diff options
author | Wenchen Fan <wenchen@databricks.com> | 2016-01-20 15:08:27 -0800 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2016-01-20 15:08:27 -0800 |
commit | f3934a8d656f1668bec065751b2a11411229b6f5 (patch) | |
tree | a353c7b5de468627aeb1c63a673a54cf122db960 /sql | |
parent | 8f90c151878571e20625e2a53561441ec0035dfc (diff) | |
download | spark-f3934a8d656f1668bec065751b2a11411229b6f5.tar.gz spark-f3934a8d656f1668bec065751b2a11411229b6f5.tar.bz2 spark-f3934a8d656f1668bec065751b2a11411229b6f5.zip |
[SPARK-12888][SQL] benchmark the new hash expression
Benchmark it on 4 different schemas, the result:
```
Intel(R) Core(TM) i7-4960HQ CPU 2.60GHz
Hash For simple: Avg Time(ms) Avg Rate(M/s) Relative Rate
-------------------------------------------------------------------------------
interpreted version 31.47 266.54 1.00 X
codegen version 64.52 130.01 0.49 X
```
```
Intel(R) Core(TM) i7-4960HQ CPU 2.60GHz
Hash For normal: Avg Time(ms) Avg Rate(M/s) Relative Rate
-------------------------------------------------------------------------------
interpreted version 4068.11 0.26 1.00 X
codegen version 1175.92 0.89 3.46 X
```
```
Intel(R) Core(TM) i7-4960HQ CPU 2.60GHz
Hash For array: Avg Time(ms) Avg Rate(M/s) Relative Rate
-------------------------------------------------------------------------------
interpreted version 9276.70 0.06 1.00 X
codegen version 14762.23 0.04 0.63 X
```
```
Intel(R) Core(TM) i7-4960HQ CPU 2.60GHz
Hash For map: Avg Time(ms) Avg Rate(M/s) Relative Rate
-------------------------------------------------------------------------------
interpreted version 58869.79 0.01 1.00 X
codegen version 9285.36 0.06 6.34 X
```
Author: Wenchen Fan <wenchen@databricks.com>
Closes #10816 from cloud-fan/hash-benchmark.
Diffstat (limited to 'sql')
-rw-r--r-- | sql/catalyst/src/test/scala/org/apache/spark/sql/HashBenchmark.scala | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/HashBenchmark.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/HashBenchmark.scala new file mode 100644 index 0000000000..184f845b4d --- /dev/null +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/HashBenchmark.scala @@ -0,0 +1,104 @@ +/* + * 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 + +import org.apache.spark.sql.catalyst.encoders.RowEncoder +import org.apache.spark.sql.catalyst.expressions.{Murmur3Hash, UnsafeProjection} +import org.apache.spark.sql.catalyst.expressions.codegen.GenerateSafeProjection +import org.apache.spark.sql.types._ +import org.apache.spark.util.Benchmark + +/** + * Benchmark for the previous interpreted hash function(InternalRow.hashCode) vs the new codegen + * hash expression(Murmur3Hash). + */ +object HashBenchmark { + + def test(name: String, schema: StructType, iters: Int): Unit = { + val numRows = 1024 * 8 + + val generator = RandomDataGenerator.forType(schema, nullable = false).get + val encoder = RowEncoder(schema) + val attrs = schema.toAttributes + val safeProjection = GenerateSafeProjection.generate(attrs, attrs) + + val rows = (1 to numRows).map(_ => + // The output of encoder is UnsafeRow, use safeProjection to turn in into safe format. + safeProjection(encoder.toRow(generator().asInstanceOf[Row])).copy() + ).toArray + + val benchmark = new Benchmark("Hash For " + name, iters * numRows) + benchmark.addCase("interpreted version") { _: Int => + for (_ <- 0L until iters) { + var sum = 0 + var i = 0 + while (i < numRows) { + sum += rows(i).hashCode() + i += 1 + } + } + } + + val getHashCode = UnsafeProjection.create(new Murmur3Hash(attrs) :: Nil, attrs) + benchmark.addCase("codegen version") { _: Int => + for (_ <- 0L until iters) { + var sum = 0 + var i = 0 + while (i < numRows) { + sum += getHashCode(rows(i)).getInt(0) + i += 1 + } + } + } + benchmark.run() + } + + def main(args: Array[String]): Unit = { + val simple = new StructType().add("i", IntegerType) + test("simple", simple, 1024) + + val normal = new StructType() + .add("null", NullType) + .add("boolean", BooleanType) + .add("byte", ByteType) + .add("short", ShortType) + .add("int", IntegerType) + .add("long", LongType) + .add("float", FloatType) + .add("double", DoubleType) + .add("bigDecimal", DecimalType.SYSTEM_DEFAULT) + .add("smallDecimal", DecimalType.USER_DEFAULT) + .add("string", StringType) + .add("binary", BinaryType) + .add("date", DateType) + .add("timestamp", TimestampType) + test("normal", normal, 128) + + val arrayOfInt = ArrayType(IntegerType) + val array = new StructType() + .add("array", arrayOfInt) + .add("arrayOfArray", ArrayType(arrayOfInt)) + test("array", array, 64) + + val mapOfInt = MapType(IntegerType, IntegerType) + val map = new StructType() + .add("map", mapOfInt) + .add("mapOfMap", MapType(IntegerType, mapOfInt)) + test("map", map, 64) + } +} |