friendlymatthew commented on PR #7808: URL: https://github.com/apache/arrow-rs/pull/7808#issuecomment-3017457757
Hi, I was thinking about reducing randomness in our benchmarks. I refactored the benches to use pseudo-random number generators. Plus, we precompute the string table before our runs. Here are the updated benchmark results. We still observe a general improvement: <img width="932" alt="Screenshot 2025-06-29 at 9 27 23 PM" src="https://github.com/user-attachments/assets/d50fe350-da39-40ec-977d-4622fc2a68bd"; /> <img width="911" alt="Screenshot 2025-06-29 at 9 27 28 PM" src="https://github.com/user-attachments/assets/3d51fe53-006e-4181-b16c-2d2785a70516"; /> Variant building with the same object schemas observe a regression, but once again, the much larger improvements to the other flow makes me not too concerned about it. -- 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...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
