#include <windows.h>
#include <d3d9.h>
#pragma comment(lib, "d3d9.lib")
#include <d3dx9.h>
#pragma comment(lib, "d3dx9.lib")

LRESULT CALLBACK WndProc (HWND hwnd, UINT message, WPARAM wParam, LPARAM lParam);
int WINAPI WinMain (HINSTANCE hInstance, HINSTANCE hPrevInstance, PSTR szCmdLine, int iCmdShow)
{
	static TCHAR szAppName[] = TEXT ("DirectXStreamExample");
	HWND         hwnd;
	MSG          msg;
	WNDCLASSEX   wndclassex = {0};
	wndclassex.cbSize        = sizeof(WNDCLASSEX);
	wndclassex.style         = CS_HREDRAW | CS_VREDRAW;
	wndclassex.lpfnWndProc   = WndProc;
	wndclassex.cbClsExtra    = 0;
	wndclassex.cbWndExtra    = 0;
	wndclassex.hInstance     = hInstance;
	wndclassex.hIcon         = LoadIcon (NULL, IDI_APPLICATION);
	wndclassex.hCursor       = LoadCursor (NULL, IDC_ARROW);
	wndclassex.hbrBackground = (HBRUSH) GetStockObject (BLACK_BRUSH);
	wndclassex.lpszMenuName  = NULL;
	wndclassex.lpszClassName = szAppName;
	wndclassex.hIconSm       = wndclassex.hIcon;

	if (!RegisterClassEx (&amp;wndclassex))
	{
		MessageBox (NULL, TEXT ("RegisterClassEx failed!"), szAppName, MB_ICONERROR);
		return 0;
	}
	hwnd = CreateWindowEx (WS_EX_OVERLAPPEDWINDOW,
		szAppName,
		TEXT ("DirectXStreamExample"),
		WS_OVERLAPPEDWINDOW,
		CW_USEDEFAULT,
		CW_USEDEFAULT,
		640,
		480,
		NULL,
		NULL,
		hInstance,
		NULL); 

	ShowWindow (hwnd, iCmdShow);
	UpdateWindow (hwnd);

	// Now setup DirectX
	IDirect3D9* d3d9 = Direct3DCreate9(D3D_SDK_VERSION);
	D3DPRESENT_PARAMETERS presentParameters;
	memset(&amp;presentParameters, 0, sizeof(D3DPRESENT_PARAMETERS));
	presentParameters.SwapEffect = D3DSWAPEFFECT_DISCARD;
	presentParameters.BackBufferFormat = D3DFMT_UNKNOWN;
	presentParameters.Windowed = true;
	IDirect3DDevice9* device = 0;
	d3d9->CreateDevice(0, D3DDEVTYPE_HAL, hwnd, D3DCREATE_MIXED_VERTEXPROCESSING, &amp;presentParameters, &amp;device);

	// Create our custom vertex format
	struct POSCOLORVERTEX
	{
		float X, Y, Z, W;
		DWORD color;
	};
	POSCOLORVERTEX vertices[] = {
		{150.0f,  50.0f, 0.5f, 1.0f, D3DCOLOR_XRGB(255,0,0)},
		{250.0f, 250.0f, 0.5f, 1.0f, D3DCOLOR_XRGB(0,255,0)},
		{ 50.0f, 250.0f, 0.5f, 1.0f, D3DCOLOR_XRGB(0,0,255)},
	};

	// Create a vertex decleration
	// Think of a vertex decleration as an object that describes a single custom
	// vertex.

	// 	typedef struct _D3DVERTEXELEMENT9
	// 	{
	// 		WORD    Stream;     // Stream index
	// 		WORD    Offset;     // Offset in the stream in bytes
	// 		BYTE    Type;       // Data type
	// 		BYTE    Method;     // Processing method
	// 		BYTE    Usage;      // Semantics
	// 		BYTE    UsageIndex; // Semantic index
	// 	} D3DVERTEXELEMENT9, *LPD3DVERTEXELEMENT9;

	// Example 1: Tutorial 1 of the DirectX SDK
	// using weighted position (aka screen coordinates) and colors but without
	// using the Fixed Pipeline
	D3DVERTEXELEMENT9 PosColorVertexElements[] = {
		{0, 0,  D3DDECLTYPE_FLOAT4,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_POSITIONT,	0},
		{0, 16, D3DDECLTYPE_D3DCOLOR,	D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_COLOR,		0},
		D3DDECL_END()
	};

#if 0
	// Example 2: If you want to add UV it would become something like this:
	D3DVERTEXELEMENT9 PosColorUVVertexElements[] = {
		{0, 0,  D3DDECLTYPE_FLOAT4,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_POSITIONT,	0},
		{0, 16, D3DDECLTYPE_D3DCOLOR,	D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_COLOR,		0},
		{0, 20, D3DDECLTYPE_FLOAT2,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_TEXCOORD,	0},
		D3DDECL_END()
	};
	// Example 3: And if you want UVs first
	D3DVERTEXELEMENT9 PosColorNormalVertexElements[] = {
		{0, 0,		D3DDECLTYPE_FLOAT2,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_TEXCOORD,	0},
		{0, 8,		D3DDECLTYPE_FLOAT4,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_POSITIONT,	0},
		{0, 8+16,	D3DDECLTYPE_D3DCOLOR,	D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_COLOR,		0},
		D3DDECL_END()
	};
	// Example 4: And if you want to send two UV's
	D3DVERTEXELEMENT9 PosColorNormalVertexElements[] = {
		{0, 0,  D3DDECLTYPE_FLOAT4,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_POSITIONT,	0},
		{0, 16, D3DDECLTYPE_D3DCOLOR,	D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_COLOR,		0},
		{0, 20, D3DDECLTYPE_FLOAT2,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_TEXCOORD,	0}, // Maps to TEXCOORD0 in shader
		{1, 28, D3DDECLTYPE_FLOAT2,		D3DDECLMETHOD_DEFAULT, D3DDECLUSAGE_TEXCOORD,	0},	// Maps to TEXCOORD1 in shader
		D3DDECL_END()
	};
#endif

	IDirect3DVertexDeclaration9* vertexDecleration = 0;
	device->CreateVertexDeclaration(PosColorVertexElements, &amp;vertexDecleration);
	device->SetVertexDeclaration(vertexDecleration);

	// Create vertex buffer
	IDirect3DVertexBuffer9*  vertexBuffer;
	device->CreateVertexBuffer(
		3*sizeof(POSCOLORVERTEX),
		0,
		0,								// DON'T pass the FVF code if you are using vertex decleration
		D3DPOOL_DEFAULT,
		&amp;vertexBuffer,
		0);

	// Fill the vertex buffer
	void* pVertices = 0;
	vertexBuffer->Lock(0, sizeof(vertices), (void**)&amp;pVertices, 0);
	memcpy(pVertices, vertices, sizeof(vertices));
	vertexBuffer->Unlock();

	bool keepRunning = true;

	while(keepRunning)
	{
		// Render
		device->Clear(0, 0, D3DCLEAR_TARGET, D3DCOLOR_XRGB(0,0,0), 1.0f, 0 );
		device->BeginScene();
		// Rendering of scene objects happens here
		// 1. Set the vertex decleration
		// 2. Set the stream source
		device->SetVertexDeclaration(vertexDecleration);
		device->SetStreamSource(0, vertexBuffer, 0, sizeof(POSCOLORVERTEX));
		device->DrawPrimitive(D3DPT_TRIANGLELIST, 0, 1);
		// End the scene
		device->EndScene();
		device->Present(0,0,0,0);

		if (PeekMessage(&amp;msg, NULL, 0, 0, PM_REMOVE))
		{
			if(msg.message == WM_QUIT) keepRunning = false;
			else
			{
				TranslateMessage (&amp;msg);
				DispatchMessage (&amp;msg);
			}
		}
	}

	vertexBuffer->Release();
	vertexDecleration->Release();
	device->Release();
	d3d9->Release();

	return msg.wParam;
}
LRESULT CALLBACK WndProc (HWND hwnd, UINT message, WPARAM wParam, LPARAM lParam)
{
	switch (message)
	{
	case WM_DESTROY:
		{
			PostQuitMessage (0);
			return (0);
		}break;
	}
	return DefWindowProc (hwnd, message, wParam, lParam);
}

Anyway I have decided to take it on and here is the result. You can download the source code here: TorusDX.zip.I have not commented it, but it is pretty straight forward. The texture that I used is from Dilbert.

If you would further apply the trick that is described on the 26 slide of Optimizing Direct X On Multi Core Architectures then I'm certain you can create something very flexible.

For example: If you need a vertex buffer, you lock the RenderingThread using [cci_cpp]RenderingThread::Lock[/cci_cpp] which will only be released once the [cci_cpp]CRITICAL_SECTION[/cci_cpp] has been released by another thread. Then you could ask the RenderingThread to create a wrapper of [cci_cpp]IDirect3DVertexBuffer9[/cci_cpp] which has added function that it will buffer everything and only update [cci_cpp]IDirect3DVertexBuffer9[/cci_cpp] inside the RenderingThread. If done correct you can easily multithread without having to worry about the following error message:

[ccWN_text]Direct3D9: (WARN) evice that was created without D3DCREATE_MULTITHREADED is being used by a thread other than the creation thread.[/ccWN_text]

You can download the source code here: DirectXMultiThreaded.zip (source only)

Anyhow, as a programmer I always want to reinvent the wheel, not because I think I know better or can do a better job, but more because I want to get familiar with. By know I have rewritten a lot of my own engines because there was always something missing here or there.

Is DXUT better than my own engines? Maybe, but DXUT is not an engine, it's a template, you could even combine DXUT with few of my engines. The only thing it does is creating structure in your application (by events like OnDeviceCreate, OnDeviceDestroy, OnDeviceReset, etc) and further it creates the window for you.

You also got access to a lot of other features, but they are optional. The only thing I dislike is the fact it includes DX10 specific elements in it, which you don't always want. I believe that a earlier version would allow you to use a define to disable it and else you could add it back yourself.