45
edits
Changes
no edit summary
#Danylo Medinski [mailto:ddmedinski@myseneca.ca?subject=GPU621%20from%20CDOT%20Wiki] Research etc.
== Progress ==
'''Oct 17th:'''
# Created Wiki page
----
== OpenMp vs C++ 11 Threads ==
===What is C++ 11 Threads===
With the introduction of C++ 11, there were major changes and additions made to the C++ Standard libraries. One of the most significant changes was the inclusion of multi-threading libraries. Before C++ 11 in order to implement multi-threading, external libraries or language extensions such as OpenMp was required.
The C++ 11 thread support library includes these 4 files to enable multi-threading
* <thread> - class and namespace for working with threads
* <mutex> - provides support for mutual exclusion
* <contition_variable> - a synchronization primitive that can be used to block a thread, or multiple threads at the same time, until another thread both modifies a shared variable (the condition), and notifies the condition_variable.
* <future> - Describes components that a C++ program can use to retrieve in one thread the result (value or exception) from a function that has run in the same thread or another thread.
===Programming Models===
====SPMD====
An example of the SPMD programming model in STD Threads using an atomic barrier
#include <iostream>
#include <iomanip>
#include <cstdlib>
#include <chrono>
#include <vector>
#include <thread>
#include <atomic>
using namespace std::chrono;
std::atomic<double> pi;
void reportTime(const char* msg, steady_clock::duration span) {
auto ms = duration_cast<milliseconds>(span);
std::cout << msg << " - took - " <<
ms.count() << " milliseconds" << std::endl;
}
void run(int ID, double stepSize, int nthrds, int n)
{
double x;
double sum = 0.0;
for (int i = ID; i < n; i = i + nthrds){
x = (i + 0.5)*stepSize;
sum += 4.0 / (1.0 + x*x);
}
sum = sum * stepSize;
pi = pi + sum;
}
int main(int argc, char** argv) {
if (argc != 3) {
std::cerr << argv[0] << ": invalid number of arguments\n";
return 1;
}
int n = atoi(argv[1]);
int numThreads = atoi(argv[2]);
steady_clock::time_point ts, te;
// calculate pi by integrating the area under 1/(1 + x^2) in n steps
ts = steady_clock::now();
std::vector<std::thread> threads(numThreads);
double stepSize = 1.0 / (double)n;
for (int ID = 0; ID < numThreads; ID++) {
int nthrds = std::thread::hardware_concurrency();
if (ID == 0) numThreads = nthrds;
threads[ID] = std::thread(run, ID, stepSize, 8, n);
}
te = steady_clock::now();
for (int i = 0; i < numThreads; i++){
threads[i].join();
}
std::cout << "n = " << n << std::fixed << std::setprecision(15) << "\n pi(exact) = " << 3.141592653589793 << "\n pi(calcd) = " << pi << std::endl;
reportTime("Integration", te - ts);
// terminate
char c;
std::cout << "Press Enter key to exit ... ";
std::cin.get(c);
}