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。
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;
}
. net 3.5及更新版本有一个新的公共类型System.Data.Linq.Binary,它封装了byte[]。它实现了IEquatable<Binary>,(实际上)比较两个字节数组。注意System.Data.Linq.Binary也有来自byte[]的隐式转换运算符。
MSDN文档:System.Data.Linq.Binary
Equals方法的反射器反编译:
private bool EqualsTo(Binary binary)
{
if (this != binary)
{
if (binary == null)
{
return false;
}
if (this.bytes.Length != binary.bytes.Length)
{
return false;
}
if (this.hashCode != binary.hashCode)
{
return false;
}
int index = 0;
int length = this.bytes.Length;
while (index < length)
{
if (this.bytes[index] != binary.bytes[index])
{
return false;
}
index++;
}
}
return true;
}
有趣的是,只有当两个Binary对象的哈希值相同时,它们才会进行逐字节比较循环。然而,这是以在二进制对象的构造函数中计算哈希值为代价的(通过使用for loop:-)遍历数组)。
上述实现意味着,在最坏的情况下,您可能必须遍历数组三次:首先计算array1的哈希值,然后计算array2的哈希值,最后(因为这是最坏的情况,长度和哈希值相等)比较array1中的字节和数组2中的字节。
总的来说,即使System.Data.Linq.Binary被内置到BCL中,我不认为这是比较两个字节数组的最快方法:-|。
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);
}
}
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 |