Question

我最近问过this question我写的一些CUDA代码来生成素数。令我惊讶的是@talonmies说我的代码在运行时运行正常。考虑到你没有得到5k代表Rick Rolling的人我相信它。但事实仍然是它在我的机器上不起作用。

对可能导致此类行为，补救措施或仅在您的计算机上运行此代码的任何见解，以便我可以获得超过2个结果样本将会膨胀。

谢谢！

P.S。这里是有问题的代码::

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

typedef struct{
    int num;
    int count;
} counterClass;

counterClass new_counterClass(counterClass aCounter, int by, int count){
    aCounter.num = by;
    aCounter.count = count%by;
    return aCounter;
}

__global__ void count(counterClass *Counters){
    int idx = threadIdx.x+blockDim.x*blockIdx.x;
    Counters[idx].count+=1;
    if(Counters[idx].count == Counters[idx].num){
        Counters[idx].count = 0;
    }
    __syncthreads();
}

__global__ void check(counterClass *Counters, bool *result){
    int idx = threadIdx.x+blockDim.x*blockIdx.x;
    if (Counters[idx].count == 0){
        *result = false;
    }
    __syncthreads();
}

int main(){
    int tPrimes = 5;    // Total Primes to Find
    int nPrimes = 1;    // Number of Primes Found
    bool  *d_result, h_result=true;
    counterClass *h_counters =(counterClass *)malloc(tPrimes*sizeof(counterClass));
    h_counters[0]=new_counterClass(h_counters[0], 2 , 0);
    counterClass *d_counters;
    int n = 2;
    cudaMalloc((void **)&d_counters, tPrimes*sizeof(counterClass));
    cudaMalloc((void **)&d_result, sizeof(bool));
    cudaMemcpy(d_counters, h_counters, tPrimes*sizeof(counterClass), cudaMemcpyHostToDevice);
    while(nPrimes<tPrimes){
        h_result=true;
        cudaMemcpy(d_result, &h_result, sizeof(bool), cudaMemcpyHostToDevice);
        n+=1;
        count<<<1,nPrimes>>>(d_counters);
        check<<<1,nPrimes>>>(d_counters,d_result);
        cudaMemcpy(&h_result, d_result, sizeof(bool), cudaMemcpyDeviceToHost);
        if(h_result){
            printf("%d\n", n);
            cudaMemcpy(h_counters, d_counters, tPrimes*sizeof(counterClass), cudaMemcpyDeviceToHost);
            h_counters[nPrimes]=new_counterClass(h_counters[nPrimes], n , 0);
            nPrimes += 1;
            cudaMemcpy(d_counters, h_counters, tPrimes*sizeof(counterClass), cudaMemcpyHostToDevice);
        }
    }
}

我的结果::

$ nvcc parraPrimes.cu -o primes
$ ./primes
3
4
5
6

而对于@talonmies代码打印3,5,7,11 ... wtf对吗？

每台机器的结果不同，我如何使其保持一致？

0 个答案: