Omega359 commented on PR #20588: URL: https://github.com/apache/datafusion/pull/20588#issuecomment-3993175192
That is interesting. I ran the benchmark on a m7i.4xlarge which is an Intel Sapphire Rapids machine. I'm curious why we're seeing it on cloud machines but not on your m4 mac. L2 cache is shared iirc on m4 max which might be a reason for the difference. I guess running benchmarks on cloud hardware is worth it considering that most implementations of DF will run on server grade hardware, not consumer - even though the consumer may be faster in some cases -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
