Dandandan commented on PR #15931: URL: https://github.com/apache/datafusion/pull/15931#issuecomment-2848098062
The main speedup I am expecting in e2e benchmarks is query 27 of clickbench, which has some mixed ascii / utf8 data and uses a `LENGTH` function. Local runs don't show a very large diff (around 6%) - profiling shows a larger diff from ~15% to ~3% of samples in do_count_chars (i.e. `.chars() A large part from the speedup in the micro benchmark seems to come the faster array creation (collect into Vec instead of PrimitiveBuilder). -- 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...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
