alamb opened a new pull request, #7979: URL: https://github.com/apache/arrow-rs/pull/7979
This PR is designed to test @jhorstmann 's question on https://github.com/apache/arrow-rs/pull/7962 from @zhuqi-lucas https://github.com/apache/arrow-rs/pull/7962#discussion_r2224772631: > Is this implementation somehow more performant than using the existing BitIndexIterator and casting its items to u32? The only difference I see is in the masking of the lowest bit, ^= 1 << bit_pos vs &= self.curr - 1, but I think llvm would know that those are equivalent. If it makes a difference, then we should adjust BitIndexIterator the same way. I made a PR based on https://github.com/apache/arrow-rs/pull/7962 and changed the code to use the existing `BitIndexIterator` and will run the same benchmarks on this one to see how it compares -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
