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

#define ARRAY_SIZE 15000576
#define NUM_THREADS 8  // Adjust based on your CPU cores

typedef struct {
    float *a;
    float *b;
    float *c;
    int start;
    int end;
} ThreadData;

void *add_arrays(void *arg) {
    ThreadData *data = (ThreadData *)arg;
    for (int i = data->start; i < data->end; i++) {
        data->c[i] = data->a[i] + data->b[i];
    }
    return NULL;
}

double get_time() {
    struct timeval tv;
    gettimeofday(&tv, NULL);
    return tv.tv_sec + tv.tv_usec * 1e-6;
}

int main() {
    float *a = (float*)malloc(ARRAY_SIZE * sizeof(float));
    float *b = (float*)malloc(ARRAY_SIZE * sizeof(float));
    float *c = (float*)malloc(ARRAY_SIZE * sizeof(float));

    // Initialize arrays
    for (int i = 0; i < ARRAY_SIZE; i++) {
        a[i] = i;
        b[i] = i * 2;
    }

    // Create threads
    pthread_t threads[NUM_THREADS];
    ThreadData thread_data[NUM_THREADS];
    int chunk_size = ARRAY_SIZE / NUM_THREADS;

    double start = get_time();
    for (int t = 0; t < NUM_THREADS; t++) {
        thread_data[t].a = a;
        thread_data[t].b = b;
        thread_data[t].c = c;
        thread_data[t].start = t * chunk_size;
        thread_data[t].end = (t == NUM_THREADS - 1) ? ARRAY_SIZE : (t + 1) * chunk_size;
        pthread_create(&threads[t], NULL, add_arrays, &thread_data[t]);
    }

    // Wait for threads to finish
    for (int t = 0; t < NUM_THREADS; t++) {
        pthread_join(threads[t], NULL);
    }
    double calc_time = get_time() - start;

    printf("Pthreads calculation time: %.6f ms\n", calc_time * 1000);

    // Print a sample of the result
    for (int i = 0; i < 10; i++) {
        printf("c[%d] = %f\n", i, c[i]);
    }

    free(a);
    free(b);
    free(c);

    return 0;
}