我正在尝试计算 curand_uniform() 返回 1.0 的次数。但是我似乎无法让以下代码为我工作:
#include <stdio.h>
#include <stdlib.h>
#include <thrust/device_vector.h>
#include <cuda.h>
#include <cuda_runtime.h>
#include <curand_kernel.h>
using namespace std;
__global__
void counts(int length, int *sum, curandStatePhilox4_32_10_t* state) {
int tempsum = int(0);
int i = blockIdx.x * blockDim.x + threadIdx.x;
curandStatePhilox4_32_10_t localState = state[i];
for(; i < length; i += blockDim.x * gridDim.x) {
double thisnum = curand_uniform( &localState );
if ( thisnum == 1.0 ){
tempsum += 1;
}
}
atomicAdd(sum, tempsum);
}
__global__
void curand_setup(curandStatePhilox4_32_10_t *state, long seed) {
int id = threadIdx.x + blockIdx.x * blockDim.x;
curand_init(seed, id, 0, &state[id]);
}
int main(int argc, char *argv[]) {
const int N = 1e5;
int* count_h = 0;
int* count_d;
cudaMalloc(&count_d, sizeof(int) );
cudaMemcpy(count_d, count_h, sizeof(int), cudaMemcpyHostToDevice);
int threads_per_block = 64;
int Nblocks = 32*6;
thrust::device_vector<curandStatePhilox4_32_10_t> d_state(Nblocks*threads_per_block);
curand_setup<<<Nblocks, threads_per_block>>>(d_state.data().get(), time(0));
counts<<<Nblocks, threads_per_block>>>(N, count_d, d_state.data().get());
cudaMemcpy(count_h, count_d, sizeof(int), cudaMemcpyDeviceToHost);
cout << count_h << endl;
cudaFree(count_d);
free(count_h);
}
我收到终端错误(在 linux 上):
terminate called after throwing an instance of 'thrust::system::system_error'
what(): parallel_for failed: cudaErrorInvalidValue: invalid argument
Aborted (core dumped)
我正在这样编译:
nvcc -Xcompiler "-fopenmp" -o test uniform_one_hit_count.cu
我不明白这个错误信息。