net 4中有一个新的内置解决方案——IStructuralEquatable

static bool ByteArrayCompare(byte[] a1, byte[] a2) 
{
    return StructuralComparisons.StructuralEqualityComparer.Equals(a1, a2);
}

我想到了许多显卡内置的块传输加速方法。但是这样你就必须按字节复制所有的数据，所以如果你不想在非托管和依赖硬件的代码中实现你的整个逻辑，这对你没有多大帮助……

Another way of optimization similar to the approach shown above would be to store as much of your data as possible in a long[] rather than a byte[] right from the start, for example if you are reading it sequentially from a binary file, or if you use a memory mapped file, read in data as long[] or single long values. Then, your comparison loop will only need 1/8th of the number of iterations it would have to do for a byte[] containing the same amount of data. It is a matter of when and how often you need to compare vs. when and how often you need to access the data in a byte-by-byte manner, e.g. to use it in an API call as a parameter in a method that expects a byte[]. In the end, you only can tell if you really know the use case...

受到ArekBulski发布的EqualBytesLongUnrolled方法的启发，我确定了一个附加优化的解决方案。在我的实例中，数组中的数组差异往往在数组的尾部附近。在测试中，我发现当这种情况发生在大型数组中时，能够以相反的顺序比较数组元素使这种解决方案比基于memcmp的解决方案获得了巨大的性能提升。下面是解决方案:

public enum CompareDirection { Forward, Backward }

private static unsafe bool UnsafeEquals(byte[] a, byte[] b, CompareDirection direction = CompareDirection.Forward)
{
    // returns when a and b are same array or both null
    if (a == b) return true;

    // if either is null or different lengths, can't be equal
    if (a == null || b == null || a.Length != b.Length)
        return false;

    const int UNROLLED = 16;                // count of longs 'unrolled' in optimization
    int size = sizeof(long) * UNROLLED;     // 128 bytes (min size for 'unrolled' optimization)
    int len = a.Length;
    int n = len / size;         // count of full 128 byte segments
    int r = len % size;         // count of remaining 'unoptimized' bytes

    // pin the arrays and access them via pointers
    fixed (byte* pb_a = a, pb_b = b)
    {
        if (r > 0 && direction == CompareDirection.Backward)
        {
            byte* pa = pb_a + len - 1;
            byte* pb = pb_b + len - 1;
            byte* phead = pb_a + len - r;
            while(pa >= phead)
            {
                if (*pa != *pb) return false;
                pa--;
                pb--;
            }
        }

        if (n > 0)
        {
            int nOffset = n * size;
            if (direction == CompareDirection.Forward)
            {
                long* pa = (long*)pb_a;
                long* pb = (long*)pb_b;
                long* ptail = (long*)(pb_a + nOffset);
                while (pa < ptail)
                {
                    if (*(pa + 0) != *(pb + 0) || *(pa + 1) != *(pb + 1) ||
                        *(pa + 2) != *(pb + 2) || *(pa + 3) != *(pb + 3) ||
                        *(pa + 4) != *(pb + 4) || *(pa + 5) != *(pb + 5) ||
                        *(pa + 6) != *(pb + 6) || *(pa + 7) != *(pb + 7) ||
                        *(pa + 8) != *(pb + 8) || *(pa + 9) != *(pb + 9) ||
                        *(pa + 10) != *(pb + 10) || *(pa + 11) != *(pb + 11) ||
                        *(pa + 12) != *(pb + 12) || *(pa + 13) != *(pb + 13) ||
                        *(pa + 14) != *(pb + 14) || *(pa + 15) != *(pb + 15)
                    )
                    {
                        return false;
                    }
                    pa += UNROLLED;
                    pb += UNROLLED;
                }
            }
            else
            {
                long* pa = (long*)(pb_a + nOffset);
                long* pb = (long*)(pb_b + nOffset);
                long* phead = (long*)pb_a;
                while (phead < pa)
                {
                    if (*(pa - 1) != *(pb - 1) || *(pa - 2) != *(pb - 2) ||
                        *(pa - 3) != *(pb - 3) || *(pa - 4) != *(pb - 4) ||
                        *(pa - 5) != *(pb - 5) || *(pa - 6) != *(pb - 6) ||
                        *(pa - 7) != *(pb - 7) || *(pa - 8) != *(pb - 8) ||
                        *(pa - 9) != *(pb - 9) || *(pa - 10) != *(pb - 10) ||
                        *(pa - 11) != *(pb - 11) || *(pa - 12) != *(pb - 12) ||
                        *(pa - 13) != *(pb - 13) || *(pa - 14) != *(pb - 14) ||
                        *(pa - 15) != *(pb - 15) || *(pa - 16) != *(pb - 16)
                    )
                    {
                        return false;
                    }
                    pa -= UNROLLED;
                    pb -= UNROLLED;
                }
            }
        }

        if (r > 0 && direction == CompareDirection.Forward)
        {
            byte* pa = pb_a + len - r;
            byte* pb = pb_b + len - r;
            byte* ptail = pb_a + len;
            while(pa < ptail)
            {
                if (*pa != *pb) return false;
                pa++;
                pb++;
            }
        }
    }

    return true;
}

如果你不反对这样做，你可以导入j#程序集“vjslib.dll”并使用它的数组。= (byte[]， byte[])方法…

如果有人嘲笑你，不要怪我……

编辑:为了它的价值，我使用Reflector来反汇编代码，下面是它的样子:

public static bool equals(sbyte[] a1, sbyte[] a2)
{
  if (a1 == a2)
  {
    return true;
  }
  if ((a1 != null) && (a2 != null))
  {
    if (a1.Length != a2.Length)
    {
      return false;
    }
    for (int i = 0; i < a1.Length; i++)
    {
      if (a1[i] != a2[i])
      {
        return false;
      }
    }
    return true;
  }
  return false;
}

我使用附带的。net 4.7发布版本做了一些测量，没有附带调试器。我认为人们一直在使用错误的度量，因为如果你关心这里的速度，你所关心的是计算两个字节数组是否相等需要多长时间。即以字节为单位的吞吐量。

StructuralComparison :              4.6 MiB/s
for                  :            274.5 MiB/s
ToUInt32             :            263.6 MiB/s
ToUInt64             :            474.9 MiB/s
memcmp               :           8500.8 MiB/s

正如你所看到的，没有比memcmp更好的方法了，而且它快了几个数量级。简单的for循环是次优选择。我仍然不明白为什么微软不能简单地包含一个缓冲区。比较方法。

[Program.cs]:

using System;
using System.Collections;
using System.Collections.Generic;
using System.Diagnostics;
using System.Linq;
using System.Runtime.InteropServices;
using System.Text;
using System.Threading.Tasks;

namespace memcmp
{
    class Program
    {
        static byte[] TestVector(int size)
        {
            var data = new byte[size];
            using (var rng = new System.Security.Cryptography.RNGCryptoServiceProvider())
            {
                rng.GetBytes(data);
            }
            return data;
        }

        static TimeSpan Measure(string testCase, TimeSpan offset, Action action, bool ignore = false)
        {
            var t = Stopwatch.StartNew();
            var n = 0L;
            while (t.Elapsed < TimeSpan.FromSeconds(10))
            {
                action();
                n++;
            }
            var elapsed = t.Elapsed - offset;
            if (!ignore)
            {
                Console.WriteLine($"{testCase,-16} : {n / elapsed.TotalSeconds,16:0.0} MiB/s");
            }
            return elapsed;
        }

        [DllImport("msvcrt.dll", CallingConvention = CallingConvention.Cdecl)]
        static extern int memcmp(byte[] b1, byte[] b2, long count);

        static void Main(string[] args)
        {
            // how quickly can we establish if two sequences of bytes are equal?

            // note that we are testing the speed of different comparsion methods

            var a = TestVector(1024 * 1024); // 1 MiB
            var b = (byte[])a.Clone();

            // was meant to offset the overhead of everything but copying but my attempt was a horrible mistake... should have reacted sooner due to the initially ridiculous throughput values...
            // Measure("offset", new TimeSpan(), () => { return; }, ignore: true);
            var offset = TimeZone.Zero

            Measure("StructuralComparison", offset, () =>
            {
                StructuralComparisons.StructuralEqualityComparer.Equals(a, b);
            });

            Measure("for", offset, () =>
            {
                for (int i = 0; i < a.Length; i++)
                {
                    if (a[i] != b[i]) break;
                }
            });

            Measure("ToUInt32", offset, () =>
            {
                for (int i = 0; i < a.Length; i += 4)
                {
                    if (BitConverter.ToUInt32(a, i) != BitConverter.ToUInt32(b, i)) break;
                }
            });

            Measure("ToUInt64", offset, () =>
            {
                for (int i = 0; i < a.Length; i += 8)
                {
                    if (BitConverter.ToUInt64(a, i) != BitConverter.ToUInt64(b, i)) break;
                }
            });

            Measure("memcmp", offset, () =>
            {
                memcmp(a, b, a.Length);
            });
        }
    }
}

如果您正在寻找一个非常快速的字节数组相等比较器，我建议您看看STSdb Labs的这篇文章:字节数组相等比较器。它提供了byte[]数组相等比较的一些最快的实现，并进行了性能测试和总结。

你也可以关注这些实现:

bigendianbytearraycompararer -快速字节[]数组从左到右的比较器(BigEndian) bigendianbytearrayequalitycompararer - -快速字节[]从左到右的相等比较器(BigEndian) 从右到左的快速字节数组比较器(LittleEndian) littleendianbytearrayequalitycompararer -快速字节[]从右向左的相等比较器(LittleEndian)