pitrou commented on PR #50629: URL: https://github.com/apache/arrow/pull/50629#issuecomment-6060292109
Here are direct links to the latest benchmark runs for convenience: * https://conbench.arrow-dev.org/compare/runs/535bca2b44634da4809039c790f895d1...a330ea940e6d42eaa75612ed057603d4/ * https://conbench.arrow-dev.org/compare/runs/d12db8f72ebd457ab34378aa869b60e4...5b85c7acabbd43ccb5a62ef7e1a2036a/ * https://conbench.arrow-dev.org/compare/runs/2bb0e5ee503240e689927cf59753353c...4ddff73f446546729fa91978e7af994b/ * https://conbench.arrow-dev.org/compare/runs/ab65f1bce8874d1f817ef416fe1f1549...4700e6382758453ab0aa663c24514da0/ Some speedups are truly massive (Float16 reading between 3x and 10x faster). The R high-level `file-read` benchmark on the Fannie Mae dataset is up to 30% faster. On some real-world Parquet files, I get file read speedups from PyArrow up to 2x faster locally. -- 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]
