GPU621/False Sharing

Analyzing False Sharing

Group Members

- Kevin Chou

Introduction

False sharing is a well-known problem that can occur when taking advantage of parallelization in modern multi-processor computers with shared memory. Although the results will be correct, frequent false sharing results in significant performance loss and reduction in scalability, effectively nullifying the benefits of parallel computing.

The Cache

What is a Cache?

False Sharing

Analyzing Workshop Example

#include <iostream>
#include <iomanip>
#include <cstdlib>
#include <chrono>
#include <omp.h>

#define NUM_THREADS 8

using namespace std::chrono;

// report system time
void reportTime(const char* msg, steady_clock::duration span)
{
    auto ms = duration_cast<milliseconds>(span);
    std::cout << msg << " - took - " <<
        ms.count() << " milliseconds" << std::endl;
}

int main(int argc, char** argv)
{
    if (argc != 2)
    {
        std::cerr << argv[0] << ": invalid number of arguments\n";
        std::cerr << "Usage: " << argv[0] << "  no_of_slices\n";
        return 1;
    }
    int n = std::atoi(argv[1]);
    steady_clock::time_point ts, te;

    // calculate pi by integrating the area under 1/(1 + x^2) in n steps
    ts = steady_clock::now();

    int actual_thread_count;
    double pi = 0.0f;
    double sum[NUM_THREADS] = { 0.0f };
    double step = 1.0 / (double)n;

    omp_set_num_threads(NUM_THREADS);
    #pragma omp parallel
    {
        int id, num_threads;
        double x;

        id = omp_get_thread_num();
        num_threads = omp_get_num_threads();

        // get master thread to return how many threads were actually created
        if (id == 0)
        {
            actual_thread_count = num_threads;
        }

        // each thread is responsible for calculating the area of a specific set of sections underneath the curve
        for (int i = id; i < n; i = i + num_threads)
        {
            x = ((double)i + 0.5f) * step;
            sum[id] += 1.0f / (1.0f + x * x);
        }
    }

    // sum up each calculation to get approximation of pi
    for (int i = 0; i < actual_thread_count; i++)
    {
        pi += 4 * sum[i] * step;
    }

    te = steady_clock::now();

    std::cout << "n = " << n <<
        std::fixed << std::setprecision(15) <<
        "\n pi(exact) = " << 3.141592653589793 <<
        "\n pi(calcd) = " << pi << std::endl;
    reportTime("Integration", te - ts);
}