Improve compression ratio of levels 3 & 4 #4171
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
terrelln
approved these changes
Oct 16, 2024
lib/compress/zstd_double_fast.c
Outdated
Comment on lines
266
to
268
| offset = (U32)(ip-matchl1); | ||
| while (((ip>anchor) & (matchl1>prefixLowest)) && (ip[-1] == matchl1[-1])) { ip--; matchl1--; mLength++; } /* catch up */ | ||
| goto _match_found; |
There was a problem hiding this comment.
Could this code be merged with the code in lines 273-275?
We could set matchs0 = matchl1, and then just fallthrough to the code on line 273. Though we might want to rename some variables.
The compression ratio benefits are small but consistent, i.e. always positive. On `silesia.tar` corpus, this modification saves ~75 KB at level 3. The measured speed cost is negligible, i.e. below noise level, between 0 and -1%.
was transferred from circleci, but was only triggered on push into dev, i.e. after pull request is merged.
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Outdated suggestions cannot be applied.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.
Following #4170 , there were a few ideas I wanted to test for the general compression performance of level 3, aka
dfaststrategy.The one proposed in this PR is consistently positive.
It feels retrospectively obvious: select the supplemental "long" match candidate only if it's effectively longer.
On
silesia.tarcorpus, this modification saves ~75 KB at level 3.And thankfully, the measured speed cost is negligible, below noise level (between 0 and -1% depending on measurements).