rmuir commented on PR #12311: URL: https://github.com/apache/lucene/pull/12311#issuecomment-1557981841
Working my way thru all the vector similarity functions, I pushed initial stab at the binary euclidean distance to https://github.com/rmuir/vectorbench run it with `java -jar target/vectorbench.jar Square` It uses the same structure as what we did for binary dotproduct and can share the constants with it, if we go with this approach. These integer ones are quick to iterate on as everything is exact and benchmark is also a randomized test case :) Here's my skylake: ``` Benchmark (size) Mode Cnt Score Error Units BinarySquareBenchmark.squareDistanceNew 1024 thrpt 5 6.331 ± 0.121 ops/us BinarySquareBenchmark.squareDistanceOld 1024 thrpt 5 1.548 ± 0.186 ops/us ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
