Cuda入门代码

Cuda入门代码

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.h>
#include <stdlib.h>

__global__ void VecAdd(float* A, float* B, float* C, int N){
    printf("Debug: blockDim.x %d blockIdx.x %d  threadIdx.x %d\n", blockDim.x, blockIdx.x, threadIdx.x);
    int i = blockDim.x * blockIdx.x + threadIdx.x;
    if (i < N)
        C[i] = A[i] + B[i];
}




int main(){

    const int N = 5;
    size_t size = N * sizeof(float);

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

    for (int i = 0; i < N; i++){
        h_A[i] = i + 1;
        h_B[i] = 5 - i;
        h_C[i] = 0;
    }


    //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 kernal
    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
    cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    for (int i = 0; i < N; i++){
        printf("%f%c", h_A[i], i == N - 1 ? '\n' : ' ');
    }

    for (int i = 0; i < N; i++){
        printf("%f%c", h_B[i], i == N - 1 ? '\n' : ' ');
    }

    for (int i = 0; i < N; i++){
        printf("%f%c", h_C[i], i == N - 1 ? '\n' : ' ');
    }

    //Free device memory
    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);

    //Free host memory
    free(h_A);
    free(h_B);
    free(h_C);

    system("pause");
    return 0;
}