#include <omp.h> #define ARR_SIZE 600 #define STEP_SIZE 100 #include <stdio.h> int main() { /* Computing Array sum using tasks */ int i; int sum = 0; #pragma omp parallel { int a[ARR_SIZE]; #pragma omp for for (i = 0; i < ARR_SIZE; i += STEP_SIZE) { int j, start = i, end = i + STEP_SIZE - 1; printf("Computing Sum(%d,%d) in thread %d of %d ", start, end, omp_get_thread_num(), omp_get_num_threads()); #pragma omp task { int psum = 0; printf("Task computing Sum(%d,%d) in thread %d of %d ", start, end, omp_get_thread_num(), omp_get_num_threads()); for (j = start; j <= end; j++) { psum += a[j]; } #pragma omp critical sum += psum; } printf("Sum=%d ", sum); } } }

Yeah. reduction(+:dot) should be put up as a clause for the code to work.

yes

And thanks to all students for asking good questions. That answers many of my questions too.

You are pipelining the data transfer through the bus so essentially all the memory 4 byte memory transfers took 100ns but 2nd memory transfer occurs 5ns after the 1st and so on

Branching statements are like if statement, for, while loop etc. Think of it as if(flag1) {flag2 = true}. The second statement "flag2=true" is dependent on the execution of flag1 instruction. if flag2 is in pipeline and flag1 turns out to be false, second statement will be thrown away. Which basically means wastage of cpu cycles spent on processing flag=true.

@Micheal Kleyman You look like an ad bot.

@Aaron Ronald And you are even worse.