素人によるCUDAのお勉強。5

簡単な例としてベクトルの足し算を行います。CPUで同じ計算を実行し、その結果とGPUで計算をした結果があっているか確かめます。

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

#define CHECK(call)\
{\
    const cudaError_t error = call;\
    if (error != cudaSuccess)\
        {\
            printf("Error: %s:%d",__FILE__,__LINE__);\
            printf("code:%d, reason: %s\n", error, cudaGetErrorString(error));\
            exit(1);\
        }\
}

void checkResult(float *hostRef, float *gpuRef, const int N){
    double epsilon = 1.0E-8;
    bool match = 1;
    int i;
    for(i=0;i<N;i++){
	if(abs(hostRef[i] - gpuRef[i])>epsilon){
            match = 0;
            printf("Arrays do not match!\n");
            printf("host %5.2f gpu %5.2f at current %d\n",hostRef[i],gpuRef[i],i);
            break;
        }
    }
    if(match)printf("Arrays match\n\n");
}

void initialData(float *ip,int size){
    int i;
    time_t t;
    srand((unsigned) time(&t));

    for(i=0;i<size;i++){
        ip[i] = (float)( rand() & 0xFF)/10.0f;
    }
}

void sumArrayOnHost(float *A, float *B, float *C, const int N){
    int idx;
    for(idx=0;idx<N;idx++)
	C[idx] = A[idx] + B[idx];
}

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

int main(int argc, char **argv){
    printf("%s Starting.. \n", argv[0]);

    int dev = 0;
    cudaSetDevice(dev);

    int nElem = 32;
    printf("Vector size %d\n",nElem);

    size_t nBytes = nElem * sizeof(float);

    float *h_A, *h_B, *hostRef, *gpuRef;

    h_A = (float *)malloc(nBytes);
    h_B = (float *)malloc(nBytes);
    hostRef = (float *)malloc(nBytes);
    gpuRef = (float *)malloc(nBytes);

    initialData(h_A, nElem);
    initialData(h_B, nElem);


    memset(hostRef,0,nBytes);
    memset(gpuRef,0,nBytes);

    float *d_A,*d_B,*d_C;
    cudaMalloc((float**)&d_A, nBytes);
    cudaMalloc((float**)&d_B, nBytes);
    cudaMalloc((float**)&d_C, nBytes);

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


    dim3 block (nElem);
    dim3 grid (nElem/block.x);

    sumArraysOnGPU<<< grid,block >>>(d_A,d_B,d_C);


    checkResult(hostRef,gpuRef,nElem);

    cudaFree(d_A);
    cudaFree(d_B);
    cudaFree(d_C);

    free(h_A);
    free(h_B);
    free(hostRef);
    free(gpuRef);

    return 0;
}

Professional CUDA C Programming