使用 x86 汇编实现 C# 的快速内存拷贝
使用 x86 汇编实现 C# 的快速内存拷贝
介绍
大家好，我是Oleksandr Karpov，这个是我第一次发表文章，希望大家喜欢。
在这我将为大家展示和介绍怎么样在C#和.NET下使用汇编秒速拷贝数据，在我是实例里面我用了一运用程序创建了一段视频，里面包含图片，视频和声音。
当然如果你也需要在C#使用汇编的情况，这方法给你提供一个快速简单的解决途径。
背景
理解本文的内容, 最好具备以下知识: 汇编语言, 内存对齐, c#, windows 和 .net 高级技巧(advanced techniques).
要提高数据复制(copy-past )的速度, 我们需要将内存地址按 16 个字节对齐. 否则, 速度不会有明显的改变. (我的例子大概快 1.02 倍 )
Pentium III+ (KNI/MMX2) 和 AMD Athlon (AMD EMMX) 这两种处理器都支持本文代码用到 SSE 指令集.
我用配置为: Pentium Dual-Core E5800 3.2GHz, 4GB RAM 双通道内存的计算机做测试, 16 个字节内存对齐的速度要比标准方式快 1.5 倍, 而非内存对齐方式的速度几乎没有变化(1.02倍).
使用代码
这是一个完整的演示测试，向你展示了性能测试以及如何使用。
FastMemCopy 类包含了用于快速内存拷贝逻辑的所有内容。
首先你需要创建一个默认的Windows Forms应用程序工程，在窗体上放两个按钮，一个PictureBox 控件，因为我们将用图片来测试。
声明几个字段先：
string bitmapPath;
Bitmap bmp, bmp2;
BitmapData bmpd, bmpd2;
byte[] buffer = null;
现在创建两个方法用来处理按钮的点击事件。
标准方法如下：
private void btnStandard_Click(object sender, EventArgs e)
{
using (OpenFileDialog ofd = new OpenFileDialog())
{
if (ofd.ShowDialog() != System.Windows.Forms.DialogResult.OK)
return;
bitmapPath = ofd.FileName;
}
//open a selected image and create an empty image with the same size
OpenImage();
//unlock for read and write images
UnlockBitmap();
//copy data from one image to another by standard method
CopyImage();
//lock images to be able to see them
LockBitmap();
//lets see what we have
pictureBox1.Image = bmp2;
}
快速方法如下：
private void btnFast_Click(object sender, EventArgs e)
{
using (OpenFileDialog ofd = new OpenFileDialog())
{
if (ofd.ShowDialog() != System.Windows.Forms.DialogResult.OK)
return;
bitmapPath = ofd.FileName;
}
//open a selected image and create an empty image with the same size
OpenImage();
//unlock for read and write images
UnlockBitmap();
//copy data from one image to another with our fast method
FastCopyImage();
//lock images to be able to see them
LockBitmap();
//lets see what we have
pictureBox1.Image = bmp2;
}
好的，现在我们有按钮并且也有了事件处理，下面来实现打开图片、锁定、解锁它们的方法，以及标准拷贝方法：
打开一个图片：
void OpenImage()
{
pictureBox1.Image = null;
buffer = null;
if (bmp != null)
{
bmp.Dispose();
bmp = null;
}
if (bmp2 != null)
{
bmp2.Dispose();
bmp2 = null;
}
GC.Collect(GC.MaxGeneration, GCCollectionMode.Forced);
bmp = (Bitmap)Bitmap.FromFile(bitmapPath);
buffer = new byte[bmp.Width * 4 * bmp.Height];
bmp2 = new Bitmap(bmp.Width, bmp.Height, bmp.Width * 4, PixelFormat.Format32bppArgb,
Marshal.UnsafeAddrOfPinnedArrayElement(buffer, 0));
}
锁定和解锁位图：
void UnlockBitmap()
{
bmpd = bmp.LockBits(new Rectangle(0, 0, bmp.Width, bmp.Height), ImageLockMode.ReadWrite,
PixelFormat.Format32bppArgb);
bmpd2 = bmp2.LockBits(new Rectangle(0, 0, bmp.Width, bmp.Height), ImageLockMode.ReadWrite,
PixelFormat.Format32bppArgb);
}
void LockBitmap()
{
bmp.UnlockBits(bmpd);
bmp2.UnlockBits(bmpd2);
}
从一个图片拷贝数据到另一个图片，并且显示测得的时间：
void CopyImage()
{
//start stopwatch
Stopwatch sw = new Stopwatch();
sw.Start();
//copy-past data 10 times
for (int i = 0; i < 10; i++)
{
System.Runtime.InteropServices.Marshal.Copy(bmpd.Scan0, buffer, 0, buffer.Length);
}
//stop stopwatch
sw.Stop();
//show measured time
MessageBox.Show(sw.ElapsedTicks.ToString());
}
这就是标准快速拷贝方法。其实一点也不复杂，我们使用了知名的 System.Runtime.InteropServices.Marshal.Copy 方法。
以及又一个“中间方法（middle-method）”以用于快速拷贝逻辑：
void FastCopyImage()
{
FastMemCopy.FastMemoryCopy(bmpd.Scan0, bmpd2.Scan0, buffer.Length);
}
现在，来实现FastMemCopy类。下面是类的声明以及我们将会在类中使用到的一些类型：
internal static class FastMemCopy
{
[Flags]
private enum AllocationTypes : uint
{
Commit = 0x1000, Reserve = 0x2000,
Reset = 0x80000, LargePages = 0x20000000,
Physical = 0x400000, TopDown = 0x100000,
WriteWatch = 0x200000
}
[Flags]
private enum MemoryProtections : uint
{
Execute = 0x10, ExecuteRead = 0x20,
ExecuteReadWrite = 0x40, ExecuteWriteCopy = 0x80,
NoAccess = 0x01, ReadOnly = 0x02,
ReadWrite = 0x04, WriteCopy = 0x08,
GuartModifierflag = 0x100, NoCacheModifierflag = 0x200,
WriteCombineModifierflag = 0x400
}
[Flags]
private enum FreeTypes : uint
{
Decommit = 0x4000, Release = 0x8000
}
[UnmanagedFunctionPointerAttribute(CallingConvention.Cdecl)]
private unsafe delegate void FastMemCopyDelegate();
private static class NativeMethods
{
[DllImport("kernel32.dll", SetLastError = true)]
internal static extern IntPtr VirtualAlloc(
IntPtr lpAddress,
UIntPtr dwSize,
AllocationTypes flAllocationType,
MemoryProtections flProtect);
[DllImport("kernel32")]
[return: MarshalAs(UnmanagedType.Bool)]
internal static extern bool VirtualFree(
IntPtr lpAddress,
uint dwSize,
FreeTypes flFreeType);
}
现在声明方法本身：
public static unsafe void FastMemoryCopy(IntPtr src, IntPtr dst, int nBytes)
{
if (IntPtr.Size == 4)
{
//we are in 32 bit mode
//allocate memory for our asm method
IntPtr p = NativeMethods.VirtualAlloc(
IntPtr.Zero,
new UIntPtr((uint)x86_FastMemCopy_New.Length),
AllocationTypes.Commit | AllocationTypes.Reserve,
MemoryProtections.ExecuteReadWrite);
try
{
//copy our method bytes to allocated memory
Marshal.Copy(x86_FastMemCopy_New, 0, p, x86_FastMemCopy_New.Length);
//make a delegate to our method
FastMemCopyDelegate _fastmemcopy =
(FastMemCopyDelegate)Marshal.GetDelegateForFunctionPointer(p,
typeof(FastMemCopyDelegate));
//offset to the end of our method block
p += x86_FastMemCopy_New.Length;
//store length param
p -= 8;
Marshal.Copy(BitConverter.GetBytes((long)nBytes), 0, p, 4);
//store destination address param
p -= 8;
Marshal.Copy(BitConverter.GetBytes((long)dst), 0, p, 4);
//store source address param
p -= 8;
Marshal.Copy(BitConverter.GetBytes((long)src), 0, p, 4);
//Start stopwatch
Stopwatch sw = new Stopwatch();
sw.Start();
//copy-past all data 10 times
for (int i = 0; i < 10; i++)
_fastmemcopy();
//stop stopwatch
sw.Stop();
//get message with measured time
System.Windows.Forms.MessageBox.Show(sw.ElapsedTicks.ToString());
}
catch (Exception ex)
{
//if any exception
System.Windows.Forms.MessageBox.Show(ex.Message);
}
finally
{
//free allocated memory
NativeMethods.VirtualFree(p, (uint)(x86_FastMemCopy_New.Length),
FreeTypes.Release);
GC.Collect(GC.MaxGeneration, GCCollectionMode.Forced);
}
}
else if (IntPtr.Size == 8)
{
throw new ApplicationException("x64 is not supported yet!");
}
}
汇编代码被表示成带注释的字节数组：
private static byte[] x86_FastMemCopy_New = new byte[]
{
0x90, //nop do nothing
0x60, //pushad store flag register on stack
0x95, //xchg ebp, eax eax contains memory address of our method
0x8B, 0xB5, 0x5A, 0x01, 0x00, 0x00, //mov esi,[ebp][00000015A] get source buffer address
0x89, 0xF0, //mov eax,esi
0x83, 0xE0, 0x0F, //and eax,00F will check if it is 16 byte aligned
0x8B, 0xBD, 0x62, 0x01, 0x00, 0x00, //mov edi,[ebp][000000162] get destination address
0x89, 0xFB, //mov ebx,edi
0x83, 0xE3, 0x0F, //and ebx,00F will check if it is 16 byte aligned
0x8B, 0x8D, 0x6A, 0x01, 0x00, 0x00, //mov ecx,[ebp][00000016A] get number of bytes to copy
0xC1, 0xE9, 0x07, //shr ecx,7 divide length by 128
0x85, 0xC9, //test ecx,ecx check if zero
0x0F, 0x84, 0x1C, 0x01, 0x00, 0x00, //jz 000000146 ↓ copy the rest
0x0F, 0x18, 0x06, //prefetchnta [esi] pre-fetch non-temporal source data for reading
0x85, 0xC0, //test eax,eax check if source address is 16 byte aligned
0x0F, 0x84, 0x8B, 0x00, 0x00, 0x00, //jz 0000000C0 ↓ go to copy if aligned
0x0F, 0x18, 0x86, 0x80, 0x02, 0x00, 0x00, //prefetchnta [esi][000000280] pre-fetch more source data
0x0F, 0x10, 0x06, //movups xmm0,[esi] copy 16 bytes of source data
0x0F, 0x10, 0x4E, 0x10, //movups xmm1,[esi][010] copy more 16 bytes
0x0F, 0x10, 0x56, 0x20, //movups xmm2,[esi][020] copy more
0x0F, 0x18, 0x86, 0xC0, 0x02, 0x00, 0x00, //prefetchnta [esi][0000002C0] pre-fetch more
0x0F, 0x10, 0x5E, 0x30, //movups xmm3,[esi][030]
0x0F, 0x10, 0x66, 0x40, //movups xmm4,[esi][040]
0x0F, 0x10, 0x6E, 0x50, //movups xmm5,[esi][050]
0x0F, 0x10, 0x76, 0x60, //movups xmm6,[esi][060]
0x0F, 0x10, 0x7E, 0x70, //movups xmm7,[esi][070] we've copied 128 bytes of source data
0x85, 0xDB, //test ebx,ebx check if destination address is 16 byte aligned
0x74, 0x21, //jz 000000087 ↓ go to past if aligned
0x0F, 0x11, 0x07, //movups [edi],xmm0 past first 16 bytes to non-aligned destination address
0x0F, 0x11, 0x4F, 0x10, //movups [edi][010],xmm1 past more
0x0F, 0x11, 0x57, 0x20, //movups [edi][020],xmm2
0x0F, 0x11, 0x5F, 0x30, //movups [edi][030],xmm3
0x0F, 0x11, 0x67, 0x40, //movups [edi][040],xmm4
0x0F, 0x11, 0x6F, 0x50, //movups [edi][050],xmm5
0x0F, 0x11, 0x77, 0x60, //movups [edi][060],xmm6
0x0F, 0x11, 0x7F, 0x70, //movups [edi][070],xmm7 we've pasted 128 bytes of source data
0xEB, 0x1F, //jmps 0000000A6 ↓ continue
0x0F, 0x2B, 0x07, //movntps [edi],xmm0 past first 16 bytes to aligned destination address
0x0F, 0x2B, 0x4F, 0x10, //movntps [edi][010],xmm1 past more
0x0F, 0x2B, 0x57, 0x20, //movntps [edi][020],xmm2
0x0F, 0x2B, 0x5F, 0x30, //movntps [edi][030],xmm3
0x0F, 0x2B, 0x67, 0x40, //movntps [edi][040],xmm4
0x0F, 0x2B, 0x6F, 0x50, //movntps [edi][050],xmm5
0x0F, 0x2B, 0x77, 0x60, //movntps [edi][060],xmm6
0x0F, 0x2B, 0x7F, 0x70, //movntps [edi][070],xmm7 we've pasted 128 bytes of source data
0x81, 0xC6, 0x80, 0x00, 0x00, 0x00, //add esi,000000080 increment source address by 128
0x81, 0xC7, 0x80, 0x00, 0x00, 0x00, //add edi,000000080 increment destination address by 128
0x83, 0xE9, 0x01, //sub ecx,1 decrement counter
0x0F, 0x85, 0x7A, 0xFF, 0xFF, 0xFF, //jnz 000000035 ↑ continue if not zero
0xE9, 0x86, 0x00, 0x00, 0x00, //jmp 000000146 ↓ go to copy the rest of data
0x0F, 0x18, 0x86, 0x80, 0x02, 0x00, 0x00, //prefetchnta [esi][000000280] pre-fetch source data
0x0F, 0x28, 0x06, //movaps xmm0,[esi] copy 128 bytes from aligned source address
0x0F, 0x28, 0x4E, 0x10, //movaps xmm1,[esi][010] copy more
0x0F, 0x28, 0x56, 0x20, //movaps xmm2,[esi][020]
0x0F, 0x18, 0x86, 0xC0, 0x02, 0x00, 0x00, //prefetchnta [esi][0000002C0] pre-fetch more data
0x0F, 0x28, 0x5E, 0x30, //movaps xmm3,[esi][030]
0x0F, 0x28, 0x66, 0x40, //movaps xmm4,[esi][040]
0x0F, 0x28, 0x6E, 0x50, //movaps xmm5,[esi][050]
0x0F, 0x28, 0x76, 0x60, //movaps xmm6,[esi][060]
0x0F, 0x28, 0x7E, 0x70, //movaps xmm7,[esi][070] we've copied 128 bytes of source data
0x85, 0xDB, //test ebx,ebx check if destination address is 16 byte aligned
0x74, 0x21, //jz 000000112 ↓ go to past if aligned
0x0F, 0x11, 0x07, //movups [edi],xmm0 past 16 bytes to non-aligned destination address
0x0F, 0x11, 0x4F, 0x10, //movups [edi][010],xmm1 past more
0x0F, 0x11, 0x57, 0x20, //movups [edi][020],xmm2
0x0F, 0x11, 0x5F, 0x30, //movups [edi][030],xmm3
0x0F, 0x11, 0x67, 0x40, //movups [edi][040],xmm4
0x0F, 0x11, 0x6F, 0x50, //movups [edi][050],xmm5
0x0F, 0x11, 0x77, 0x60, //movups [edi][060],xmm6
0x0F, 0x11, 0x7F, 0x70, //movups [edi][070],xmm7 we've pasted 128 bytes of data
0xEB, 0x1F, //jmps 000000131 ↓ continue copy-past
0x0F, 0x2B, 0x07, //movntps [edi],xmm0 past 16 bytes to aligned destination address
0x0F, 0x2B, 0x4F, 0x10, //movntps [edi][010],xmm1 past more
0x0F, 0x2B, 0x57, 0x20, //movntps [edi][020],xmm2
0x0F, 0x2B, 0x5F, 0x30, //movntps [edi][030],xmm3
0x0F, 0x2B, 0x67, 0x40, //movntps [edi][040],xmm4
0x0F, 0x2B, 0x6F, 0x50, //movntps [edi][050],xmm5
0x0F, 0x2B, 0x77, 0x60, //movntps [edi][060],xmm6
0x0F, 0x2B, 0x7F, 0x70, //movntps [edi][070],xmm7 we've pasted 128 bytes of data
0x81, 0xC6, 0x80, 0x00, 0x00, 0x00, //add esi,000000080 increment source address by 128
0x81, 0xC7, 0x80, 0x00, 0x00, 0x00, //add edi,000000080 increment destination address by 128
0x83, 0xE9, 0x01, //sub ecx,1 decrement counter
0x0F, 0x85, 0x7A, 0xFF, 0xFF, 0xFF, //jnz 0000000C0 ↑ continue copy-past if non-zero
0x8B, 0x8D, 0x6A, 0x01, 0x00, 0x00, //mov ecx,[ebp][00000016A] get number of bytes to copy
0x83, 0xE1, 0x7F, //and ecx,07F get rest number of bytes
0x85, 0xC9, //test ecx,ecx check if there are bytes
0x74, 0x02, //jz 000000155 ↓ exit if there are no more bytes
0xF3, 0xA4, //rep movsb copy rest of bytes
0x0F, 0xAE, 0xF8, //sfence performs a serializing operation on all store-to-memory instructions
0x61, //popad restore flag register
0xC3, //retn return from our method to C#
0x00, 0x00, 0x00, 0x00, //source buffer address
0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, //destination buffer address
0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, //number of bytes to copy-past
0x00, 0x00, 0x00, 0x00
};
我们将会通过前面创建的托管来调用汇编方法。
该方法目前工作在32位模式下，将来我会实现64位模式。
谁感兴趣的话可以添加到源代码中（文章中几乎包含了所有的代码）
兴趣点
在实现及测试该方法期间，我发现prefetchnta命令描述的不是很清楚，甚至是Intel的说明书也是一样。所以我尝试自己以及通过google来弄明白
。注意movntps和movaps说明，它们只在16字节内存地址对齐时工作。
C#多线程编程实例 线程与窗体交互【附源码】
C#数学运算表达式解释器
在C语言中解析JSON配置文件
C++ Primer Plus 第6版 中文版 清晰有书签PDF+源代码
本文永久更新链接地址：
评论暂时关闭