Direct3D 11 版本：
ID3D11Device* device;
struct CUSTOMVERTEX {
FLOAT x, y, z;
DWORD color;
};
ID3D11Buffer* positionsVB;
struct cudaGraphicsResource* positionsVB_CUDA;
int main() {
// Get a CUDA-enabled adapter
IDXGIFactory* factory;
CreateDXGIFactory(__uuidof(IDXGIFactory), (void**)&factory);
IDXGIAdapter* adapter = 0;
for (unsigned int i = 0; !adapter; ++i) {
if (FAILED(factory->EnumAdapters(i, &adapter))
break;
int dev;
if (cudaD3D11GetDevice(&dev, adapter) == cudaSuccess)
break;
adapter->Release();
}
factory->Release();
// Create swap chain and device
…
sFnPtr_D3D11CreateDeviceAndSwapChain(adapter, D3D11_DRIVER_TYPE_HARDWARE, 0, D3D11_CREATE_DEVICE_DEBUG, featureLevels, 3, D3D11_SDK_VERSION, &swapChainDesc, &swapChain, &device, &featureLevel, &deviceContext);
adapter->Release();
// Register device with CUDA
cudaD3D11SetDirect3DDevice(device);
// Create vertex buffer and register it with CUDA
unsigned int size = width * height * sizeof(CUSTOMVERTEX);
D3D11_BUFFER_DESC bufferDesc;
bufferDesc.Usage = D3D11_USAGE_DEFAULT;
bufferDesc.ByteWidth = size;
bufferDesc.BindFlags = D3D11_BIND_VERTEX_BUFFER;
bufferDesc.CPUAccessFlags = 0;
bufferDesc.MiscFlags = 0;
device->CreateBuffer(&bufferDesc, 0, &positionsVB);
cudaGraphicsD3D11RegisterResource(&positionsVB_CUDA,
positionsVB,
cudaGraphicsRegisterFlagsNone);
cudaGraphicsResourceSetMapFlags(positionsVB_CUDA,
struct CUSTOMVERTEX {
FLOAT x, y, z;
DWORD color;
};
ID3D11Buffer* positionsVB;
struct cudaGraphicsResource* positionsVB_CUDA;
int main() {
// Get a CUDA-enabled adapter
IDXGIFactory* factory;
CreateDXGIFactory(__uuidof(IDXGIFactory), (void**)&factory);
IDXGIAdapter* adapter = 0;
for (unsigned int i = 0; !adapter; ++i) {
if (FAILED(factory->EnumAdapters(i, &adapter))
break;
int dev;
if (cudaD3D11GetDevice(&dev, adapter) == cudaSuccess)
break;
adapter->Release();
}
factory->Release();
// Create swap chain and device
…
sFnPtr_D3D11CreateDeviceAndSwapChain(adapter, D3D11_DRIVER_TYPE_HARDWARE, 0, D3D11_CREATE_DEVICE_DEBUG, featureLevels, 3, D3D11_SDK_VERSION, &swapChainDesc, &swapChain, &device, &featureLevel, &deviceContext);
adapter->Release();
// Register device with CUDA
cudaD3D11SetDirect3DDevice(device);
// Create vertex buffer and register it with CUDA
unsigned int size = width * height * sizeof(CUSTOMVERTEX);
D3D11_BUFFER_DESC bufferDesc;
bufferDesc.Usage = D3D11_USAGE_DEFAULT;
bufferDesc.ByteWidth = size;
bufferDesc.BindFlags = D3D11_BIND_VERTEX_BUFFER;
bufferDesc.CPUAccessFlags = 0;
bufferDesc.MiscFlags = 0;
device->CreateBuffer(&bufferDesc, 0, &positionsVB);
cudaGraphicsD3D11RegisterResource(&positionsVB_CUDA,
positionsVB,
cudaGraphicsRegisterFlagsNone);
cudaGraphicsResourceSetMapFlags(positionsVB_CUDA,
// Execute kernel
dim3 dimBlock(16, 16, 1);
dim3 dimGrid(width / dimBlock.x, height / dimBlock.y, 1);
createVertices<<<dimGrid, dimBlock>>>(positions, time, width, height);
// Unmap vertex buffer
cudaGraphicsUnmapResources(1, &positionsVB_CUDA, 0);
// Draw and present
...
}
void releaseVB() {
cudaGraphicsUnregisterResource(positionsVB_CUDA);
positionsVB->Release();
}
__global__ void createVertices(float4* positions, float time, unsigned int width, unsigned int height){
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
// Calculate uv coordinates
float u = x / (float)width;
float v = y / (float)height;
u = u * 2.0f - 1.0f;
v = v * 2.0f - 1.0f;
dim3 dimBlock(16, 16, 1);
dim3 dimGrid(width / dimBlock.x, height / dimBlock.y, 1);
createVertices<<<dimGrid, dimBlock>>>(positions, time, width, height);
// Unmap vertex buffer
cudaGraphicsUnmapResources(1, &positionsVB_CUDA, 0);
// Draw and present
...
}
void releaseVB() {
cudaGraphicsUnregisterResource(positionsVB_CUDA);
positionsVB->Release();
}
__global__ void createVertices(float4* positions, float time, unsigned int width, unsigned int height){
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
// Calculate uv coordinates
float u = x / (float)width;
float v = y / (float)height;
u = u * 2.0f - 1.0f;
v = v * 2.0f - 1.0f;
