why increase the execution time in my openmp code?

Question

I try to calculate the speed-up of a parallel simple code. It's a simple loop. First I use open-mp in c++ to parallelize it. Then I want to find the execution time of each thread, I use the maximum thread time as parallel execution time. I repeat it by different thread number, but the time is worse! Could you help me?

#include "stdafx.h"
#include "omp.h"
#include "conio.h"
double diftime[64];
int a,i,threadnum;
int main()
{
threadnum=2;
omp_set_nested(1);
omp_set_dynamic(0);
#pragma omp parallel num_threads(threadnum) 
{
    double start_time,end_time;
    int id = omp_get_thread_num();
    start_time=omp_get_wtime();
    #pragma omp for nowait schedule(static)
    for (i=0;i<2000000;i++){a++;}
    end_time=omp_get_wtime();
    diftime[id]=diftime[id]+(end_time-start_time);      
    printf("thread[%d] = %.32g\n",id,end_time-start_time);  
}
getch();
return 0;
}

Answer 1

The reason is that your loop operation is so simple that the compiler replaces the loop with the result of a after the loop. Take a look at this example:

#include <stdio.h>

int main()
{
   size_t i;
   unsigned a = 0;
   for (i = 0; i < (1UL << 20); i++) // the loop should run 1048576 times
      a++;
   printf("%ud\n", a);
   return 0;
}

But when we look at the generated instructions via gcc -O2 -S test.c , we find

_main:
LFB20:
   subq   $8, %rsp
LCFI0:
   movl   $1048576, %esi  # the loop is replaced by a's value!
   xorl   %eax, %eax
   leaq   LC0(%rip), %rdi
   call   _printf
   xorl   %eax, %eax
   addq   $8, %rsp
LCFI1:
   ret

So, the reason why your measured time goes up is that it takes more time to generate and handle more threads (which don't really do anything).

---

If you want to force the compiler to create a loop, you should make the variable in the loop volatile , like that:

#include <stdio.h>

#include <omp.h>

double diftime[64];
int main()
{
   int i;
   unsigned a = 0;
#pragma omp parallel
   {
      double start_time, end_time;
      int id = omp_get_thread_num();
      start_time = omp_get_wtime();
      volatile int b = 0;  // #############################
#pragma omp for nowait schedule(static)
      for (i = 0; i < (1UL << 20); i++)
         b++;
      end_time = omp_get_wtime();
      diftime[id] = diftime[id] + (end_time - start_time);
      printf("thread[%d] = %.32g\n", id, end_time - start_time);
// ensure only one thread at a time executes the next line
#pragma omp critical  
      a += b;
   }
   printf("a = %d\n", a);
   return 0;
}