3.3 CUDA 驱动 API（The CUDA Driver API）

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);

    // Initialize input vectors
    ...

    // Initialize
    cuInit(0);

    // Get number of devices supporting CUDA
    int deviceCount = 0;
    cuDeviceGetCount(&deviceCount);
    if (deviceCount == 0) {
        printf("There is no device supporting CUDA.\n");
        exit (0);
    }

    // Get handle for device 0
    CUdevice cuDevice;
    cuDeviceGet(&cuDevice, 0);

    // Create context
    CUcontext cuContext;
    cuCtxCreate(&cuContext, 0, cuDevice);

    // Create module from binary file
    CUmodule cuModule;
    cuModuleLoad(&cuModule, "VecAdd.ptx");

    // Allocate vectors in device memory
    CUdeviceptr d_A;
    cuMemAlloc(&d_A, size);
    CUdeviceptr d_B;
    cuMemAlloc(&d_B, size);
    CUdeviceptr d_C;
    cuMemAlloc(&d_C, size);

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

    // Get function handle from module
    CUfunction vecAdd;
    cuModuleGetFunction(&vecAdd, cuModule, "VecAdd");

    // Invoke kernel
    int threadsPerBlock = 256;
    int blocksPerGrid =
            (N + threadsPerBlock - 1) / threadsPerBlock;
    void* args[] = { &d_A, &d_B, &d_C, &N };
    cuLaunchKernel(vecAdd,
                   blocksPerGrid, 1, 1, threadsPerBlock, 1, 1,
                   0, 0, args, 0);

    ...
}

CUmodule cuModule;
cuModuleLoad(&cuModule, "myModule.ptx");
CUfunction myKernel;
cuModuleGetFunction(&myKernel, cuModule, "MyKernel");

#define BUFFER_SIZE 8192
CUmodule cuModule;
CUjit_option options[3];
void* values[3];
char* PTXCode = "some PTX code";
char error_log[BUFFER_SIZE];
int err;
options[0] = CU_JIT_ERROR_LOG_BUFFER;
values[0]  = (void*)error_log;
options[1] = CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES;
values[1]  = (void*)BUFFER_SIZE;
options[2] = CU_JIT_TARGET_FROM_CUCONTEXT;
values[2]  = 0;
err = cuModuleLoadDataEx(&cuModule, PTXCode, 3, options, values);
if (err != CUDA_SUCCESS)
    printf("Link error:\n%s\n", error_log);

#define BUFFER_SIZE 8192
CUmodule cuModule;
CUjit_option options[6];
void* values[6];
float walltime;
char error_log[BUFFER_SIZE], info_log[BUFFER_SIZE];
char* PTXCode0 = "some PTX code";
char* PTXCode1 = "some other PTX code";
CUlinkState linkState;
int err;
void* cubin;
size_t cubinSize;
options[0] = CU_JIT_WALL_TIME;
values[0] = (void*)&walltime;
options[1] = CU_JIT_INFO_LOG_BUFFER;
values[1] = (void*)info_log;
options[2] = CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES;
values[2] = (void*)BUFFER_SIZE;
options[3] = CU_JIT_ERROR_LOG_BUFFER;
values[3] = (void*)error_log;
options[4] = CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES;
values[4] = (void*)BUFFER_SIZE;
options[5] = CU_JIT_LOG_VERBOSE;
values[5] = (void*)1;
cuLinkCreate(6, options, values, &linkState);
err = cuLinkAddData(linkState, CU_JIT_INPUT_PTX,
                    (void*)PTXCode0, strlen(PTXCode0) + 1, 0, 0, 0, 0);
if (err != CUDA_SUCCESS)
    printf("Link error:\n%s\n", error_log);
err = cuLinkAddData(linkState, CU_JIT_INPUT_PTX,
                    (void*)PTXCode1, strlen(PTXCode1) + 1, 0, 0, 0, 0);
if (err != CUDA_SUCCESS)
    printf("Link error:\n%s\n", error_log);
cuLinkComplete(linkState, &cubin, &cubinSize);
printf("Link completed in %fms. Linker Output:\n%s\n", walltime, info_log);
cuModuleLoadData(cuModule, cubin);
cuLinkDestroy(linkState);

#define BUFFER_SIZE 8192
CUmodule cuModule;
CUjit_option options[3];
void* values[3];
char* cubinCode = "some cubin code";
char error_log[BUFFER_SIZE];
int err;
options[0] = CU_JIT_ERROR_LOG_BUFFER;
values[0]  = (void*)error_log;
options[1] = CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES;
values[1]  = (void*)BUFFER_SIZE;
options[2] = CU_JIT_BINARY_LOADER_THREAD_COUNT;
values[2]  = 0; // Use as many threads as CPUs on the machine
err = cuModuleLoadDataEx(&cuModule, cubinCode, 3, options, values);
if (err != CUDA_SUCCESS)
    printf("Link error:\n%s\n", error_log);

#define ALIGN_UP(offset, alignment) \
      (offset) = ((offset) + (alignment) - 1) & ~((alignment) - 1)

char paramBuffer[1024];
size_t paramBufferSize = 0;

#define ADD_TO_PARAM_BUFFER(value, alignment)                   \
    do {                                                        \
        paramBufferSize = ALIGN_UP(paramBufferSize, alignment); \
        memcpy(paramBuffer + paramBufferSize,                   \
               &(value), sizeof(value));                        \
        paramBufferSize += sizeof(value);                       \
    } while (0)

int i;
ADD_TO_PARAM_BUFFER(i, __alignof(i));
float4 f4;
ADD_TO_PARAM_BUFFER(f4, 16); // float4's alignment is 16
char c;
ADD_TO_PARAM_BUFFER(c, __alignof(c));
float f;
ADD_TO_PARAM_BUFFER(f, __alignof(f));
CUdeviceptr devPtr;
ADD_TO_PARAM_BUFFER(devPtr, __alignof(devPtr));
float2 f2;
ADD_TO_PARAM_BUFFER(f2, 8); // float2's alignment is 8

void* extra[] = {
    CU_LAUNCH_PARAM_BUFFER_POINTER, paramBuffer,
    CU_LAUNCH_PARAM_BUFFER_SIZE,    &paramBufferSize,
    CU_LAUNCH_PARAM_END
};
cuLaunchKernel(cuFunction,
               blockWidth, blockHeight, blockDepth,
               gridWidth, gridHeight, gridDepth,
               0, 0, 0, extra);

typedef struct {
    float  f;
    float4 f4;
} myStruct;

CUdeviceptr devPtr;
float* d_data;

// Allocation using driver API
cuMemAlloc(&devPtr, size);
d_data = (float*)devPtr;

// Allocation using runtime API
cudaMalloc(&d_data, size);
devPtr = (CUdeviceptr)d_data;