Speed up the branchless UTF-8 decoder by removing !len #7
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Outdated suggestions cannot be applied.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 your post, you say: "Adding that !len is actually somewhat costly,
though I couldn’t figure out why."
My suspicion was that it is because the "!" operator would essentially
behave like a branch, returning 1 if the input is 0 and 0 otherwise.
So, my idea was to copy the table of lengths you have and create another
one for "error lengths" to get that same effect (0 when it's OK and 1
when there is an error, to ensure that it moves forward at least one
byte, as mentioned).
The throughput went up from 504 MB/s to 557 MB/s on my machine.