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
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 |
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;
}
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。
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);
});
}
}
}
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
