stevomitric opened a new pull request, #56744: URL: https://github.com/apache/spark/pull/56744
### What changes were proposed in this pull request? Add `TimestampNanosBenchmark`, comparing the microsecond timestamp path against the nanosecond timestamp types `TIMESTAMP_NTZ(p)` / `TIMESTAMP_LTZ(p)` (p in [7, 9]) across cast, string parse/format, hashing, sort, group-by, MIN/MAX, datetime functions, and Parquet/ORC read/write. ### Why are the changes needed? To quantify the per-row overhead of the 16-byte `TimestampNanosVal` carrier vs the 8-byte micros `Long`, and to surface known nanos gaps (no radix sort prefix; row-based-only vectorized Parquet read). ### Does this PR introduce _any_ user-facing change? No, test-only. ### How was this patch tested? N/A (benchmark). Results regenerated via the `Run benchmarks` GitHub Action. ### Was this patch authored or co-authored using generative AI tooling? Generated-by: Claude Code (Claude Opus 4.8) -- 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]
