Pranshu-S commented on PR #16706: URL: https://github.com/apache/lucene/pull/16706#issuecomment-5895940104
> It also [adds a few cycles](https://github.com/apache/lucene/blob/020802ff07053f50ed215244a90f3696cef498a3/lucene/core/src/java/org/apache/lucene/util/packed/DirectReader.java#L320-L322) on the hot path compared to the [32-bit lookup](https://github.com/apache/lucene/blob/020802ff07053f50ed215244a90f3696cef498a3/lucene/core/src/java/org/apache/lucene/util/packed/DirectReader.java#L381) -- could you also share search latency from your benchmark? Agree, we could possibly round up the bytes like from 12 -> 16 or 22 -> 24 for reducing these CPU instructions but can benchmark independently what suits this setup. I am running the latency benchmarks, ended up doing a large cycle which crashed in between. I'll share the results in a while -- 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]
