// Kernel definition
__global__ void VecAdd(float* A, float* B, float* C)
{
    int i = threadIdx.x;
    C[i] = A[i] + B[i];
}

int main()
{
    ...
    // Kernel invocation with N threads
    VecAdd<<<1, N>>>(A, B, C);
    ...
}

// Kernel definition
__global__ void MatAdd(float A[N][N], float B[N][N],
                       float C[N][N])
{
    int i = threadIdx.x;
    int j = threadIdx.y;
    C[i][j] = A[i][j] + B[i][j];
}

int main()
{
    ...
    // Kernel invocation with one block of N * N * 1 threads
    int numBlocks = 1;
    dim3 threadsPerBlock(N, N);
    MatAdd<<<numBlocks, threadsPerBlock>>>(A, B, C);
    ...
}

nvcc x.cu
        -gencode arch=compute_50,code=sm_50
        -gencode arch=compute_60,code=sm_60
        -gencode arch=compute_70,code=\"compute_70,sm_70\"

// Device code
__global__ void VecAdd(float* A, float* B, float* C, int N)
{
    int i = blockDim.x * blockIdx.x + threadIdx.x;
    if (i < N)
        C[i] = A[i] + B[i];
}
            
// Host code
int main()
{
    int N = ...;
    size_t size = N * sizeof(float);

    // Allocate input vectors h_A and h_B in host memory
    float* h_A = (float*)malloc(size);
    float* h_B = (float*)malloc(size);
    float* h_C = (float*)malloc(size);

    // Initialize input vectors
    ...

    // Allocate vectors in device memory
    float* d_A;
    cudaMalloc(&d_A, size);
    float* d_B;
    cudaMalloc(&d_B, size);
    float* d_C;
    cudaMalloc(&d_C, size);

    // Copy vectors from host memory to device memory
    cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    // Invoke kernel
    int threadsPerBlock = 256;
    int blocksPerGrid =
            (N + threadsPerBlock - 1) / threadsPerBlock;
    VecAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, N);

    // Copy result from device memory to host memory
    // h_C contains the result in host memory
    cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    // Free device memory
    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
            
    // Free host memory
    ...
}

// Host code
int width = 64, height = 64;
float* devPtr;
size_t pitch;
cudaMallocPitch(&devPtr, &pitch,
                width * sizeof(float), height);
MyKernel<<<100, 512>>>(devPtr, pitch, width, height);

// Device code
__global__ void MyKernel(float* devPtr,
                         size_t pitch, int width, int height)
{
    for (int r = 0; r < height; ++r) {
        float* row = (float*)((char*)devPtr + r * pitch);
        for (int c = 0; c < width; ++c) {
            float element = row[c];
        }
    }
}

// Host code
int width = 64, height = 64, depth = 64;
cudaExtent extent = make_cudaExtent(width * sizeof(float),
                                    height, depth);
cudaPitchedPtr devPitchedPtr;
cudaMalloc3D(&devPitchedPtr, extent);
MyKernel<<<100, 512>>>(devPitchedPtr, width, height, depth);

// Device code
__global__ void MyKernel(cudaPitchedPtr devPitchedPtr,
                         int width, int height, int depth)
{
    char* devPtr = devPitchedPtr.ptr;
    size_t pitch = devPitchedPtr.pitch;
    size_t slicePitch = pitch * height;
    for (int z = 0; z < depth; ++z) {
        char* slice = devPtr + z * slicePitch;
        for (int y = 0; y < height; ++y) {
            float* row = (float*)(slice + y * pitch);
            for (int x = 0; x < width; ++x) {
                float element = row[x];
            }
        }
    }
}

__constant__ float constData[256];
float data[256];
cudaMemcpyToSymbol(constData, data, sizeof(data));
cudaMemcpyFromSymbol(data, constData, sizeof(data));

__device__ float devData;
float value = 3.14f;
cudaMemcpyToSymbol(devData, &value, sizeof(float));

__device__ float* devPointer;
float* ptr;
cudaMalloc(&ptr, 256 * sizeof(float));
cudaMemcpyToSymbol(devPointer, &ptr, sizeof(ptr));

cudaGetDeviceProperties(&prop, device_id);                
size_t size = min(int(prop.l2CacheSize * 0.75), prop.persistingL2CacheMaxSize);
cudaDeviceSetLimit(cudaLimitPersistingL2CacheSize, size); /* set-aside 3/4 of L2 cache for persisting accesses or the max allowed*/ 

cudaStreamAttrValue stream_attribute;                                         // Stream level attributes data structure
stream_attribute.accessPolicyWindow.base_ptr  = reinterpret_cast<void*>(ptr); // Global Memory data pointer
stream_attribute.accessPolicyWindow.num_bytes = num_bytes;                    // Number of bytes for persistence access.
                                                                              // (Must be less than cudaDeviceProp::accessPolicyMaxWindowSize)
stream_attribute.accessPolicyWindow.hitRatio  = 0.6;                          // Hint for cache hit ratio
stream_attribute.accessPolicyWindow.hitProp   = cudaAccessPropertyPersisting; // Type of access property on cache hit
stream_attribute.accessPolicyWindow.missProp  = cudaAccessPropertyStreaming;  // Type of access property on cache miss.

//Set the attributes to a CUDA stream of type cudaStream_t
cudaStreamSetAttribute(stream, cudaStreamAttributeAccessPolicyWindow, &stream_attribute); 

cudaKernelNodeAttrValue node_attribute;                                     // Kernel level attributes data structure
node_attribute.accessPolicyWindow.base_ptr  = reinterpret_cast<void*>(ptr); // Global Memory data pointer
node_attribute.accessPolicyWindow.num_bytes = num_bytes;                    // Number of bytes for persistence access.
                                                                            // (Must be less than cudaDeviceProp::accessPolicyMaxWindowSize)
node_attribute.accessPolicyWindow.hitRatio  = 0.6;                          // Hint for cache hit ratio
node_attribute.accessPolicyWindow.hitProp   = cudaAccessPropertyPersisting; // Type of access property on cache hit
node_attribute.accessPolicyWindow.missProp  = cudaAccessPropertyStreaming;  // Type of access property on cache miss.
                                    
//Set the attributes to a CUDA Graph Kernel node of type cudaGraphNode_t
cudaGraphKernelNodeSetAttribute(node, cudaKernelNodeAttributeAccessPolicyWindow, &node_attribute); 

cudaStream_t stream;
cudaStreamCreate(&stream);                                                                  // Create CUDA stream

cudaDeviceProp prop;                                                                        // CUDA device properties variable
cudaGetDeviceProperties( &prop, device_id);                                                 // Query GPU properties
size_t size = min( int(prop.l2CacheSize * 0.75) , prop.persistingL2CacheMaxSize );
cudaDeviceSetLimit( cudaLimitPersistingL2CacheSize, size);                                  // set-aside 3/4 of L2 cache for persisting accesses or the max allowed

size_t window_size = min(prop.accessPolicyMaxWindowSize, num_bytes);                        // Select minimum of user defined num_bytes and max window size.

cudaStreamAttrValue stream_attribute;                                                       // Stream level attributes data structure
stream_attribute.accessPolicyWindow.base_ptr  = reinterpret_cast<void*>(data1);               // Global Memory data pointer
stream_attribute.accessPolicyWindow.num_bytes = window_size;                                // Number of bytes for persistence access
stream_attribute.accessPolicyWindow.hitRatio  = 0.6;                                        // Hint for cache hit ratio
stream_attribute.accessPolicyWindow.hitProp   = cudaAccessPropertyPersisting;               // Persistence Property
stream_attribute.accessPolicyWindow.missProp  = cudaAccessPropertyStreaming;                // Type of access property on cache miss

cudaStreamSetAttribute(stream, cudaStreamAttributeAccessPolicyWindow, &stream_attribute);   // Set the attributes to a CUDA Stream

for(int i = 0; i < 10; i++) {
    cuda_kernelA<<<grid_size,block_size,0,stream>>>(data1);                                 // This data1 is used by a kernel multiple times
}                                                                                           // [data1 + num_bytes) benefits from L2 persistence
cuda_kernelB<<<grid_size,block_size,0,stream>>>(data1);                                     // A different kernel in the same stream can also benefit
                                                                                            // from the persistence of data1

stream_attribute.accessPolicyWindow.num_bytes = 0;                                          // Setting the window size to 0 disable it
cudaStreamSetAttribute(stream, cudaStreamAttributeAccessPolicyWindow, &stream_attribute);   // Overwrite the access policy attribute to a CUDA Stream
cudaCtxResetPersistingL2Cache();                                                            // Remove any persistent lines in L2 

cuda_kernelC<<<grid_size,block_size,0,stream>>>(data2);                                     // data2 can now benefit from full L2 in normal mode

enum cudaLimit {
    /* other fields not shown */
    cudaLimitPersistingL2CacheSize
}; 

// Matrices are stored in row-major order:
// M(row, col) = *(M.elements + row * M.width + col)
typedef struct {
    int width;
    int height;
    float* elements;
} Matrix;

// Thread block size
#define BLOCK_SIZE 16

// Forward declaration of the matrix multiplication kernel
__global__ void MatMulKernel(const Matrix, const Matrix, Matrix);

// Matrix multiplication - Host code
// Matrix dimensions are assumed to be multiples of BLOCK_SIZE
void MatMul(const Matrix A, const Matrix B, Matrix C)
{
    // Load A and B to device memory
    Matrix d_A;
    d_A.width = A.width; d_A.height = A.height;
    size_t size = A.width * A.height * sizeof(float);
    cudaMalloc(&d_A.elements, size);
    cudaMemcpy(d_A.elements, A.elements, size,
               cudaMemcpyHostToDevice);
    Matrix d_B;
    d_B.width = B.width; d_B.height = B.height;
    size = B.width * B.height * sizeof(float);
    cudaMalloc(&d_B.elements, size);
    cudaMemcpy(d_B.elements, B.elements, size,
               cudaMemcpyHostToDevice);

    // Allocate C in device memory
    Matrix d_C;
    d_C.width = C.width; d_C.height = C.height;
    size = C.width * C.height * sizeof(float);
    cudaMalloc(&d_C.elements, size);

    // Invoke kernel
    dim3 dimBlock(BLOCK_SIZE, BLOCK_SIZE);
    dim3 dimGrid(B.width / dimBlock.x, A.height / dimBlock.y);
    MatMulKernel<<<dimGrid, dimBlock>>>(d_A, d_B, d_C);

    // Read C from device memory
    cudaMemcpy(C.elements, d_C.elements, size,
               cudaMemcpyDeviceToHost);

    // Free device memory
    cudaFree(d_A.elements);
    cudaFree(d_B.elements);
    cudaFree(d_C.elements);
}

// Matrix multiplication kernel called by MatMul()
__global__ void MatMulKernel(Matrix A, Matrix B, Matrix C)
{
    // Each thread computes one element of C
    // by accumulating results into Cvalue
    float Cvalue = 0;
    int row = blockIdx.y * blockDim.y + threadIdx.y;
    int col = blockIdx.x * blockDim.x + threadIdx.x;
    for (int e = 0; e < A.width; ++e)
        Cvalue += A.elements[row * A.width + e]
                * B.elements[e * B.width + col];
    C.elements[row * C.width + col] = Cvalue;
}

// Matrices are stored in row-major order:
// M(row, col) = *(M.elements + row * M.stride + col)
typedef struct {
    int width;
    int height;
    int stride; 
    float* elements;
} Matrix;

// Get a matrix element
__device__ float GetElement(const Matrix A, int row, int col)
{
    return A.elements[row * A.stride + col];
}

// Set a matrix element
__device__ void SetElement(Matrix A, int row, int col,
                           float value)
{
    A.elements[row * A.stride + col] = value;
}

// Get the BLOCK_SIZExBLOCK_SIZE sub-matrix Asub of A that is
// located col sub-matrices to the right and row sub-matrices down
// from the upper-left corner of A
 __device__ Matrix GetSubMatrix(Matrix A, int row, int col) 
{
    Matrix Asub;
    Asub.width    = BLOCK_SIZE;
    Asub.height   = BLOCK_SIZE;
    Asub.stride   = A.stride;
    Asub.elements = &A.elements[A.stride * BLOCK_SIZE * row
                                         + BLOCK_SIZE * col];
    return Asub;
}

// Thread block size
#define BLOCK_SIZE 16

// Forward declaration of the matrix multiplication kernel
__global__ void MatMulKernel(const Matrix, const Matrix, Matrix);

// Matrix multiplication - Host code
// Matrix dimensions are assumed to be multiples of BLOCK_SIZE
void MatMul(const Matrix A, const Matrix B, Matrix C)
{
    // Load A and B to device memory
    Matrix d_A;
    d_A.width = d_A.stride = A.width; d_A.height = A.height;
    size_t size = A.width * A.height * sizeof(float);
    cudaMalloc(&d_A.elements, size);
    cudaMemcpy(d_A.elements, A.elements, size,
               cudaMemcpyHostToDevice);
    Matrix d_B;
    d_B.width = d_B.stride = B.width; d_B.height = B.height;
    size = B.width * B.height * sizeof(float);
    cudaMalloc(&d_B.elements, size);
    cudaMemcpy(d_B.elements, B.elements, size,
    cudaMemcpyHostToDevice);

    // Allocate C in device memory
    Matrix d_C;
    d_C.width = d_C.stride = C.width; d_C.height = C.height;
    size = C.width * C.height * sizeof(float);
    cudaMalloc(&d_C.elements, size);

    // Invoke kernel
    dim3 dimBlock(BLOCK_SIZE, BLOCK_SIZE);
    dim3 dimGrid(B.width / dimBlock.x, A.height / dimBlock.y);
    MatMulKernel<<<dimGrid, dimBlock>>>(d_A, d_B, d_C);

    // Read C from device memory
    cudaMemcpy(C.elements, d_C.elements, size,
               cudaMemcpyDeviceToHost);

    // Free device memory
    cudaFree(d_A.elements);
    cudaFree(d_B.elements);
    cudaFree(d_C.elements);
}

// Matrix multiplication kernel called by MatMul()
 __global__ void MatMulKernel(Matrix A, Matrix B, Matrix C)
{
    // Block row and column
    int blockRow = blockIdx.y;
    int blockCol = blockIdx.x;

    // Each thread block computes one sub-matrix Csub of C
    Matrix Csub = GetSubMatrix(C, blockRow, blockCol);

    // Each thread computes one element of Csub
    // by accumulating results into Cvalue
    float Cvalue = 0;

    // Thread row and column within Csub
    int row = threadIdx.y;
    int col = threadIdx.x;

    // Loop over all the sub-matrices of A and B that are
    // required to compute Csub
    // Multiply each pair of sub-matrices together
    // and accumulate the results
    for (int m = 0; m < (A.width / BLOCK_SIZE); ++m) {

        // Get sub-matrix Asub of A
        Matrix Asub = GetSubMatrix(A, blockRow, m);

        // Get sub-matrix Bsub of B
        Matrix Bsub = GetSubMatrix(B, m, blockCol);

        // Shared memory used to store Asub and Bsub respectively
        __shared__ float As[BLOCK_SIZE][BLOCK_SIZE];
        __shared__ float Bs[BLOCK_SIZE][BLOCK_SIZE];

        // Load Asub and Bsub from device memory to shared memory
        // Each thread loads one element of each sub-matrix
        As[row][col] = GetElement(Asub, row, col);
        Bs[row][col] = GetElement(Bsub, row, col);

        // Synchronize to make sure the sub-matrices are loaded
        // before starting the computation
        __syncthreads();
        // Multiply Asub and Bsub together
        for (int e = 0; e < BLOCK_SIZE; ++e)
            Cvalue += As[row][e] * Bs[e][col];

        // Synchronize to make sure that the preceding
        // computation is done before loading two new
        // sub-matrices of A and B in the next iteration
        __syncthreads();
    }

    // Write Csub to device memory
    // Each thread writes one element
    SetElement(Csub, row, col, Cvalue);
}

cudaStream_t stream[2];
for (int i = 0; i < 2; ++i)
    cudaStreamCreate(&stream[i]);
float* hostPtr;
cudaMallocHost(&hostPtr, 2 * size);

for (int i = 0; i < 2; ++i) {
    cudaMemcpyAsync(inputDevPtr + i * size, hostPtr + i * size,
                    size, cudaMemcpyHostToDevice, stream[i]);
    MyKernel <<<100, 512, 0, stream[i]>>>
          (outputDevPtr + i * size, inputDevPtr + i * size, size);
    cudaMemcpyAsync(hostPtr + i * size, outputDevPtr + i * size,
                    size, cudaMemcpyDeviceToHost, stream[i]);
}

for (int i = 0; i < 2; ++i)
    cudaStreamDestroy(stream[i]);

for (int i = 0; i < 2; ++i)
    cudaMemcpyAsync(inputDevPtr + i * size, hostPtr + i * size,
                    size, cudaMemcpyHostToDevice, stream[i]);
for (int i = 0; i < 2; ++i)
    MyKernel<<<100, 512, 0, stream[i]>>>
          (outputDevPtr + i * size, inputDevPtr + i * size, size);
for (int i = 0; i < 2; ++i)
    cudaMemcpyAsync(hostPtr + i * size, outputDevPtr + i * size,
                    size, cudaMemcpyDeviceToHost, stream[i]);

void CUDART_CB MyCallback(cudaStream_t stream, cudaError_t status, void *data){
    printf("Inside callback %d\n", (size_t)data);
}
...
for (size_t i = 0; i < 2; ++i) {
    cudaMemcpyAsync(devPtrIn[i], hostPtr[i], size, cudaMemcpyHostToDevice, stream[i]);
    MyKernel<<<100, 512, 0, stream[i]>>>(devPtrOut[i], devPtrIn[i], size);
    cudaMemcpyAsync(hostPtr[i], devPtrOut[i], size, cudaMemcpyDeviceToHost, stream[i]);
    cudaLaunchHostFunc(stream[i], MyCallback, (void*)i);
}

// get the range of stream priorities for this device
int priority_high, priority_low;
cudaDeviceGetStreamPriorityRange(&priority_low, &priority_high);
// create streams with highest and lowest available priorities
cudaStream_t st_high, st_low;
cudaStreamCreateWithPriority(&st_high, cudaStreamNonBlocking, priority_high);
cudaStreamCreateWithPriority(&st_low, cudaStreamNonBlocking, priority_low);

// Create the graph - it starts out empty
cudaGraphCreate(&graph, 0);

// For the purpose of this example, we'll create
// the nodes separately from the dependencies to
// demonstrate that it can be done in two stages.
// Note that dependencies can also be specified 
// at node creation. 
cudaGraphAddKernelNode(&a, graph, NULL, 0, &nodeParams);
cudaGraphAddKernelNode(&b, graph, NULL, 0, &nodeParams);
cudaGraphAddKernelNode(&c, graph, NULL, 0, &nodeParams);
cudaGraphAddKernelNode(&d, graph, NULL, 0, &nodeParams);

// Now set up dependencies on each node
cudaGraphAddDependencies(graph, &a, &b, 1);     // A->B
cudaGraphAddDependencies(graph, &a, &c, 1);     // A->C
cudaGraphAddDependencies(graph, &b, &d, 1);     // B->D
cudaGraphAddDependencies(graph, &c, &d, 1);     // C->D

cudaGraph_t graph;

cudaStreamBeginCapture(stream);

kernel_A<<< ..., stream >>>(...);
kernel_B<<< ..., stream >>>(...);
libraryCall(stream);
kernel_C<<< ..., stream >>>(...);

cudaStreamEndCapture(stream, &graph);

// stream1 is the origin stream
cudaStreamBeginCapture(stream1);

kernel_A<<< ..., stream1 >>>(...);

// Fork into stream2
cudaEventRecord(event1, stream1);
cudaStreamWaitEvent(stream2, event1);

kernel_B<<< ..., stream1 >>>(...);
kernel_C<<< ..., stream2 >>>(...);

// Join stream2 back to origin stream (stream1)
cudaEventRecord(event2, stream2);
cudaStreamWaitEvent(stream1, event2);

kernel_D<<< ..., stream1 >>>(...);

// End capture in the origin stream
cudaStreamEndCapture(stream1, &graph);

// stream1 and stream2 no longer in capture mode  

cudaGraphExec_t graphExec = NULL;

for (int i = 0; i < 10; i++) {
    cudaGraph_t graph;
    cudaGraphExecUpdateResult updateResult;
    cudaGraphNode_t errorNode;

    // In this example we use stream capture to create the graph.
    // You can also use the Graph API to produce a graph.
    cudaStreamBeginCapture(stream, cudaStreamCaptureModeGlobal);

    // Call a user-defined, stream based workload, for example
    do_cuda_work(stream);

    cudaStreamEndCapture(stream, &graph);

    // If we've already instantiated the graph, try to update it directly
    // and avoid the instantiation overhead
    if (graphExec != NULL) {
        // If the graph fails to update, errorNode will be set to the
        // node causing the failure and updateResult will be set to a
        // reason code.
        cudaGraphExecUpdate(graphExec, graph, &errorNode, &updateResult);
    }

    // Instantiate during the first iteration or whenever the update
    // fails for any reason
    if (graphExec == NULL || updateResult != cudaGraphExecUpdateSuccess) {

        // If a previous update failed, destroy the cudaGraphExec_t
        // before re-instantiating it
        if (graphExec != NULL) {
            cudaGraphExecDestroy(graphExec);
        }   
        // Instantiate graphExec from graph. The error node and
        // error message parameters are unused here.
        cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0);
    }   

    cudaGraphDestroy(graph);
    cudaGraphLaunch(graphExec, stream);
    cudaStreamSynchronize(stream);
}

cudaEvent_t start, stop;
cudaEventCreate(&start);
cudaEventCreate(&stop);

cudaEventDestroy(start);
cudaEventDestroy(stop);

cudaEventRecord(start, 0);
for (int i = 0; i < 2; ++i) {
    cudaMemcpyAsync(inputDev + i * size, inputHost + i * size,
                    size, cudaMemcpyHostToDevice, stream[i]);
    MyKernel<<<100, 512, 0, stream[i]>>>
               (outputDev + i * size, inputDev + i * size, size);
    cudaMemcpyAsync(outputHost + i * size, outputDev + i * size,
                    size, cudaMemcpyDeviceToHost, stream[i]);
}
cudaEventRecord(stop, 0);
cudaEventSynchronize(stop);
float elapsedTime;
cudaEventElapsedTime(&elapsedTime, start, stop);

int deviceCount;
cudaGetDeviceCount(&deviceCount);
int device;
for (device = 0; device < deviceCount; ++device) {
    cudaDeviceProp deviceProp;
    cudaGetDeviceProperties(&deviceProp, device);
    printf("Device %d has compute capability %d.%d.\n",
           device, deviceProp.major, deviceProp.minor);
}

size_t size = 1024 * sizeof(float);
cudaSetDevice(0);            // Set device 0 as current
float* p0;
cudaMalloc(&p0, size);       // Allocate memory on device 0
MyKernel<<<1000, 128>>>(p0); // Launch kernel on device 0
cudaSetDevice(1);            // Set device 1 as current
float* p1;
cudaMalloc(&p1, size);       // Allocate memory on device 1
MyKernel<<<1000, 128>>>(p1); // Launch kernel on device 1

cudaSetDevice(0);               // Set device 0 as current
cudaStream_t s0;
cudaStreamCreate(&s0);          // Create stream s0 on device 0
MyKernel<<<100, 64, 0, s0>>>(); // Launch kernel on device 0 in s0
cudaSetDevice(1);               // Set device 1 as current
cudaStream_t s1;
cudaStreamCreate(&s1);          // Create stream s1 on device 1
MyKernel<<<100, 64, 0, s1>>>(); // Launch kernel on device 1 in s1

// This kernel launch will fail:
MyKernel<<<100, 64, 0, s0>>>(); // Launch kernel on device 1 in s0

cudaSetDevice(0);                   // Set device 0 as current
float* p0;
size_t size = 1024 * sizeof(float);
cudaMalloc(&p0, size);              // Allocate memory on device 0
MyKernel<<<1000, 128>>>(p0);        // Launch kernel on device 0
cudaSetDevice(1);                   // Set device 1 as current
cudaDeviceEnablePeerAccess(0, 0);   // Enable peer-to-peer access
                                    // with device 0

// Launch kernel on device 1
// This kernel launch can access memory on device 0 at address p0
MyKernel<<<1000, 128>>>(p0);

cudaSetDevice(0);                   // Set device 0 as current
float* p0;
size_t size = 1024 * sizeof(float);
cudaMalloc(&p0, size);              // Allocate memory on device 0
cudaSetDevice(1);                   // Set device 1 as current
float* p1;
cudaMalloc(&p1, size);              // Allocate memory on device 1
cudaSetDevice(0);                   // Set device 0 as current
MyKernel<<<1000, 128>>>(p0);        // Launch kernel on device 0
cudaSetDevice(1);                   // Set device 1 as current
cudaMemcpyPeer(p1, 1, p0, 0, size); // Copy p0 to p1
MyKernel<<<1000, 128>>>(p1);   

struct cudaTextureDesc
{
    enum cudaTextureAddressMode addressMode[3];
    enum cudaTextureFilterMode  filterMode;
    enum cudaTextureReadMode    readMode;
    int                         sRGB;
    int                         normalizedCoords;
    unsigned int                maxAnisotropy;
    enum cudaTextureFilterMode  mipmapFilterMode;
    float                       mipmapLevelBias;
    float                       minMipmapLevelClamp;
    float                       maxMipmapLevelClamp;
};

// Simple transformation kernel
__global__ void transformKernel(float* output,
                                cudaTextureObject_t texObj,
                                int width, int height,
                                float theta) 
{
    // Calculate normalized texture coordinates
    unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
    unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;

    float u = x / (float)width;
    float v = y / (float)height;

    // Transform coordinates
    u -= 0.5f;
    v -= 0.5f;
    float tu = u * cosf(theta) - v * sinf(theta) + 0.5f;
    float tv = v * cosf(theta) + u * sinf(theta) + 0.5f;

    // Read from texture and write to global memory
    output[y * width + x] = tex2D<float>(texObj, tu, tv);
}
// Host code
int main()
{
    const int height = 1024;
    const int width = 1024;
    float angle = 0.5;

    // Allocate and set some host data
    float *h_data = (float *)std::malloc(sizeof(float) * width * height);
    for (int i = 0; i < height * width; ++i)
        h_data[i] = i;

    // Allocate CUDA array in device memory
    cudaChannelFormatDesc channelDesc =
        cudaCreateChannelDesc(32, 0, 0, 0, cudaChannelFormatKindFloat);
    cudaArray_t cuArray;
    cudaMallocArray(&cuArray, &channelDesc, width, height);

    // Set pitch of the source (the width in memory in bytes of the 2D array pointed
    // to by src, including padding), we dont have any padding
    const size_t spitch = width * sizeof(float);
    // Copy data located at address h_data in host memory to device memory
    cudaMemcpy2DToArray(cuArray, 0, 0, h_data, spitch, width * sizeof(float),
                        height, cudaMemcpyHostToDevice);

    // Specify texture
    struct cudaResourceDesc resDesc;
    memset(&resDesc, 0, sizeof(resDesc));
    resDesc.resType = cudaResourceTypeArray;
    resDesc.res.array.array = cuArray;

    // Specify texture object parameters
    struct cudaTextureDesc texDesc;
    memset(&texDesc, 0, sizeof(texDesc));
    texDesc.addressMode[0] = cudaAddressModeWrap;
    texDesc.addressMode[1] = cudaAddressModeWrap;
    texDesc.filterMode = cudaFilterModeLinear;
    texDesc.readMode = cudaReadModeElementType;
    texDesc.normalizedCoords = 1;

    // Create texture object
    cudaTextureObject_t texObj = 0;
    cudaCreateTextureObject(&texObj, &resDesc, &texDesc, NULL);

    // Allocate result of transformation in device memory
    float *output;
    cudaMalloc(&output, width * height * sizeof(float));

    // Invoke kernel
    dim3 threadsperBlock(16, 16);
    dim3 numBlocks((width + threadsperBlock.x - 1) / threadsperBlock.x,
                    (height + threadsperBlock.y - 1) / threadsperBlock.y);
    transformKernel<<<numBlocks, threadsperBlock>>>(output, texObj, width, height,
                                                    angle);
    // Copy data from device back to host
    cudaMemcpy(h_data, output, width * height * sizeof(float),
                cudaMemcpyDeviceToHost);

    // Destroy texture object
    cudaDestroyTextureObject(texObj);

    // Free device memory
    cudaFreeArray(cuArray);
    cudaFree(output);

    // Free host memory
    free(h_data);

    return 0;
}

texture<DataType, Type, ReadMode> texRef;

struct textureReference {
    int                          normalized;
    enum cudaTextureFilterMode   filterMode;
    enum cudaTextureAddressMode  addressMode[3];
    struct cudaChannelFormatDesc channelDesc;
    int                          sRGB;
    unsigned int                 maxAnisotropy;
    enum cudaTextureFilterMode   mipmapFilterMode;
    float                        mipmapLevelBias;
    float                        minMipmapLevelClamp;
    float                        maxMipmapLevelClamp;
}

struct cudaChannelFormatDesc {
  int x, y, z, w;
  enum cudaChannelFormatKind f;
};
其中 x、y、z 和 w 等于返回值的每个分量的位数，f 为：

*cudaChannelFormatKindSigned 如果这些组件是有符号整数类型，
*cudaChannelFormatKindUnsigned 如果它们是无符号整数类型，
*cudaChannelFormatKindFloat 如果它们是浮点类型。

texture<float, cudaTextureType2D,
        cudaReadModeElementType> texRef;
textureReference* texRefPtr;
cudaGetTextureReference(&texRefPtr, &texRef);
cudaChannelFormatDesc channelDesc =
                             cudaCreateChannelDesc<float>();
size_t offset;
cudaBindTexture2D(&offset, texRefPtr, devPtr, &channelDesc,
                  width, height, pitch);

texture<float, cudaTextureType2D,
        cudaReadModeElementType> texRef;
cudaChannelFormatDesc channelDesc =
                             cudaCreateChannelDesc<float>();
size_t offset;
cudaBindTexture2D(&offset, texRef, devPtr, channelDesc,
                  width, height, pitch);

texture<float, cudaTextureType2D,
        cudaReadModeElementType> texRef;
textureReference* texRefPtr;
cudaGetTextureReference(&texRefPtr, &texRef);
cudaChannelFormatDesc channelDesc;
cudaGetChannelDesc(&channelDesc, cuArray);
cudaBindTextureToArray(texRef, cuArray, &channelDesc);

texture<float, cudaTextureType2D,
        cudaReadModeElementType> texRef;
cudaBindTextureToArray(texRef, cuArray);

// 2D float texture
texture<float, cudaTextureType2D, cudaReadModeElementType> texRef;

// Simple transformation kernel
__global__ void transformKernel(float* output,
                                int width, int height,
                                float theta) 
{
    // Calculate normalized texture coordinates
    unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
    unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;

    float u = x / (float)width;
    float v = y / (float)height;

    // Transform coordinates
    u -= 0.5f;
    v -= 0.5f;
    float tu = u * cosf(theta) - v * sinf(theta) + 0.5f;
    float tv = v * cosf(theta) + u * sinf(theta) + 0.5f;


    // Read from texture and write to global memory
    output[y * width + x] = tex2D(texRef, tu, tv);
}

// Host code
int main()
{
    // Allocate CUDA array in device memory
    cudaChannelFormatDesc channelDesc =
               cudaCreateChannelDesc(32, 0, 0, 0,
                                     cudaChannelFormatKindFloat);
    cudaArray* cuArray;
    cudaMallocArray(&cuArray, &channelDesc, width, height);

    // Copy to device memory some data located at address h_data
    // in host memory 
    cudaMemcpyToArray(cuArray, 0, 0, h_data, size,
                      cudaMemcpyHostToDevice);

    // Set texture reference parameters
    texRef.addressMode[0] = cudaAddressModeWrap;
    texRef.addressMode[1] = cudaAddressModeWrap;
    texRef.filterMode     = cudaFilterModeLinear;
    texRef.normalized     = true;

    // Bind the array to the texture reference
    cudaBindTextureToArray(texRef, cuArray, channelDesc);

    // Allocate result of transformation in device memory
    float* output;
    cudaMalloc(&output, width * height * sizeof(float));

    // Invoke kernel
    dim3 dimBlock(16, 16);
    dim3 dimGrid((width  + dimBlock.x - 1) / dimBlock.x,
                 (height + dimBlock.y - 1) / dimBlock.y);
    transformKernel<<<dimGrid, dimBlock>>>(output, width, height,
                                           angle);

    // Free device memory
    cudaFreeArray(cuArray);
    cudaFree(output);

    return 0;
}

// Simple copy kernel
__global__ void copyKernel(cudaSurfaceObject_t inputSurfObj,
                           cudaSurfaceObject_t outputSurfObj,
                           int width, int height) 
{
    // Calculate surface coordinates
    unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
    unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
    if (x < width && y < height) {
        uchar4 data;
        // Read from input surface
        surf2Dread(&data,  inputSurfObj, x * 4, y);
        // Write to output surface
        surf2Dwrite(data, outputSurfObj, x * 4, y);
    }
}

// Host code
int main()
{
    const int height = 1024;
    const int width = 1024;

    // Allocate and set some host data
    unsigned char *h_data =
        (unsigned char *)std::malloc(sizeof(unsigned char) * width * height * 4);
    for (int i = 0; i < height * width * 4; ++i)
        h_data[i] = i;

    // Allocate CUDA arrays in device memory
    cudaChannelFormatDesc channelDesc =
        cudaCreateChannelDesc(8, 8, 8, 8, cudaChannelFormatKindUnsigned);
    cudaArray_t cuInputArray;
    cudaMallocArray(&cuInputArray, &channelDesc, width, height,
                    cudaArraySurfaceLoadStore);
    cudaArray_t cuOutputArray;
    cudaMallocArray(&cuOutputArray, &channelDesc, width, height,
                    cudaArraySurfaceLoadStore);

    // Set pitch of the source (the width in memory in bytes of the 2D array
    // pointed to by src, including padding), we dont have any padding
    const size_t spitch = 4 * width * sizeof(unsigned char);
    // Copy data located at address h_data in host memory to device memory
    cudaMemcpy2DToArray(cuInputArray, 0, 0, h_data, spitch,
                        4 * width * sizeof(unsigned char), height,
                        cudaMemcpyHostToDevice);

    // Specify surface
    struct cudaResourceDesc resDesc;
    memset(&resDesc, 0, sizeof(resDesc));
    resDesc.resType = cudaResourceTypeArray;

    // Create the surface objects
    resDesc.res.array.array = cuInputArray;
    cudaSurfaceObject_t inputSurfObj = 0;
    cudaCreateSurfaceObject(&inputSurfObj, &resDesc);
    resDesc.res.array.array = cuOutputArray;
    cudaSurfaceObject_t outputSurfObj = 0;
    cudaCreateSurfaceObject(&outputSurfObj, &resDesc);

    // Invoke kernel
    dim3 threadsperBlock(16, 16);
    dim3 numBlocks((width + threadsperBlock.x - 1) / threadsperBlock.x,
                    (height + threadsperBlock.y - 1) / threadsperBlock.y);
    copyKernel<<<numBlocks, threadsperBlock>>>(inputSurfObj, outputSurfObj, width,
                                                height);

    // Copy data from device back to host
    cudaMemcpy2DFromArray(h_data, spitch, cuOutputArray, 0, 0,
                            4 * width * sizeof(unsigned char), height,
                            cudaMemcpyDeviceToHost);

    // Destroy surface objects
    cudaDestroySurfaceObject(inputSurfObj);
    cudaDestroySurfaceObject(outputSurfObj);

    // Free device memory
    cudaFreeArray(cuInputArray);
    cudaFreeArray(cuOutputArray);

    // Free host memory
    free(h_data);

  return 0;
}

GLuint positionsVBO;
struct cudaGraphicsResource* positionsVBO_CUDA;

int main()
{
    // Initialize OpenGL and GLUT for device 0
    // and make the OpenGL context current
    ...
    glutDisplayFunc(display);

    // Explicitly set device 0
    cudaSetDevice(0);

    // Create buffer object and register it with CUDA
    glGenBuffers(1, &positionsVBO);
    glBindBuffer(GL_ARRAY_BUFFER, positionsVBO);
    unsigned int size = width * height * 4 * sizeof(float);
    glBufferData(GL_ARRAY_BUFFER, size, 0, GL_DYNAMIC_DRAW);
    glBindBuffer(GL_ARRAY_BUFFER, 0);
    cudaGraphicsGLRegisterBuffer(&positionsVBO_CUDA,
                                 positionsVBO,
                                 cudaGraphicsMapFlagsWriteDiscard);

    // Launch rendering loop
    glutMainLoop();

    ...
}

void display()
{
    // Map buffer object for writing from CUDA
    float4* positions;
    cudaGraphicsMapResources(1, &positionsVBO_CUDA, 0);
    size_t num_bytes; 
    cudaGraphicsResourceGetMappedPointer((void**)&positions,
                                         &num_bytes,  
                                         positionsVBO_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 buffer object
    cudaGraphicsUnmapResources(1, &positionsVBO_CUDA, 0);

    // Render from buffer object
    glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
    glBindBuffer(GL_ARRAY_BUFFER, positionsVBO);
    glVertexPointer(4, GL_FLOAT, 0, 0);
    glEnableClientState(GL_VERTEX_ARRAY);
    glDrawArrays(GL_POINTS, 0, width * height);
    glDisableClientState(GL_VERTEX_ARRAY);

    // Swap buffers
    glutSwapBuffers();
    glutPostRedisplay();
}
void deleteVBO()
{
    cudaGraphicsUnregisterResource(positionsVBO_CUDA);
    glDeleteBuffers(1, &positionsVBO);
}

__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;

    // calculate simple sine wave pattern
    float freq = 4.0f;
    float w = sinf(u * freq + time)
            * cosf(v * freq + time) * 0.5f;

    // Write positions
    positions[y * width + x] = make_float4(u, w, v, 1.0f);
}

IDirect3D9* D3D;
IDirect3DDevice9* device;
struct CUSTOMVERTEX {
    FLOAT x, y, z;
    DWORD color;
};
IDirect3DVertexBuffer9* positionsVB;
struct cudaGraphicsResource* positionsVB_CUDA;

int main()
{
    int dev;
    // Initialize Direct3D
    D3D = Direct3DCreate9Ex(D3D_SDK_VERSION);

    // Get a CUDA-enabled adapter
    unsigned int adapter = 0;
    for (; adapter < g_pD3D->GetAdapterCount(); adapter++) {
        D3DADAPTER_IDENTIFIER9 adapterId;
        g_pD3D->GetAdapterIdentifier(adapter, 0, &adapterId);
        if (cudaD3D9GetDevice(&dev, adapterId.DeviceName)
            == cudaSuccess)
            break;
    }

     // Create device
    ...
    D3D->CreateDeviceEx(adapter, D3DDEVTYPE_HAL, hWnd,
                        D3DCREATE_HARDWARE_VERTEXPROCESSING,
                        &params, NULL, &device);

    // Use the same device
    cudaSetDevice(dev);

    // Create vertex buffer and register it with CUDA
    unsigned int size = width * height * sizeof(CUSTOMVERTEX);
    device->CreateVertexBuffer(size, 0, D3DFVF_CUSTOMVERTEX,
                               D3DPOOL_DEFAULT, &positionsVB, 0);
    cudaGraphicsD3D9RegisterResource(&positionsVB_CUDA,
                                     positionsVB,
                                     cudaGraphicsRegisterFlagsNone);
    cudaGraphicsResourceSetMapFlags(positionsVB_CUDA,
                                    cudaGraphicsMapFlagsWriteDiscard);

    // Launch rendering loop
    while (...) {
        ...
        Render();
        ...
    }
    ...
}
void Render()
{
    // Map vertex buffer for writing from CUDA
    float4* positions;
    cudaGraphicsMapResources(1, &positionsVB_CUDA, 0);
    size_t num_bytes; 
    cudaGraphicsResourceGetMappedPointer((void**)&positions,
                                         &num_bytes,  
                                         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;

    // Calculate simple sine wave pattern
    float freq = 4.0f;
    float w = sinf(u * freq + time)
            * cosf(v * freq + time) * 0.5f;

    // Write positions
    positions[y * width + x] =
                make_float4(u, w, v, __int_as_float(0xff00ff00));
}

ID3D10Device* device;
struct CUSTOMVERTEX {
    FLOAT x, y, z;
    DWORD color;
};
ID3D10Buffer* positionsVB;
struct cudaGraphicsResource* positionsVB_CUDA;
            
int main()
{
    int dev;
    // 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;
        if (cudaD3D10GetDevice(&dev, adapter) == cudaSuccess)
            break;
        adapter->Release();
    }
    factory->Release();
            
    // Create swap chain and device
    ...
    D3D10CreateDeviceAndSwapChain(adapter, 
                                  D3D10_DRIVER_TYPE_HARDWARE, 0, 
                                  D3D10_CREATE_DEVICE_DEBUG,
                                  D3D10_SDK_VERSION, 
                                  &swapChainDesc, &swapChain,
                                  &device);
    adapter->Release();

    // Use the same device
    cudaSetDevice(dev);

    // Create vertex buffer and register it with CUDA
    unsigned int size = width * height * sizeof(CUSTOMVERTEX);
    D3D10_BUFFER_DESC bufferDesc;
    bufferDesc.Usage          = D3D10_USAGE_DEFAULT;
    bufferDesc.ByteWidth      = size;
    bufferDesc.BindFlags      = D3D10_BIND_VERTEX_BUFFER;
    bufferDesc.CPUAccessFlags = 0;
    bufferDesc.MiscFlags      = 0;
    device->CreateBuffer(&bufferDesc, 0, &positionsVB);
    cudaGraphicsD3D10RegisterResource(&positionsVB_CUDA,
                                      positionsVB,
                                      cudaGraphicsRegisterFlagsNone);
                                      cudaGraphicsResourceSetMapFlags(positionsVB_CUDA,
                                      cudaGraphicsMapFlagsWriteDiscard);

    // Launch rendering loop
    while (...) {
        ...
        Render();
        ...
    }
    ...
}
void Render()
{
    // Map vertex buffer for writing from CUDA
    float4* positions;
    cudaGraphicsMapResources(1, &positionsVB_CUDA, 0);
    size_t num_bytes; 
    cudaGraphicsResourceGetMappedPointer((void**)&positions,
                                         &num_bytes,  
                                         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;

    // Calculate simple sine wave pattern
    float freq = 4.0f;
    float w = sinf(u * freq + time)
            * cosf(v * freq + time) * 0.5f;
            
    // Write positions
    positions[y * width + x] =
                make_float4(u, w, v, __int_as_float(0xff00ff00));
}