Fix SVE2 histogram accumulator overflow#4711
Open
AGSaidi wants to merge 1 commit into
Open
Conversation
HIST_count_sve2 reduces symbol counts into 16-bit accumulators, which wrap past 65535. On blocks up to ZSTD_BLOCKSIZE_MAX (128 KB) a symbol can exceed that, wrapping a frequent symbol to a small count and producing a bad (but valid) Huffman table, inflating the block by up to ~60%. Use a saturating add (svqadd) so the count caps at 65535 and the frequency ordering is preserved.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
HIST_count_sve2 reduces symbol counts into 16-bit accumulators, which wrap past 65535. On blocks up to ZSTD_BLOCKSIZE_MAX (128 KB) a symbol can exceed that, wrapping a frequent symbol to a small count and producing a bad (but valid) Huffman table, inflating the block by up to ~60%. Use a saturating add (svqadd) so the count caps at 65535 and the frequency ordering is preserved.