parser.c: Use SWAR to skip consecutive spaces #886
Merged
Conversation
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
Closes: ruby#881 If we encounter a newline, it is likely that the document is pretty printed, hence that the newline is followed by multiple spaces. In such case we can use SWAR to count up to eight consecutive spaces at once. ``` == Parsing activitypub.json (58160 bytes) ruby 3.4.6 (2025-09-16 revision dbd83256b1) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- after 1.118k i/100ms Calculating ------------------------------------- after 11.223k (± 0.7%) i/s (89.10 μs/i) - 57.018k in 5.080522s Comparison: before: 10834.4 i/s after: 11223.4 i/s - 1.04x faster == Parsing twitter.json (567916 bytes) ruby 3.4.6 (2025-09-16 revision dbd83256b1) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- after 118.000 i/100ms Calculating ------------------------------------- after 1.188k (± 1.0%) i/s (841.62 μs/i) - 6.018k in 5.065355s Comparison: before: 1094.8 i/s after: 1188.2 i/s - 1.09x faster == Parsing citm_catalog.json (1727030 bytes) ruby 3.4.6 (2025-09-16 revision dbd83256b1) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- after 58.000 i/100ms Calculating ------------------------------------- after 570.506 (± 3.7%) i/s (1.75 ms/i) - 2.900k in 5.091529s Comparison: before: 419.6 i/s after: 570.5 i/s - 1.36x faster == Parsing float parsing (2251051 bytes) ruby 3.4.6 (2025-09-16 revision dbd83256b1) +YJIT +PRISM [arm64-darwin24] Warming up -------------------------------------- after 22.000 i/100ms Calculating ------------------------------------- after 212.010 (± 1.9%) i/s (4.72 ms/i) - 1.078k in 5.086885s Comparison: before: 189.4 i/s after: 212.0 i/s - 1.12x faster ``` Co-Authored-By: Scott Myron <[email protected]>
byroot
force-pushed
the
parser-whitespace-switch
branch
from
9cd6375 to
b3fd7b2
Compare
Contributor
|
Thank you for the improvements! |
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.
Closes: #881
If we encounter a newline, it is likely that the document is pretty printed, hence that the newline is followed by multiple spaces.
In such case we can use SWAR to count up to eight consecutive spaces at once.
FYI: @samyron