Rich-T-kid opened a new issue, #23921: URL: https://github.com/apache/datafusion/issues/23921
Same single-element `create_hashes` pattern here, but this one is on the streaming hot path (called once per appended group). Since consecutive `append_val` calls usually see the same `dict_values` array, caching the batch's hashes keyed on `Arc::as_ptr(dict.values())` would reduce this to one vectorized hash pass per batch. Fine as a follow-up. _Originally posted by @zhuqi-lucas in https://github.com/apache/datafusion/pull/23187#discussion_r3655353799_ -- 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]
