对于VTune性能分析 以及Thread Profiler的疑问？

double Pi()

	{

		int i;

		long num_steps = 40000000;

		double x, pi, step, sum = 0.0;

		step = 1.0 / (double) num_steps;

		omp_set_num_threads(NUM_THREADS);

#pragma omp parallel for reduction(+:sum) private(x) 

		for (i = 0; i < num_steps; ++ i)

		{

			x = (i - 0.5) * step;

			sum += 4.0 / (1.0 + x * x);



		}

		pi = step*sum;

		return pi;

	}



void fun2()

{

	double sum;

	sum=Pi();

	std::cout<<"result is :"<<sum<<std::endl;

}

int main(int argc, char** argv)

{

	clock_t t1=clock();

	fun2();

	clock_t t2=clock();

	std::cout<<"time: "<<difftime(t2,t1)<<std::endl;

	//system("pause");

}