org.openjdk.jmh.samples.JMHSample_34_SafeLooping Maven / Gradle / Ivy

/*
 * Copyright (c) 2014, Oracle America, Inc.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *  * Redistributions of source code must retain the above copyright notice,
 *    this list of conditions and the following disclaimer.
 *
 *  * Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 *  * Neither the name of Oracle nor the names of its contributors may be used
 *    to endorse or promote products derived from this software without
 *    specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
 * THE POSSIBILITY OF SUCH DAMAGE.
 */
package org.openjdk.jmh.samples;

import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.CompilerControl;
import org.openjdk.jmh.annotations.Fork;
import org.openjdk.jmh.annotations.Measurement;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.annotations.Param;
import org.openjdk.jmh.annotations.Scope;
import org.openjdk.jmh.annotations.Setup;
import org.openjdk.jmh.annotations.State;
import org.openjdk.jmh.annotations.Warmup;
import org.openjdk.jmh.infra.Blackhole;
import org.openjdk.jmh.runner.Runner;
import org.openjdk.jmh.runner.RunnerException;
import org.openjdk.jmh.runner.options.Options;
import org.openjdk.jmh.runner.options.OptionsBuilder;

import java.util.concurrent.TimeUnit;

@State(Scope.Thread)
@Warmup(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Measurement(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
@Fork(3)
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.NANOSECONDS)
public class JMHSample_34_SafeLooping {

    /*
     * JMHSample_11_Loops warns about the dangers of using loops in @Benchmark methods.
     * Sometimes, however, one needs to traverse through several elements in a dataset.
     * This is hard to do without loops, and therefore we need to devise a scheme for
     * safe looping.
     */

    /*
     * Suppose we want to measure how much it takes to execute work() with different
     * arguments. This mimics a frequent use case when multiple instances with the same
     * implementation, but different data, is measured.
     */

    static final int BASE = 42;

    static int work(int x) {
        return BASE + x;
    }

    /*
     * Every benchmark requires control. We do a trivial control for our benchmarks
     * by checking the benchmark costs are growing linearly with increased task size.
     * If it doesn't, then something wrong is happening.
     */

    @Param({"1", "10", "100", "1000"})
    int size;

    int[] xs;

    @Setup
    public void setup() {
        xs = new int[size];
        for (int c = 0; c < size; c++) {
            xs[c] = c;
        }
    }

    /*
     * First, the obviously wrong way: "saving" the result into a local variable would not
     * work. A sufficiently smart compiler will inline work(), and figure out only the last
     * work() call needs to be evaluated. Indeed, if you run it with varying $size, the score
     * will stay the same!
     */

    @Benchmark
    public int measureWrong_1() {
        int acc = 0;
        for (int x : xs) {
            acc = work(x);
        }
        return acc;
    }

    /*
     * Second, another wrong way: "accumulating" the result into a local variable. While
     * it would force the computation of each work() method, there are software pipelining
     * effects in action, that can merge the operations between two otherwise distinct work()
     * bodies. This will obliterate the benchmark setup.
     *
     * In this example, HotSpot does the unrolled loop, merges the $BASE operands into a single
     * addition to $acc, and then does a bunch of very tight stores of $x-s. The final performance
     * depends on how much of the loop unrolling happened *and* how much data is available to make
     * the large strides.
     */

    @Benchmark
    public int measureWrong_2() {
        int acc = 0;
        for (int x : xs) {
            acc += work(x);
        }
        return acc;
    }

    /*
     * Now, let's see how to measure these things properly. A very straight-forward way to
     * break the merging is to sink each result to Blackhole. This will force runtime to compute
     * every work() call in full. (We would normally like to care about several concurrent work()
     * computations at once, but the memory effects from Blackhole.consume() prevent those optimization
     * on most runtimes).
     */

    @Benchmark
    public void measureRight_1(Blackhole bh) {
        for (int x : xs) {
            bh.consume(work(x));
        }
    }

    /*
     * DANGEROUS AREA, PLEASE READ THE DESCRIPTION BELOW.
     *
     * Sometimes, the cost of sinking the value into a Blackhole is dominating the nano-benchmark score.
     * In these cases, one may try to do a make-shift "sinker" with non-inlineable method. This trick is
     * *very* VM-specific, and can only be used if you are verifying the generated code (that's a good
     * strategy when dealing with nano-benchmarks anyway).
     *
     * You SHOULD NOT use this trick in most cases. Apply only where needed.
     */

    @Benchmark
    public void measureRight_2() {
        for (int x : xs) {
            sink(work(x));
        }
    }

    @CompilerControl(CompilerControl.Mode.DONT_INLINE)
    public static void sink(int v) {
        // IT IS VERY IMPORTANT TO MATCH THE SIGNATURE TO AVOID AUTOBOXING.
        // The method intentionally does nothing.
    }


    /*
     * ============================== HOW TO RUN THIS TEST: ====================================
     *
     * You might notice measureWrong_1 does not depend on $size, measureWrong_2 has troubles with
     * linearity, and otherwise much faster than both measureRight_*. You can also see measureRight_2
     * is marginally faster than measureRight_1.
     *
     * You can run this test:
     *
     * a) Via the command line:
     *    $ mvn clean install
     *    $ java -jar target/benchmarks.jar JMHSample_34
     *
     * b) Via the Java API:
     *    (see the JMH homepage for possible caveats when running from IDE:
     *      http://openjdk.java.net/projects/code-tools/jmh/)
     */

    public static void main(String[] args) throws RunnerException {
        Options opt = new OptionsBuilder()
                .include(JMHSample_34_SafeLooping.class.getSimpleName())
                .forks(3)
                .build();

        new Runner(opt).run();
    }

}