Kimahriman commented on code in PR #53468: URL: https://github.com/apache/spark/pull/53468#discussion_r3837364649
########## sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/ArraySetLikeBenchmark.scala: ########## @@ -0,0 +1,85 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.execution.benchmark + +import org.apache.spark.benchmark.Benchmark +import org.apache.spark.sql.functions._ + +/** + * Benchmark for measuring perf of array set-like operations. + * To run this benchmark: + * {{{ + * 1. without sbt: + * bin/spark-submit --class <this class> --jars <spark core test jar> <sql core test jar> + * 2. build/sbt "sql/Test/runMain <this class>" + * 3. generate result: + * SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/Test/runMain <this class>" + * Results will be written to "benchmarks/ArraySetLikeBenchmark-results.txt". + * }}} + */ +object ArraySetLikeBenchmark extends SqlBasedBenchmark { + private val N = 1000L + + override def runBenchmarkSuite(mainArgs: Array[String]): Unit = { + val range1 = lit((1 to 20000).map(x => Array(x, x)).toArray) + val range2 = lit((10001 to 30000).map(x => Array(x, x)).toArray) + + + val arrayDistinctBenchmark = new Benchmark("Array Distinct", N, output = output) + arrayDistinctBenchmark.addCase("array_distinct") { _ => Review Comment: Benchmark results got lost in the last PR description update, re-added -- 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]
