|
| 1 | +/* |
| 2 | + * Licensed to the Apache Software Foundation (ASF) under one |
| 3 | + * or more contributor license agreements. See the NOTICE file |
| 4 | + * distributed with this work for additional information |
| 5 | + * regarding copyright ownership. The ASF licenses this file |
| 6 | + * to you under the Apache License, Version 2.0 (the |
| 7 | + * "License"); you may not use this file except in compliance |
| 8 | + * with the License. You may obtain a copy of the License at |
| 9 | + * |
| 10 | + * http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | + * |
| 12 | + * Unless required by applicable law or agreed to in writing, |
| 13 | + * software distributed under the License is distributed on an |
| 14 | + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 15 | + * KIND, either express or implied. See the License for the |
| 16 | + * specific language governing permissions and limitations |
| 17 | + * under the License. |
| 18 | + */ |
| 19 | + |
| 20 | +package org.apache.spark.sql.benchmark |
| 21 | + |
| 22 | +case class ComparisonExprConfig( |
| 23 | + name: String, |
| 24 | + query: String, |
| 25 | + extraCometConfigs: Map[String, String] = Map.empty) |
| 26 | + |
| 27 | +/** |
| 28 | + * Comprehensive benchmark for Comet comparison and predicate expressions. To run this benchmark: |
| 29 | + * {{{ |
| 30 | + * SPARK_GENERATE_BENCHMARK_FILES=1 make benchmark-org.apache.spark.sql.benchmark.CometComparisonExpressionBenchmark |
| 31 | + * }}} |
| 32 | + * Results will be written to "spark/benchmarks/CometComparisonExpressionBenchmark-**results.txt". |
| 33 | + */ |
| 34 | +object CometComparisonExpressionBenchmark extends CometBenchmarkBase { |
| 35 | + |
| 36 | + private val comparisonExpressions = List( |
| 37 | + ComparisonExprConfig("equal_to", "SELECT c_int = c_int2 FROM parquetV1Table"), |
| 38 | + ComparisonExprConfig("not_equal_to", "SELECT c_int != c_int2 FROM parquetV1Table"), |
| 39 | + ComparisonExprConfig("less_than", "SELECT c_int < c_int2 FROM parquetV1Table"), |
| 40 | + ComparisonExprConfig("less_than_or_equal", "SELECT c_int <= c_int2 FROM parquetV1Table"), |
| 41 | + ComparisonExprConfig("greater_than", "SELECT c_int > c_int2 FROM parquetV1Table"), |
| 42 | + ComparisonExprConfig("greater_than_or_equal", "SELECT c_int >= c_int2 FROM parquetV1Table"), |
| 43 | + ComparisonExprConfig("equal_null_safe", "SELECT c_int <=> c_int2 FROM parquetV1Table"), |
| 44 | + ComparisonExprConfig("is_null", "SELECT c_int IS NULL FROM parquetV1Table"), |
| 45 | + ComparisonExprConfig("is_not_null", "SELECT c_int IS NOT NULL FROM parquetV1Table"), |
| 46 | + ComparisonExprConfig("is_nan_float", "SELECT isnan(c_float) FROM parquetV1Table"), |
| 47 | + ComparisonExprConfig("is_nan_double", "SELECT isnan(c_double) FROM parquetV1Table"), |
| 48 | + ComparisonExprConfig("and", "SELECT (c_int > 0) AND (c_int2 < 100) FROM parquetV1Table"), |
| 49 | + ComparisonExprConfig("or", "SELECT (c_int > 0) OR (c_int2 < 100) FROM parquetV1Table"), |
| 50 | + ComparisonExprConfig("not", "SELECT NOT (c_int > 0) FROM parquetV1Table"), |
| 51 | + ComparisonExprConfig( |
| 52 | + "in_list", |
| 53 | + "SELECT c_int IN (1, 10, 100, 1000, 10000) FROM parquetV1Table"), |
| 54 | + ComparisonExprConfig( |
| 55 | + "not_in_list", |
| 56 | + "SELECT c_int NOT IN (1, 10, 100, 1000, 10000) FROM parquetV1Table")) |
| 57 | + |
| 58 | + override def runCometBenchmark(mainArgs: Array[String]): Unit = { |
| 59 | + val values = 1024 * 1024 |
| 60 | + |
| 61 | + runBenchmarkWithTable("Comparison expression benchmarks", values) { v => |
| 62 | + withTempPath { dir => |
| 63 | + withTempTable("parquetV1Table") { |
| 64 | + prepareTable( |
| 65 | + dir, |
| 66 | + spark.sql(s""" |
| 67 | + SELECT |
| 68 | + CASE WHEN value % 10 = 0 THEN NULL ELSE CAST((value % 100000) - 50000 AS INT) END AS c_int, |
| 69 | + CASE WHEN value % 10 = 1 THEN NULL ELSE CAST((value % 1000) AS INT) END AS c_int2, |
| 70 | + CASE |
| 71 | + WHEN value % 50 = 2 THEN NULL |
| 72 | + WHEN value % 50 = 3 THEN CAST('NaN' AS FLOAT) |
| 73 | + ELSE CAST((value % 10000) / 100.0 AS FLOAT) |
| 74 | + END AS c_float, |
| 75 | + CASE |
| 76 | + WHEN value % 50 = 4 THEN NULL |
| 77 | + WHEN value % 50 = 5 THEN CAST('NaN' AS DOUBLE) |
| 78 | + ELSE CAST((value % 10000) / 100.0 AS DOUBLE) |
| 79 | + END AS c_double |
| 80 | + FROM $tbl |
| 81 | + """)) |
| 82 | + |
| 83 | + comparisonExpressions.foreach { config => |
| 84 | + runExpressionBenchmark(config.name, v, config.query, config.extraCometConfigs) |
| 85 | + } |
| 86 | + } |
| 87 | + } |
| 88 | + } |
| 89 | + } |
| 90 | +} |
0 commit comments