jianxind commented on pull request #7314: URL: https://github.com/apache/arrow/pull/7314#issuecomment-645294042
The numbers looks good for sparse part on the benchmark device also now, even though locally my device can get more better speed up thanks to bigger L2/L3 size. I don't know if it's a good direction considering compiler can do less things on the bitmap based. @emkornfield And others, thoughts? ---------------------------------------------------------------- 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