You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by GitBox <gi...@apache.org> on 2020/12/13 15:45:39 UTC

[GitHub] [arrow] Dandandan edited a comment on pull request #8900: ARROW-10810: [Rust] Improve comparison kernels performance

Dandandan edited a comment on pull request #8900:
URL: https://github.com/apache/arrow/pull/8900#issuecomment-744024794


   Cool to know / read @alamb to see that we are getting closer to "optimal" performance on a single thread. The PRs I create are also based on profiling DataFusion, showing that it has "real world" improvement on those changes as well besides getting good result on the benchmarks. I hope they are useful for influxdb as well.
   
   The docs / presentation are looking very interesting, it probably isn't recorded?
   
   As mentioned there is for some datatypes (like strings) there is some overhead still related to the `assert!`s that I reverted for now. Probably the bitmap code also could be improved which could close the gap. I think it is cool to compare it against a "native" rust implementation.


----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org