LuciferYang commented on code in PR #55853: URL: https://github.com/apache/spark/pull/55853#discussion_r3247491976
########## sql/core/benchmarks/ParquetVectorUpdaterBenchmark-jdk21-results.txt: ########## @@ -7,13 +7,13 @@ AMD EPYC 7763 64-Core Processor Identity Updaters: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ BooleanUpdater 0 0 0 17004.4 0.1 1.0X -ByteUpdater (INT32 -> Byte) 0 0 0 3758.6 0.3 0.2X -ShortUpdater (INT32 -> Short) 1 1 0 1678.4 0.6 0.1X -IntegerUpdater 0 0 0 10276.1 0.1 0.6X Review Comment: display precision artifact — not a real zero. The per-row cost for these updaters is below 1 ns, so 1M rows × ~0.1 ns finishes in roughly 0.1 ms per iteration, which rounds down to 0 at the ms column's resolution. The real signal lives in Rate(M/s) and Per Row(ns). It's a pre-existing display quirk of the Benchmark framework ... -- 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]
