jasperjiaguo commented on PR #9336: URL: https://github.com/apache/pinot/pull/9336#issuecomment-1242636876
> At a glance not using the stream API to convert the iterators to bitmaps and using the array overload instead of the iterator overload should improve the results. I seem to recall BufferFastAggregation.and being more efficient for larger numbers of bitmaps, so it may not shine in this particular context. Modified to use array and blackhole. Updated the results. Briefly looked at the `workShyAnd` and it seems to use the similar idea of intersecting the containers prior to full intersection to minimize the range. It could be the extra preparation work is not worth it when number of bitmaps are samll. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
