相关疑难解决方法(0)

我想在CUDA上实现Inter-block障碍,但遇到了严重的问题.

我无法弄清楚为什么它不起作用.

#include <iostream>
#include <cstdlib>
#include <ctime>

#define SIZE 10000000
#define BLOCKS 100 

using namespace std;

struct Barrier {
    int *count;

    __device__ void wait() {
        atomicSub(count, 1);
        while(*count)
            ;
    }

    Barrier() {
        int blocks = BLOCKS;
        cudaMalloc((void**) &count, sizeof(int));
        cudaMemcpy(count, &blocks, sizeof(int), cudaMemcpyHostToDevice);
    }

    ~Barrier() {
        cudaFree(count);
    }
};


__global__ void sum(int* vec, int* cache, int *sum, Barrier barrier)
{
    int tid = blockIdx.x;

    int temp = 0;
    while(tid < SIZE) {
        temp += vec[tid];
        tid += gridDim.x;
    } …