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...

简单的回答是:

    public bool Compare(byte[] b1, byte[] b2)
    {
        return Encoding.ASCII.GetString(b1) == Encoding.ASCII.GetString(b2);
    }

通过这种方式，您可以使用优化的. net字符串比较来进行字节数组比较，而不需要编写不安全的代码。这是它如何在后台完成的:

private unsafe static bool EqualsHelper(String strA, String strB)
{
    Contract.Requires(strA != null);
    Contract.Requires(strB != null);
    Contract.Requires(strA.Length == strB.Length);

    int length = strA.Length;

    fixed (char* ap = &strA.m_firstChar) fixed (char* bp = &strB.m_firstChar)
    {
        char* a = ap;
        char* b = bp;

        // Unroll the loop

        #if AMD64
            // For the AMD64 bit platform we unroll by 12 and
            // check three qwords at a time. This is less code
            // than the 32 bit case and is shorter
            // pathlength.

            while (length >= 12)
            {
                if (*(long*)a     != *(long*)b)     return false;
                if (*(long*)(a+4) != *(long*)(b+4)) return false;
                if (*(long*)(a+8) != *(long*)(b+8)) return false;
                a += 12; b += 12; length -= 12;
            }
       #else
           while (length >= 10)
           {
               if (*(int*)a != *(int*)b) return false;
               if (*(int*)(a+2) != *(int*)(b+2)) return false;
               if (*(int*)(a+4) != *(int*)(b+4)) return false;
               if (*(int*)(a+6) != *(int*)(b+6)) return false;
               if (*(int*)(a+8) != *(int*)(b+8)) return false;
               a += 10; b += 10; length -= 10;
           }
       #endif

        // This depends on the fact that the String objects are
        // always zero terminated and that the terminating zero is not included
        // in the length. For odd string sizes, the last compare will include
        // the zero terminator.
        while (length > 0)
        {
            if (*(int*)a != *(int*)b) break;
            a += 2; b += 2; length -= 2;
        }

        return (length <= 0);
    }
}

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;
}

对于那些关心顺序的人(即希望你的memcmp返回一个int而不是什么都没有)，. net Core 3.0(以及。net Standard 2.1也就是。net 5.0)将包括一个Span.SequenceCompareTo(…)扩展方法(加上一个Span.SequenceEqualTo)，可以用来比较两个ReadOnlySpan<T>实例(其中T: IComparable<T>)。

在最初的GitHub提案中，讨论了与跳转表计算的方法比较，将字节[]读为长[]，SIMD使用，以及对CLR实现的memcmp的p/调用。

继续向前，这应该是您比较字节数组或字节范围的首选方法(对于. net Standard 2.1 api，应该使用Span<byte>而不是byte[])，并且它足够快，您应该不再关心优化它(不，尽管在名称上有相似之处，但它的性能不像可怕的Enumerable.SequenceEqual那样糟糕)。

#if NETCOREAPP3_0_OR_GREATER
// Using the platform-native Span<T>.SequenceEqual<T>(..)
public static int Compare(byte[] range1, int offset1, byte[] range2, int offset2, int count)
{
    var span1 = range1.AsSpan(offset1, count);
    var span2 = range2.AsSpan(offset2, count);

    return span1.SequenceCompareTo(span2);
    // or, if you don't care about ordering
    // return span1.SequenceEqual(span2);
}
#else
// The most basic implementation, in platform-agnostic, safe C#
public static bool Compare(byte[] range1, int offset1, byte[] range2, int offset2, int count)
{
    // Working backwards lets the compiler optimize away bound checking after the first loop
    for (int i = count - 1; i >= 0; --i)
    {
        if (range1[offset1 + i] != range2[offset2 + i])
        {
            return false;
        }
    }

    return true;
}
#endif

为了比较短的字节数组，下面是一个有趣的hack:

if(myByteArray1.Length != myByteArray2.Length) return false;
if(myByteArray1.Length == 8)
   return BitConverter.ToInt64(myByteArray1, 0) == BitConverter.ToInt64(myByteArray2, 0); 
else if(myByteArray.Length == 4)
   return BitConverter.ToInt32(myByteArray2, 0) == BitConverter.ToInt32(myByteArray2, 0); 

那么，我可能会转而考虑问题中列出的解决方案。

对这段代码进行性能分析会很有趣。

你可以使用Enumerable。SequenceEqual方法。

using System;
using System.Linq;
...
var a1 = new int[] { 1, 2, 3};
var a2 = new int[] { 1, 2, 3};
var a3 = new int[] { 1, 2, 4};
var x = a1.SequenceEqual(a2); // true
var y = a1.SequenceEqual(a3); // false

如果你因为某些原因不能使用. net 3.5，你的方法是可以的。 编译器运行时环境会优化你的循环，所以你不需要担心性能。