gimgit commented on PR #16827: URL: https://github.com/apache/iceberg/pull/16827#issuecomment-5363530778
Nice — 1.7 GB/op to ~6.7 KB/op from buffering the transpose is a great outcome, and the matched-arm JMH setup (same seed, single invocation) makes the 3-4x curve cost a number reviewers can actually trust. Glad the question was useful. On locality-as-density-variance: that framing makes sense for space-filling curves, and it's a better fit than per-column bounds there. Looking forward to the follow-up issue — happy to compare notes with the linear-order detection in #17504 once it's up. -- 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]
