emkornfield commented on pull request #6985: URL: https://github.com/apache/arrow/pull/6985#issuecomment-630572790
> So the BMI2 instructions incur a large slowdown here (even catastrophic with gcc). I would expect bad numbers with GCC 7.5 since we lose autovectorization and use BMI2. Agree that clang-8 numbers still look pretty bad on AMD. I guess this PR will have to wait until we can do runtime dispatch :( ---------------------------------------------------------------- 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: us...@infra.apache.org
