linux+cuda+例程

#include <stdio.h>
#include <assert.h>
#include <cuda_runtime.h>

__global__ void vectorAdd(const float *A, const float *B, float *C, int numElements) {
    int i = blockDim.x * blockIdx.x + threadIdx.x;

    if (i < numElements) {
        C[i] = A[i] + B[i];
    }
}

int main(void) {
    int numElements = 50000;
    size_t size = numElements * sizeof(float);

    float *h_A = (float *)malloc(size);
    float *h_B = (float *)malloc(size);
    float *h_C = (float *)malloc(size);

    for (int i = 0; i < numElements; ++i) {
        h_A[i] = rand() % 100;
        h_B[i] = rand() % 100;
    }

    float *d_A, *d_B, *d_C;

    cudaMalloc(&d_A, size);
    cudaMalloc(&d_B, size);
    cudaMalloc(&d_C, size);

    cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    int threadsPerBlock = 256;
    int blocksPerGrid = (numElements + threadsPerBlock - 1) / threadsPerBlock;

    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);

    cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    for (int i = 0; i < numElements; i++) {
        assert(h_A[i] + h_B[i] == h_C[i]);
    }

    printf("Test PASSED\n");

    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);
    free(h_A);
    free(h_B);
    free(h_C);

    return 0;
}

nvcc vectorAdd.cu -o vectorAdd

./vectorAdd