Code Optimization

Hello my dear friends.

Today we will look into such popular thing like cross-platform code, and such powerful thing like assembler. Of course, we will use C#.NET for this all as usually  :)

To make a cross-platform code we have to be aware of two main things:

- method call conventions 

- system API

We need different platform dependent system APIs to allocate and free executing memory and we need universal code to avoid method call convention problems.

To call system dependent APIs we need to understand what OS we are running under, here is code how we can do it:

 
        private enum Platform
        {
            Windows,
            Linux,
            Mac
        }

        private static Platform RunningPlatform()
        {
            switch (Environment.OSVersion.Platform)
            {
                case PlatformID.Unix:
                    // Well, there are chances MacOSX is reported as Unix instead of MacOSX.
                    // Instead of platform check, we'll do a feature checks (Mac specific root folders)
                    if (Directory.Exists("/Applications")
                        & Directory.Exists("/System")
                        & Directory.Exists("/Users")
                        & Directory.Exists("/Volumes"))
                        return Platform.Mac;
                    else
                        return Platform.Linux;
                case PlatformID.MacOSX:
                    return Platform.Mac;
                default:
                    return Platform.Windows;
            }
        }

Now we are going to declare PInvokes for linux and windows and implement logic to allocate and free memory with regards to OS we are running under (linux pinvokes were taken from the Mono source code):

        #region Windows

        [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
        }
        [DllImport("kernel32.dll", SetLastError = true)]
        private static extern IntPtr VirtualAlloc(
            IntPtr lpAddress,
            UIntPtr dwSize,
            AllocationTypes flAllocationType,
            MemoryProtections flProtect);

　
        [DllImport("kernel32")]
        [return: MarshalAs(UnmanagedType.Bool)]
        private static extern bool VirtualFree(
            IntPtr lpAddress,
            uint dwSize,
            FreeTypes flFreeType);

        #endregion
        #region Unix

        [AttributeUsage(
        AttributeTargets.Class |
        AttributeTargets.Delegate |
        AttributeTargets.Enum |
        AttributeTargets.Field |
        AttributeTargets.Struct)]
        private class MapAttribute : Attribute
        {
            private string nativeType;
            private string suppressFlags;

            public MapAttribute()
            {
            }
            public MapAttribute(string nativeType)
            {
                this.nativeType = nativeType;
            }

            public string NativeType
            {
                get { return nativeType; }
            }
            public string SuppressFlags
            {
                get { return suppressFlags; }
                set { suppressFlags = value; }
            }
        }

        private const string MPH = "MonoPosixHelper";
        private const string LIBC = "msvcrt";

        [Map]
        [Flags]
        private enum MmapProts : int
        {
            PROT_READ = 0x1,  // Page can be read.
            PROT_WRITE = 0x2,  // Page can be written.
            PROT_EXEC = 0x4,  // Page can be executed.
            PROT_NONE = 0x0,  // Page can not be accessed.
            PROT_GROWSDOWN = 0x01000000, // Extend change to start of
            //   growsdown vma (mprotect only).
            PROT_GROWSUP = 0x02000000, // Extend change to start of
            //   growsup vma (mprotect only).
        }

        [Map]
        [Flags]
        private enum MmapFlags : int
        {
            MAP_SHARED = 0x01,     // Share changes.
            MAP_PRIVATE = 0x02,     // Changes are private.
            MAP_TYPE = 0x0f,     // Mask for type of mapping.
            MAP_FIXED = 0x10,     // Interpret addr exactly.
            MAP_FILE = 0,
            MAP_ANONYMOUS = 0x20,     // Don't use a file.
            MAP_ANON = MAP_ANONYMOUS,
            // These are Linux-specific.
            MAP_GROWSDOWN = 0x00100,  // Stack-like segment.
            MAP_DENYWRITE = 0x00800,  // ETXTBSY
            MAP_EXECUTABLE = 0x01000,  // Mark it as an executable.
            MAP_LOCKED = 0x02000,  // Lock the mapping.
            MAP_NORESERVE = 0x04000,  // Don't check for reservations.
            MAP_POPULATE = 0x08000,  // Populate (prefault) pagetables.
            MAP_NONBLOCK = 0x10000,  // Do not block on IO.
        }

        [DllImport(MPH, SetLastError = true,
                EntryPoint = "Mono_Posix_Syscall_mmap")]
        private static extern IntPtr mmap(IntPtr start, ulong length,
                MmapProts prot, MmapFlags flags, int fd, long offset);


        [DllImport(MPH, SetLastError = true,
                EntryPoint = "Mono_Posix_Syscall_munmap")]
        public static extern int munmap(IntPtr start, ulong length);


        [DllImport(MPH, SetLastError = true,
                        EntryPoint = "Mono_Posix_Syscall_mprotect")]
        private static extern int mprotect(IntPtr start, ulong len, MmapProts prot);

        [DllImport(MPH, CallingConvention = CallingConvention.Cdecl,
                SetLastError = true, EntryPoint = "Mono_Posix_Stdlib_malloc")]
        private static extern IntPtr malloc(ulong size);
        [DllImport(LIBC, CallingConvention = CallingConvention.Cdecl)]
        public static extern void free(IntPtr ptr);
        #endregion

        [UnmanagedFunctionPointerAttribute(CallingConvention.Cdecl)]
        public unsafe delegate void asmFunc();

        public static IntPtr VirtualAlloc(uint size)
        {
            IntPtr ptr = IntPtr.Zero;
            if (RunningPlatform() == Platform.Windows)
            {
                ptr = VirtualAlloc(
                IntPtr.Zero,
                new UIntPtr(size),
                AllocationTypes.Commit | AllocationTypes.Reserve,
                MemoryProtections.ExecuteReadWrite);
            }
            else
            {
                Console.WriteLine("Linux memory allocation...");

                ptr = mmap(IntPtr.Zero, 4096, MmapProts.PROT_EXEC | MmapProts.PROT_READ | MmapProts.PROT_WRITE, MmapFlags.MAP_ANONYMOUS | MmapFlags.MAP_PRIVATE, 0, 0);
                
                Console.WriteLine("memory ptr: " + ptr.ToInt64());
            }
            return ptr;
        }

        public static void VirtualFree(IntPtr ptr, uint size)
        {
            if (RunningPlatform() == Platform.Windows)
            {
                VirtualFree(ptr, size, FreeTypes.Release);
            }
            else
            {
                Console.WriteLine("Free memory ptr: " + ptr.ToInt64());
                int r = munmap(ptr, size);
                Console.WriteLine("memory free status: " + r);
            }
        }

Ok, we have methods to allocate and free memory and now, we need some predefined assembly code and template to avoid any calling convention problems. To do it we will declare our methods and delegates as parameter-less and will pass parameters as declared bytes:

 
            byte[] codeArray = new byte[]
            {
                0xE8,   // call next code after data
                0x00,
                0x00,
                0x00,
                0x00,
                //
                //data will go here
                //


                0x5B,   // pop e/rbx - now e/rbx looks into data address

                0xFF,   // inc dword [e/rbx]
                0x03,
                (byte)(IntPtr.Size > 4 ? 0x48 : 0x90),
                0xFF,   // inc e/rbx
                0xC3,
                (byte)(IntPtr.Size > 4 ? 0x48 : 0x90),
                0xFF,   // inc e/rbx
                0xC3,
                (byte)(IntPtr.Size > 4 ? 0x48 : 0x90),
                0xFF,   // inc e/rbx
                0xC3,
                (byte)(IntPtr.Size > 4 ? 0x48 : 0x90),
                0xFF,   // inc e/rbx
                0xC3,
                (byte)(IntPtr.Size > 4 ? 0x48 : 0x90),   // dec d/qword [rbx]
                0xFF,
                0x0B,

                0xC3    // retn - return from your method
            };

            byte[] dataArray = new byte[]
            {
                0xFF,   //parameter Int32
                0x00,
                0x00,
                0x00,
                0x00,   //parameter Int64
                0x00,
                0x00,
                0x00,
                0x00,
                0x00,
                0x00,
                0x00
            };

            Console.WriteLine("Ptr size: " + IntPtr.Size);

            //allocate memory for our asm method
            IntPtr pp = Native.VirtualAlloc((uint)(codeArray.Length + dataArray.Length));

            unsafe
            {
                IntPtr p = pp;
                int n = 0;
                byte* bptr = (byte*)p;
                Marshal.Copy(codeArray, 0, p, 4);
                p += 1;

                //write offset to the next code line
                Marshal.WriteInt32(p, dataArray.Length);
                p += 4;

                //copy data
                Marshal.Copy(dataArray, 0, p, dataArray.Length);
                p += dataArray.Length;

                //copy rest of the code
                Marshal.Copy(codeArray, 5, p, codeArray.Length - 5);
                bptr[n] = bptr[n];
                n = 0;
            }
            Native.asmFunc asmFunc = (Native.asmFunc)System.Runtime.InteropServices.Marshal.GetDelegateForFunctionPointer(pp, typeof(Native.asmFunc));

            Console.WriteLine("in param int32 = " + BitConverter.ToInt32(dataArray, 0));
            Console.WriteLine("in param int64 = " + BitConverter.ToInt64(dataArray, sizeof(Int32)));

            Console.WriteLine("call asm method...");
            asmFunc();
            Console.WriteLine("exit asm method");

As our methods are parameter-less a system will not use stack and we will not have to care about stack. To get address of our first parameter we will use well-known technic, such as call addr and pop reg, that moves to our next processor instruction and pops back an address, this address will be the address of our first parameter.

To pass back any parameters from our assembly method we will use the same address to put them before return back.

            //copy params back to array
            Marshal.Copy(pp + 5, dataArray, 0, dataArray.Length);

            Console.WriteLine("out param int32 = " + BitConverter.ToInt32(dataArray, 0));
            Console.WriteLine("out param int64 = " + BitConverter.ToInt64(dataArray, sizeof(Int32)));

            //free allocated memory
            Native.VirtualFree(pp, (uint)(codeArray.Length + dataArray.Length));
            GC.Collect(GC.MaxGeneration, GCCollectionMode.Forced);


            Console.WriteLine("any key to exit");
            Console.ReadLine();

Now run it and test it. Remember that running this code, or any assembly code, under visual studio may cause error and exception, so always test your code out of any debugger.

I did test this code under Windows 10 64 bit and compiling in x32 and x64 modes, and Linux Ubuntu 14.04 64 bit mode.

Comments are welcome.

Thank you all,

See you later :)

1vqHSTrq1GEoEF7QsL8dhmJfRMDVxhv2y

Introduction

I'm Oleksandr Karpov and this is my first article here, thanks for reading it.

Here, I'm going to show and explain how to copy data really fast and how to use assembly under C# and .NET. In my case, I use it in a video creating application from images, video and sound.
Also, if you have an assembly method or function that you need to use under C#, it will show you how to do it in a quick and simple way.

Background

To understand it all, it would be great for you to know assembly language, memory alignment and some C#, Windows and .NET advanced techniques.
To be able to copy-paste data really fast, you need it to have 16 byte aligned memory address in other way it will have almost the same speed (in my case, about 1.02 time faster).

The code uses SSE instructions that are supported by processors from Pentium III+ (KNI/MMX2), AMD Athlon (AMD EMMX).

I have tested it on my Pentium Dual-Core E5800 3.2GHz with 4GB RAM in dual mode.
For me, the fast copy method is 1.5 times faster than the standard with 16 byte memory aligned and
almost the same (1.02 times faster) with non-aligned memory addresses.

To be able to allocate 16 byte aligned memory in C# under Windows, we have three ways to do it:

a) On this time it seems that Bitmap object (actually windows itself inside) allocates memory  with 16 byte aligned address, so we can use Bitmap to easy and quick aligned memory allocation;

b) As managed array by adding 8 bytes more (as windows heap is 8 byte aligned) and calculating 16 byte aligned memory point within allocated memory:

int dataLength = 4096;

// +8 bytes as windows heap is 8 byte aligned
byte[] buffer = new byte[dataLength + 8];

IntPtr addr = Marshal.UnsafeAddrOfPinnedArrayElement(buffer, 0);

//(int)(((long)addr + 15) / 16 * 16 - getting point to 16 byte aligned address            
int bufferAlignedOffset = (int)(((long)addr + 15) / 16 * 16 - addr);

c) By allocating memory with VirtualAlloc API:

IntPtr addr = VirtualAlloc(IntPtr.Zero,
			    new UIntPtr(dataLength + 8),
			    AllocationTypes.Commit | AllocationTypes.Reserve,
			    MemoryProtections.ExecuteReadWrite);

addr = new IntPtr(((long)addr + 15) / 16 * 16);

Using the Code

This is a complete performance test that will show you performance measurements and how to use it all.

The FastMemCopy class contains all things for fast memory copy logic.

First thing you need is to create a default Windows Forms application project and put two buttons on the form and the PictureBox control as we will test it on images.

Let's declare some fields:

string bitmapPath;
Bitmap bmp, bmp2;
BitmapData bmpd, bmpd2;
byte[] buffer = null;

Now, we will create two methods to handle click events for our buttons.

For standard method:

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;
}

and for fast method:

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;
}

Ok, now we have buttons and event handlers so let's implement methods that will open images, lock, unlock them and standard copy method:

Open an image:

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));
}

Lock and unlock bitmaps:

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);
}

and copy data from one image to another and show measured time:

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());
}

That's it for the standard copy-paste method. Actually, there is nothing too complex, we use well-known System.Runtime.InteropServices.Marshal.Copy method.

And one more "middle-method" for the fast copy logic:

void FastCopyImage()
{
    FastMemCopy.FastMemoryCopy(bmpd.Scan0, bmpd2.Scan0, buffer.Length);
}

Now, let's implement the FastMemCopy class. Here is the declaration of the class and some types we will use inside of it:

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);
    }

Now let's declare the method itself:

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!");
    }
}

and assembly code that is represented as an array of bytes with explanation:

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
};

We will call this assembly method via delegate we have created earlier.

This method works in 32 bit mode for now and I will implement the 64 bit mode later.
I will add source code if anyone is interested in it (almost all code is there in the article).

Pay attention, the assembly code throws an exception if it is run under Visual Studio, and I still don't understand why.

Points of Interest

During implementation and testing this method, I have found that prefetchnta command is not very clear described even by the Intel specification, so I did try to figure out it myself and via Google.
Also, pay attention to movntps and movaps instructions as they work with 16-byte memory aligned addresses only.

History

• Bitmap and 16 byte memory alignment
• Source code and memory alignment samples were added
• First version - 06/23/2015
  

1vqHSTrq1GEoEF7QsL8dhmJfRMDVxhv2y