C ++ multi-threaded program shows the same performance as serial

Question

I just want to write a simple C ++ program that creates two threads, and each of them fills the vector with squares of integers (0, 1, 4, 9, ...). Here is my code:

#include <iostream>
#include <vector>
#include <functional>
#include <thread>
#include <time.h>

#define MULTI 1
#define SIZE 10000000

void fill(std::vector<unsigned long long int> &v, size_t n)
{
    for (size_t i = 0; i < n; ++i) {
        v.push_back(i * i);
    }
}

int main()
{
    std::vector<unsigned long long int> v1, v2;
    v1.reserve(SIZE);
    v2.reserve(SIZE);
    #if !MULTI
    clock_t t = clock();
    fill(v1, SIZE);
    fill(v2, SIZE);
    t = clock() - t;
    #else
    clock_t t = clock();
    std::thread first(fill, std::ref(v1), SIZE);
    fill(v2, SIZE);
    first.join();
    t = clock() - t;
    #endif
    std::cout << (float)t / CLOCKS_PER_SEC << std::endl;
    return 0;
}

But when I run my program, I see that there is no significant difference between the serial version and the parallel version (or sometimes the parallel version shows even worse results). Any idea what is going on?

Answer 1

When I execute your code from MSVC2015 to i7, I notice:

• 14 26 . . .
• 0,3 0,2 , , .

, , fill() .

, fill() (, ), . , , , , .

:

, , , , , , , doug , (.. ).

, , , , , ( ):

:

// computation intensive
void mytask(unsigned long long loops)
{
    volatile double x; 
    for (unsigned long long i = 0; i < loops; i++) {
        x = sin(sqrt(i) / i*3.14159);
    }
}

//memory intensive
void mytask2(vector<unsigned long long>& v, unsigned long long loops)
{
    for (unsigned long long i = 0; i < loops; i++) {
        v.push_back(i*3+10);
    }
}

Answer 2

, , , , .

, . std::this_thread::sleep_for

Answer 3

: , ( * i) ( v.push_back). . . unix

>time ./a.out 

.

#include <iostream>
#include <vector>
#include <functional>
#include <thread>
#include <time.h>
#include <math.h>

#define MULTI 1
#define SIZE 10000000

void fill(std::vector<unsigned long long int> &v, size_t n)
{
    int sum = 0;
    for (size_t i = 0; i < n; ++i) {
        for (size_t j = 0; j < 100; ++j) {
            sum += sqrt(i*j);
        }
    }
    v.push_back(sum);
}

int main()
{
    std::vector<unsigned long long int> v1, v2;
    v1.reserve(SIZE);
    v2.reserve(SIZE);
    #if !MULTI
    fill(v1, SIZE);
    fill(v2, SIZE);
    #else
    std::thread first(fill, std::ref(v1), SIZE);
    std::thread second(fill, std::ref(v2), SIZE);

    first.join();
    second.join();
    #endif
    return 0;
}