[UnmanagedFunctionPointer(CallingConvention.StdCall)]

 delegate void VectorAddDelegate(float[] C, float[] B, float[] A, int length);

 [DllImport("kernel32.dll", SetLastError = true)]

 static extern IntPtr VirtualAlloc(

     IntPtr lpAddress, UIntPtr dwSize,

     IntPtr flAllocationType, IntPtr flProtect);

 //This array of bytes has been produced from

 //the SSE assembly version – it is a complete

 //function that accepts four parameters (three

 //vectors and length) and adds the vectors

 byte[] sseAssemblyBytes = {

     0x8b, 0x5c, 0x24, 0x10, 0x8b, 0x74, 0x24, 0x0c, 0x8b,

     0x7c, 0x24, 0x08, 0x8b, 0x4c, 0x24, 0x04, 0x31, 0xd2,

     0x0f, 0x10, 0x0c, 0x97, 0x0f, 0x10, 0x04, 0x96, 0x0f,

     0x58, 0xc8, 0x0f, 0x11, 0x0c, 0x91, 0x83, 0xc2, 0x04,

     0x39, 0xda, 0x7f, 0xea, 0xc2, 0x10, 0x00 };

 IntPtr codeBuffer = VirtualAlloc(

     IntPtr.Zero, new UIntPtr((uint)sseAssemblyBytes.Length),

     0x1000 | 0x2000, //MEM_COMMIT | MEM_RESERVE

     0x40 //EXECUTE_READWRITE

     );

 Marshal.Copy(sseAssemblyBytes, , codeBuffer, sseAssemblyBytes.Length);

 VectorAddDelegate addVectors = (VectorAddDelegate)

     Marshal.GetDelegateForFunctionPointer(codeBuffer, typeof(VectorAddDelegate));

 //We can now use ‘addVectors’ to add vectors!