为什么Enumerable.Range比直接yield循环更快？

Question

下面的代码是检查执行相同解决方案的三种不同方式的性能。

    public static void Main(string[] args)
    {
        // for loop
        {
            Stopwatch sw = Stopwatch.StartNew();

            int accumulator = 0;
            for (int i = 1; i <= 100000000; ++i)
            {
                accumulator += i;
            }

            sw.Stop();

            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, accumulator);
        }

        //Enumerable.Range
        {
            Stopwatch sw = Stopwatch.StartNew();

            var ret = Enumerable.Range(1, 100000000).Aggregate(0, (accumulator, n) => accumulator + n);

            sw.Stop();
            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, ret);
        }

        //self-made IEnumerable<int>
        {
            Stopwatch sw = Stopwatch.StartNew();

            var ret = GetIntRange(1, 100000000).Aggregate(0, (accumulator, n) => accumulator + n);

            sw.Stop();
            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, ret);
        }
    }

    private static IEnumerable<int> GetIntRange(int start, int count)
    {
        int end = start + count;

        for (int i = start; i < end; ++i)
        {
            yield return i;
        }
    }
}

结果是：

time = 306; result = 987459712
time = 1301; result = 987459712
time = 2860; result = 987459712

“for循环”并不奇怪。比其他两个解决方案更快，因为Enumerable.Aggregate需要更多的方法调用。然而，“Enumerable.Range”让我感到惊讶。比“自制的IEnumerable”更快。我认为Enumerable.Range比简单的GetIntRange方法有更多的开销。

可能的原因是什么？

Answer 1

Enumerable.Range 为什么要比你自己的 GetIntRange 慢？实际上，如果 Enumerable.Range 被定义为

public static class Enumerable {
    public static IEnumerable<int> Range(int start, int count) {
        var end = start + count;
        for(var current = start; current < end; ++current) {
            yield return current;
        }
    }
}

那么它应该与你自己的 GetIntRange 一样快。这实际上是 Enumerable.Range 的参考实现，没有编译器或程序员的任何技巧。

您可能希望将 GetIntRange 和 System.Linq.Enumerable.Range 与以下实现进行比较（当然，正如Rob指出的那样，在发布模式下编译） 。对于编译器从迭代器块生成的内容，可以稍微优化此实现。

public static class Enumerable {
    public static IEnumerable<int> Range(int start, int count) {
        return new RangeEnumerable(start, count);
    }
    private class RangeEnumerable : IEnumerable<int> {
        private int _Start;
        private int _Count;
        public RangeEnumerable(int start, int count) {
            _Start = start;
            _Count = count;
        }
        public virtual IEnumerator<int> GetEnumerator() {
            return new RangeEnumerator(_Start, _Count);
        }
        IEnumerator IEnumerable.GetEnumerator() {
            return GetEnumerator();
        }
    }
    private class RangeEnumerator : IEnumerator<int> {
        private int _Current;
        private int _End;
        public RangeEnumerator(int start, int count) {
            _Current = start - 1;
            _End = start + count;
        }
        public virtual void Dispose() {
            _Current = _End;
        }
        public virtual void Reset() {
            throw new NotImplementedException();
        }
        public virtual bool MoveNext() {
            ++_Current;
            return _Current < _End;
        }
        public virtual int Current { get { return _Current; } }
        object IEnumerator.Current { get { return Current; } }
    }
}

Answer 2

我的猜测是你在调试器中运行。以下是我的结果，从命令行使用“/ o + / debug-”

构建

time = 142; result = 987459712
time = 1590; result = 987459712
time = 1792; result = 987459712

仍然存在细微差别，但并不是那么明显。迭代器块实现不如定制解决方案那么有效，但它们非常好。

Answer 3

假设这是一个正在运行的发布版本，否则所有比较都会关闭，因为JIT不会平稳运行。

您可以使用反射器查看装配体，看看产量是多少'声明也在扩大。编译器将创建一个类来封装迭代器。也许生成的代码中的内务处理比Enumerable.Range的实现更多，这可能是手工编码的

Answer 4

Reflector输出的细微差别（以及参数检查和内部化的额外水平在这里绝对不相关）。基本代码更像是：

public static IEnumerable<int> Range(int start, int count) {
    for(int current = 0; current < count; ++current) {
        yield return start + current;
    }
}

也就是说，它们代替另一个局部变量，为每个产量应用额外的添加。

我试图对此进行基准测试，但我无法阻止足够的外部进程来获得可理解的结果。我还尝试了两次测试，以忽略JIT编译器的效果，但即使这样也有“有趣”的结果。

以下是我的结果示例：

Run 0:
time = 4149; result = 405000000450000000
time = 25645; result = 405000000450000000
time = 39229; result = 405000000450000000
time = 29872; result = 405000000450000000

time = 4277; result = 405000000450000000
time = 26878; result = 405000000450000000
time = 26333; result = 405000000450000000
time = 26684; result = 405000000450000000

Run 1:
time = 4063; result = 405000000450000000
time = 22714; result = 405000000450000000
time = 34744; result = 405000000450000000
time = 26954; result = 405000000450000000

time = 4033; result = 405000000450000000
time = 26657; result = 405000000450000000
time = 25855; result = 405000000450000000
time = 25031; result = 405000000450000000

Run 2:
time = 4021; result = 405000000450000000
time = 21815; result = 405000000450000000
time = 34304; result = 405000000450000000
time = 32040; result = 405000000450000000

time = 3993; result = 405000000450000000
time = 24779; result = 405000000450000000
time = 29275; result = 405000000450000000
time = 32254; result = 405000000450000000

和代码

using System;
using System.Linq;
using System.Collections.Generic;
using System.Diagnostics;

namespace RangeTests
{
  class TestRange
  {
    public static void Main(string[] args)
    {
      for(int l = 1; l <= 2; ++l)
      {
        const int N = 900000000;
        System.GC.Collect(2);
        // for loop
        {
            Stopwatch sw = Stopwatch.StartNew();

            long accumulator = 0;
            for (int i = 1; i <= N; ++i)
            {
                accumulator += i;
            }

            sw.Stop();

            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, accumulator);
        }
        System.GC.Collect(2);

        //Enumerable.Range
        {
            Stopwatch sw = Stopwatch.StartNew();

            var ret = Enumerable.Range(1, N).Aggregate(0, (long accumulator,int n) => accumulator + n);

            sw.Stop();
            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, ret);
        }
        System.GC.Collect(2);

        //self-made IEnumerable<int>
        {
            Stopwatch sw = Stopwatch.StartNew();

            var ret = GetIntRange(1, N).Aggregate(0, (long accumulator,int n) => accumulator + n);

            sw.Stop();
            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, ret);
        }
        System.GC.Collect(2);

        //self-made adjusted IEnumerable<int>
        {
            Stopwatch sw = Stopwatch.StartNew();

            var ret = GetRange(1, N).Aggregate(0, (long accumulator,int n) => accumulator + n);

            sw.Stop();
            Console.WriteLine("time = {0}; result = {1}", sw.ElapsedMilliseconds, ret);
        }
        System.GC.Collect(2);
        Console.WriteLine();
    } }

    private static IEnumerable<int> GetIntRange(int start, int count)
    {
        int end = start + count;

        for (int i = start; i < end; ++i)
        {
            yield return i;
        }
    }

    private static IEnumerable<int> GetRange(int start, int count)
    {
        for (int i = 0; i < count; ++i)
        {
            yield return start + i;
        }
    }
} }

用

编译

csc.exe -optimize+ -debug- RangeTests.cs