curand每次在一个线程中给出相同的数字

Question

当我调用curand时，我总是在一个线程中获得相同的数字。然而，它们对于每个线程是不同的。我在下一个代码中做错了什么？

#define MAXTHREADS 2
#define NBBLOCKS 2


__global__ void testRand ( curandState * state, int nb ){
    int id = threadIdx.x  + blockIdx.x * blockDim.x;
    int value;
    for (int i=0;i<nb;i++){
        curandState localState = state[id];
        value = curand(&localState);
        printf("Id %i, value %i\n",id,value);
    }
}
__global__ void setup_kernel ( curandState * state, unsigned long seed )
{
    int id = threadIdx.x  + blockIdx.x * blockDim.x;
    curand_init ( seed, id , 0, &state[id] );
}

/**
* Image comes in in horizontal lines
*/
void findOptimum() {
    const dim3 blockSize(MAXTHREADS);
    const dim3 gridSize(NBBLOCKS);

    curandState* devStates;
    cudaMalloc ( &devStates,MAXTHREADS*NBBLOCKS*sizeof( curandState ) );
    time_t t;
    time(&t);
    setup_kernel <<< gridSize, blockSize >>> ( devStates, (unsigned long) t );  
    int nb = 4;
    testRand  <<< gridSize, blockSize >>> ( devStates,nb);  
    testRand  <<< gridSize, blockSize >>> ( devStates,nb);  

    cudaFree(devStates);
}

输出：

Id 0, value -1075808309
Id 1, value -1660353324
Id 2, value 1282291714
Id 3, value -1892750252
Id 0, value -1075808309
Id 1, value -1660353324
Id 2, value 1282291714
Id 3, value -1892750252
...

这重复了几次。

Answer 1

正如talonmies指出的那样，我没有修改全球状态。

在state[id] = localState行后添加curand(localState)解决了问题。