Function main

cpp/0_Introduction/vectorAddDrv/vectorAddDrv.cpp:75–192

Host code

// Host code
int main(int argc, char **argv)
{
    printf("Vector Addition (Driver API)\n");
    int               N = 50000, devID = 0;
    size_t            size            = N * sizeof(float);
    CUctxCreateParams ctxCreateParams = {};

    // Initialize
    checkCudaErrors(cuInit(0));

    cuDevice = findCudaDeviceDRV(argc, (const char **)argv);
    // Create context
    checkCudaErrors(cuCtxCreate(&cuContext, &ctxCreateParams, 0, cuDevice));

    // first search for the module path before we load the results
    string module_path;

    std::ostringstream fatbin;

    if (!findFatbinPath(FATBIN_FILE, module_path, argv, fatbin)) {
        exit(EXIT_FAILURE);
    }
    else {
        printf("> initCUDA loading module: <%s>\n", module_path.c_str());
    }

    if (!fatbin.str().size()) {
        printf("fatbin file empty. exiting..\n");
        exit(EXIT_FAILURE);
    }

    // Create module from binary file (FATBIN)
    checkCudaErrors(cuModuleLoadData(&cuModule, fatbin.str().c_str()));

    // Get function handle from module
    checkCudaErrors(cuModuleGetFunction(&vecAdd_kernel, cuModule, "VecAdd_kernel"));

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

    // Initialize input vectors
    RandomInit(h_A, N);
    RandomInit(h_B, N);

    // Allocate vectors in device memory
    checkCudaErrors(cuMemAlloc(&d_A, size));

    checkCudaErrors(cuMemAlloc(&d_B, size));

    checkCudaErrors(cuMemAlloc(&d_C, size));

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

    checkCudaErrors(cuMemcpyHtoD(d_B, h_B, size));