マルチスレッドアプリケーションにおけるフォールスシェアリングを理解して解決する実際の問題

void *calculate_pdist_segment(void *data) {
    struct pdist_segment *segment = (struct pdist_segment *)data;
    size_t interval_a = segment->interval_a, interval_b = segment->interval_b;
    double lambda = segment->lambda;
    int *d = segment->data;

    for (size_t i = interval_a; i < interval_b; i++) {
        segment->pdist[i] = pow(lambda, d[i]) * exp(-lambda) / tgamma(d[i] + 1);
    }
    return NULL;
}

double *amath_pdist(int *data, double lambda, size_t n_elements, size_t n_threads) {
    double *pdist = malloc(sizeof(double) * n_elements);
    pthread_t threads[n_threads];
    struct pdist_segment segments[n_threads];
    size_t step = n_elements / n_threads;

    for (size_t i = 0; i < n_threads; i++) {
        segments[i].data = data;
        segments[i].lambda = lambda;
        segments[i].pdist = pdist;
        segments[i].interval_a = step * i;
        segments[i].interval_b = (i == n_threads - 1) ? n_elements : (step * (i + 1));
        pthread_create(&threads[i], NULL, calculate_pdist_segment, &segments[i]);
    }

    for (size_t i = 0; i < n_threads; i++) {
        pthread_join(threads[i], NULL);
    }

    return pdist;
}

double *amath_pdist(int *data, double lambda, size_t n_elements, size_t n_threads) {
    double *pdist;
    if (posix_memalign((void **)&pdist, 64, sizeof(double) * n_elements) != 0) {
        perror("Failed to allocate aligned memory");
        return NULL;
    }

    pthread_t threads[n_threads];
    struct pdist_segment segments[n_threads];
    size_t step = n_elements / n_threads;

    for (size_t i = 0; i < n_threads; i++) {
        segments[i].data = data;
        segments[i].lambda = lambda;
        segments[i].pdist = pdist;
        segments[i].interval_a = step * i;
        segments[i].interval_b = (i == n_threads - 1) ? n_elements : (step * (i + 1));
        pthread_create(&threads[i], NULL, calculate_pdist_segment, &segments[i]);
    }

    for (size_t i = 0; i < n_threads; i++) {
        pthread_join(threads[i], NULL);
    }

    return pdist;
}