Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/13065#discussion_r88139065 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/MiscBenchmark.scala --- @@ -124,12 +124,124 @@ class MiscBenchmark extends BenchmarkBase { } benchmark.run() - /** + /* model name : Westmere E56xx/L56xx/X56xx (Nehalem-C) collect limit: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------- collect limit 1 million 833 / 1284 1.3 794.4 1.0X collect limit 2 millions 3348 / 4005 0.3 3193.3 0.2X */ } + + ignore("generate explode") { + val N = 1 << 24 + runBenchmark("generate explode array", N) { + val df = sparkSession.range(N).selectExpr( + "id as key", + "array(rand(), rand(), rand(), rand(), rand()) as values") + df.selectExpr("key", "explode(values) value").count() + } + + /* + Java HotSpot(TM) 64-Bit Server VM 1.8.0_92-b14 on Mac OS X 10.11.6 + Intel(R) Core(TM) i7-4980HQ CPU @ 2.80GHz + + generate explode array: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative + ------------------------------------------------------------------------------------------------ + generate explode array wholestage off 6920 / 7129 2.4 412.5 1.0X + generate explode array wholestage on 623 / 646 26.9 37.1 11.1X --- End diff -- Done
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org