Question

I have created this little program to calculate pi using probability and ratios. In order to make it run faster I decided to give multithreading with pthreads a shot. Unfortunately, even after doing much searching around I was unable to solve the problem I have in that when I run the threadFunc function, with one thread, whether that be with a pthread, or just normally called from the calculate_pi_mt function, the performance is much better (at least twice or if not 3 times better) than when I try running it with two threads on my dual core machine. I have tried disabling optimizations to no avail. As far as I can see, when the thread is running it is using local variables apart from at the end when I have used a mutex lock to create the sum of hits…

Firstly are there any tips for creating code that will run better here? (ie style) because I’m just learning by trying this stuff.

And secondly would there be any reason for these obvious performance problems?
When running with number of threads set to 1, one of my cpus maxes out at 100%. When set to two, the second cpu rises to roughly 80%-90%, but all this extra work it is apparently doing is to no avail! Could it be the use of the rand() function?

struct arguments {
    int n_threads;
    int rays;
    int hits_in;
    pthread_mutex_t *mutex;
};


void *threadFunc(void *arg)
{
    struct arguments* args=(struct arguments*)arg;

    int n = 0;
    int local_hits_in = 0;
    double x;
    double y;
    double r;
    while (n < args->rays)
    {
        n++;
        x = ((double)rand())/((double)RAND_MAX);
        y = ((double)rand())/((double)RAND_MAX);
        r = (double)sqrt(pow(x, 2) + pow(y, 2)); 
        if (r < 1.0){
            local_hits_in++;
        }
    }

    pthread_mutex_lock(args->mutex);
    args->hits_in += local_hits_in;
    pthread_mutex_unlock(args->mutex);

    return NULL;
}


double calculate_pi_mt(int rays, int threads){
    double answer;
    int c;
    unsigned int iseed = (unsigned int)time(NULL);
    srand(iseed);

    if ( (float)(rays/threads) != ((float)rays)/((float)threads) ){
        printf("Error: number of rays is not evenly divisible by threads\n");
    }

    /* argument initialization */
    struct arguments* args = malloc(sizeof(struct arguments));
    args->hits_in = 0;
    args->rays = rays/threads;
    args->n_threads = 0;
    args->mutex = malloc(sizeof(pthread_mutex_t));
    if (pthread_mutex_init(args->mutex, NULL)){
        printf("Error creating mutex!\n");
    }


    pthread_t thread_ary[MAXTHREADS];

    c=0;
    while (c < threads){
        args->n_threads += 1;
        if (pthread_create(&(thread_ary[c]),NULL,threadFunc, args)){
            printf("Error when creating thread\n");
        }
        printf("Created Thread: %d\n", args->n_threads);
        c+=1;
    }


    c=0;
    while (c < threads){
        printf("main waiting for thread %d to terminate...\n", c+1);
        if (pthread_join(thread_ary[c],NULL)){
            printf("Error while waiting for thread to join\n");
        }
        printf("Destroyed Thread: %d\n", c+1);

        c+=1;
    }

    printf("Hits in %d\n", args->hits_in);
    printf("Rays: %d\n", rays);
    answer = 4.0 * (double)(args->hits_in)/(double)(rays);

    //freeing everything!
    pthread_mutex_destroy(args->mutex);
    free(args->mutex);
    free(args);

    return answer;
}

Answer 1

There’s a couple of problems I can see:

• rand() is not thread-safe. Use drand48_r() (which generates a double in the range [0.0, 1.0) natively, which is what you want)
• You only create one struct arguments structure, then try to use that for multiple threads. You need to create a seperate one for each thread (just use an array).

---

Here’s how I’d clean up your approach. Note how we don’t need to use any mutexes – each thread just stashes its own return value in a seperate location, and the main thread adds them up after the other threads have finished:

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <sys/time.h>
#include <pthread.h>

struct thread_info {
    int thread_n;
    pthread_t thread_id;
    int rays;
    int hits_in;
};

void seed_rand(int thread_n, struct drand48_data *buffer)
{
    struct timeval tv;

    gettimeofday(&tv, NULL);
    srand48_r(tv.tv_sec * thread_n + tv.tv_usec, buffer);
}

void *threadFunc(void *arg)
{
    struct thread_info *thread_info = arg;
    struct drand48_data drand_buffer;

    int n = 0;
    const int rays = thread_info->rays;
    int hits_in = 0;
    double x;
    double y;
    double r;

    seed_rand(thread_info->thread_n, &drand_buffer);

    for (n = 0; n < rays; n++)
    {
        drand48_r(&drand_buffer, &x);
        drand48_r(&drand_buffer, &y);
        r = x * x + y * y;
        if (r < 1.0){
            hits_in++;
        }
    }

    thread_info->hits_in = hits_in;
    return NULL;
}


double calculate_pi_mt(int rays, int threads)
{
    int c;
    int hits_in = 0;

    if (rays % threads) {
        printf("Error: number of rays is not evenly divisible by threads\n");
        rays = (rays / threads) * threads;
    }

    /* argument initialization */
    struct thread_info *thr = malloc(threads * sizeof thr[0]);

    for (c = 0; c < threads; c++) {
        thr[c].thread_n = c;
        thr[c].rays = rays / threads;
        thr[c].hits_in = 0;
        if (pthread_create(&thr[c].thread_id, NULL, threadFunc, &thr[c])) {
            printf("Error when creating thread\n");
        }
        printf("Created Thread: %d\n", thr[c].thread_n);
    }

    for (c = 0; c < threads; c++) {
        printf("main waiting for thread %d to terminate...\n", c);
        if (pthread_join(thr[c].thread_id, NULL)) {
            printf("Error while waiting for thread to join\n");
        }
        hits_in += thr[c].hits_in;
        printf("Destroyed Thread: %d\n", c+1);
    }

    printf("Hits in %d\n", hits_in);
    printf("Rays: %d\n", rays);
    double answer = (4.0 * hits_in) / rays;

    free(thr);

    return answer;
}