Replace XXH64 with a simplified version #346
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
This function gives the same result as regular xxh64(), but the difference is that it only works on single 64-bit values. Mostly the "bit mixing" part of xxh64 (functions finalize()/avalanche()) is left. This performs a little bit better than calling the original function on an 8-byte slice because the compiler does not fully inline everything (finalize() remains a function call). This speeds up index generation by a couple of percent.
|
Approved. |
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Outdated suggestions cannot be applied.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.
This function gives the same result as regular XXH64(), but with the difference that it only works on single 64-bit values, which makes it possible to reduce it to just a couple of lines; mostly the "bit mixing" part (functions finalize()/avalanche()) is left.
This performs a little bit better than calling the original function on an 8-byte slice because the compiler (at least GCC) does not fully inline the original function (finalize() remains a function call).
This speeds up index generation by a couple of percent: 163 are reduced to 159 seconds for CHM13.