_t accumulation, safer readback validation, and regression coverage for overflow cases.
Motivation and Context
DML batched readback previously accumulated output tensor byte sizes in uint32_t, so multiple individually valid outputs could wrap the aggregate size used to allocate the D3D12 readback heap. This change tightens the sizing path and keeps the readback allocation consistent with the per-tensor copy sizes.