#17662: Conv2d fix split reader #17936
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
In cases where amount of data that needs to be read is uneven, between first and second reader and in case there are multiple blocks to be read (case when act_block_h_override is used) conv2d would fail with pcc issues. Problem was that offsets for readers between blocks didn't account for potentially different amount of data being read by the other reader.
mywoodstock
approved these changes
Feb 18, 2025
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Outdated suggestions cannot be applied.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.
In cases where amount of data that needs to be read is uneven, between first and second reader and in case there are multiple blocks to be read (case when act_block_h_override is used) conv2d would fail with pcc issues.
Problem was that offsets for readers between blocks didn't account for potentially different amount of data being read by the other reader.
Ticket
Link to Github Issue
Problem description
Provide context for the problem.
What's changed
Now both activation readers (NC, BR) are aware of amount of data read by the other reader, and can properly calculate the offset into the next block they need to read.
Checklist