我怎样才能做得快呢?
当然我可以这样做:
static bool ByteArrayCompare(byte[] a1, byte[] a2)
{
if (a1.Length != a2.Length)
return false;
for (int i=0; i<a1.Length; i++)
if (a1[i]!=a2[i])
return false;
return true;
}
但我正在寻找一个BCL函数或一些高度优化的已证明的方法来做到这一点。
java.util.Arrays.equals((sbyte[])(Array)a1, (sbyte[])(Array)a2);
工作得很好，但这似乎不适用于x64。
注意我的快速回答。
当前回答
找不到一个我完全满意的解决方案(合理的性能，但没有不安全的代码/pinvoke)，所以我想出了这个，没有真正的原创，但工作:
/// <summary>
///
/// </summary>
/// <param name="array1"></param>
/// <param name="array2"></param>
/// <param name="bytesToCompare"> 0 means compare entire arrays</param>
/// <returns></returns>
public static bool ArraysEqual(byte[] array1, byte[] array2, int bytesToCompare = 0)
{
if (array1.Length != array2.Length) return false;
var length = (bytesToCompare == 0) ? array1.Length : bytesToCompare;
var tailIdx = length - length % sizeof(Int64);
//check in 8 byte chunks
for (var i = 0; i < tailIdx; i += sizeof(Int64))
{
if (BitConverter.ToInt64(array1, i) != BitConverter.ToInt64(array2, i)) return false;
}
//check the remainder of the array, always shorter than 8 bytes
for (var i = tailIdx; i < length; i++)
{
if (array1[i] != array2[i]) return false;
}
return true;
}
与本页上的其他解决方案相比，性能:
简单循环:19837滴答，1.00
*位收敛器:4886 ticks, 4.06
unsafcompare: 1636 ticks, 12.12
EqualBytesLongUnrolled: 637 tick, 31.09
P/Invoke memcmp: 369 ticks, 53.67
在linqpad上测试，1000000字节的相同数组(最坏的情况)，每个数组500次迭代。
其他回答
我开发了一个方法，稍微击败memcmp() (plinth的答案)和非常轻微击败EqualBytesLongUnrolled() (Arek Bulski的答案)在我的PC上。基本上，它以4而不是8展开循环。
2019年3月30日更新：
从。net核心3.0开始，我们有了SIMD支持!
这个解决方案在我的PC上是最快的:
#if NETCOREAPP3_0
using System.Runtime.Intrinsics.X86;
#endif
…
public static unsafe bool Compare(byte[] arr0, byte[] arr1)
{
if (arr0 == arr1)
{
return true;
}
if (arr0 == null || arr1 == null)
{
return false;
}
if (arr0.Length != arr1.Length)
{
return false;
}
if (arr0.Length == 0)
{
return true;
}
fixed (byte* b0 = arr0, b1 = arr1)
{
#if NETCOREAPP3_0
if (Avx2.IsSupported)
{
return Compare256(b0, b1, arr0.Length);
}
else if (Sse2.IsSupported)
{
return Compare128(b0, b1, arr0.Length);
}
else
#endif
{
return Compare64(b0, b1, arr0.Length);
}
}
}
#if NETCOREAPP3_0
public static unsafe bool Compare256(byte* b0, byte* b1, int length)
{
byte* lastAddr = b0 + length;
byte* lastAddrMinus128 = lastAddr - 128;
const int mask = -1;
while (b0 < lastAddrMinus128) // unroll the loop so that we are comparing 128 bytes at a time.
{
if (Avx2.MoveMask(Avx2.CompareEqual(Avx.LoadVector256(b0), Avx.LoadVector256(b1))) != mask)
{
return false;
}
if (Avx2.MoveMask(Avx2.CompareEqual(Avx.LoadVector256(b0 + 32), Avx.LoadVector256(b1 + 32))) != mask)
{
return false;
}
if (Avx2.MoveMask(Avx2.CompareEqual(Avx.LoadVector256(b0 + 64), Avx.LoadVector256(b1 + 64))) != mask)
{
return false;
}
if (Avx2.MoveMask(Avx2.CompareEqual(Avx.LoadVector256(b0 + 96), Avx.LoadVector256(b1 + 96))) != mask)
{
return false;
}
b0 += 128;
b1 += 128;
}
while (b0 < lastAddr)
{
if (*b0 != *b1) return false;
b0++;
b1++;
}
return true;
}
public static unsafe bool Compare128(byte* b0, byte* b1, int length)
{
byte* lastAddr = b0 + length;
byte* lastAddrMinus64 = lastAddr - 64;
const int mask = 0xFFFF;
while (b0 < lastAddrMinus64) // unroll the loop so that we are comparing 64 bytes at a time.
{
if (Sse2.MoveMask(Sse2.CompareEqual(Sse2.LoadVector128(b0), Sse2.LoadVector128(b1))) != mask)
{
return false;
}
if (Sse2.MoveMask(Sse2.CompareEqual(Sse2.LoadVector128(b0 + 16), Sse2.LoadVector128(b1 + 16))) != mask)
{
return false;
}
if (Sse2.MoveMask(Sse2.CompareEqual(Sse2.LoadVector128(b0 + 32), Sse2.LoadVector128(b1 + 32))) != mask)
{
return false;
}
if (Sse2.MoveMask(Sse2.CompareEqual(Sse2.LoadVector128(b0 + 48), Sse2.LoadVector128(b1 + 48))) != mask)
{
return false;
}
b0 += 64;
b1 += 64;
}
while (b0 < lastAddr)
{
if (*b0 != *b1) return false;
b0++;
b1++;
}
return true;
}
#endif
public static unsafe bool Compare64(byte* b0, byte* b1, int length)
{
byte* lastAddr = b0 + length;
byte* lastAddrMinus32 = lastAddr - 32;
while (b0 < lastAddrMinus32) // unroll the loop so that we are comparing 32 bytes at a time.
{
if (*(ulong*)b0 != *(ulong*)b1) return false;
if (*(ulong*)(b0 + 8) != *(ulong*)(b1 + 8)) return false;
if (*(ulong*)(b0 + 16) != *(ulong*)(b1 + 16)) return false;
if (*(ulong*)(b0 + 24) != *(ulong*)(b1 + 24)) return false;
b0 += 32;
b1 += 32;
}
while (b0 < lastAddr)
{
if (*b0 != *b1) return false;
b0++;
b1++;
}
return true;
}
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。
让我们再加一个!
最近微软发布了一个特殊的NuGet包System.Runtime.CompilerServices.Unsafe。它的特殊之处在于它是用IL编写的，并且提供了c#中无法直接使用的低级功能。
它的一个方法unsafety . as <T>(object)允许将任何引用类型转换为另一个引用类型，跳过任何安全检查。这通常是一个非常糟糕的主意，但如果两种类型具有相同的结构，它就可以工作。因此，我们可以使用这个函数将字节[]转换为长[]:
bool CompareWithUnsafeLibrary(byte[] a1, byte[] a2)
{
if (a1.Length != a2.Length) return false;
var longSize = (int)Math.Floor(a1.Length / 8.0);
var long1 = Unsafe.As<long[]>(a1);
var long2 = Unsafe.As<long[]>(a2);
for (var i = 0; i < longSize; i++)
{
if (long1[i] != long2[i]) return false;
}
for (var i = longSize * 8; i < a1.Length; i++)
{
if (a1[i] != a2[i]) return false;
}
return true;
}
注意long1。Length仍然会返回原始数组的长度，因为它存储在数组内存结构中的字段中。
这个方法没有这里演示的其他方法那么快，但它比朴素方法快得多，不使用不安全的代码或P/Invoke或固定，实现非常简单(IMO)。以下是我的机器上的一些BenchmarkDotNet结果:
BenchmarkDotNet=v0.10.3.0, OS=Microsoft Windows NT 6.2.9200.0
Processor=Intel(R) Core(TM) i7-4870HQ CPU 2.50GHz, ProcessorCount=8
Frequency=2435775 Hz, Resolution=410.5470 ns, Timer=TSC
[Host] : Clr 4.0.30319.42000, 64bit RyuJIT-v4.6.1637.0
DefaultJob : Clr 4.0.30319.42000, 64bit RyuJIT-v4.6.1637.0
Method | Mean | StdDev |
----------------------- |-------------- |---------- |
UnsafeLibrary | 125.8229 ns | 0.3588 ns |
UnsafeCompare | 89.9036 ns | 0.8243 ns |
JSharpEquals | 1,432.1717 ns | 1.3161 ns |
EqualBytesLongUnrolled | 43.7863 ns | 0.8923 ns |
NewMemCmp | 65.4108 ns | 0.2202 ns |
ArraysEqual | 910.8372 ns | 2.6082 ns |
PInvokeMemcmp | 52.7201 ns | 0.1105 ns |
我还为所有测试创建了一个要点。
似乎EqualBytesLongUnrolled是上述建议中最好的。
被跳过的方法(Enumerable.SequenceEqual,StructuralComparisons.StructuralEqualityComparer.Equals)不是慢速的。在265MB的数组上，我测量了这个:
Host Process Environment Information:
BenchmarkDotNet.Core=v0.9.9.0
OS=Microsoft Windows NT 6.2.9200.0
Processor=Intel(R) Core(TM) i7-3770 CPU 3.40GHz, ProcessorCount=8
Frequency=3323582 ticks, Resolution=300.8802 ns, Timer=TSC
CLR=MS.NET 4.0.30319.42000, Arch=64-bit RELEASE [RyuJIT]
GC=Concurrent Workstation
JitModules=clrjit-v4.6.1590.0
Type=CompareMemoriesBenchmarks Mode=Throughput
Method | Median | StdDev | Scaled | Scaled-SD |
----------------------- |------------ |---------- |------- |---------- |
NewMemCopy | 30.0443 ms | 1.1880 ms | 1.00 | 0.00 |
EqualBytesLongUnrolled | 29.9917 ms | 0.7480 ms | 0.99 | 0.04 |
msvcrt_memcmp | 30.0930 ms | 0.2964 ms | 1.00 | 0.03 |
UnsafeCompare | 31.0520 ms | 0.7072 ms | 1.03 | 0.04 |
ByteArrayCompare | 212.9980 ms | 2.0776 ms | 7.06 | 0.25 |
OS=Windows
Processor=?, ProcessorCount=8
Frequency=3323582 ticks, Resolution=300.8802 ns, Timer=TSC
CLR=CORE, Arch=64-bit ? [RyuJIT]
GC=Concurrent Workstation
dotnet cli version: 1.0.0-preview2-003131
Type=CompareMemoriesBenchmarks Mode=Throughput
Method | Median | StdDev | Scaled | Scaled-SD |
----------------------- |------------ |---------- |------- |---------- |
NewMemCopy | 30.1789 ms | 0.0437 ms | 1.00 | 0.00 |
EqualBytesLongUnrolled | 30.1985 ms | 0.1782 ms | 1.00 | 0.01 |
msvcrt_memcmp | 30.1084 ms | 0.0660 ms | 1.00 | 0.00 |
UnsafeCompare | 31.1845 ms | 0.4051 ms | 1.03 | 0.01 |
ByteArrayCompare | 212.0213 ms | 0.1694 ms | 7.03 | 0.01 |
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);
});
}
}
}
