Parallel Programming with OpenMP
Scope
In shared memory programming multiple CPUs can access the same variables. This makes the program more efficient and saves copying. In some cases, each thread needs its own copy of the variables – such as the loop variables in parallel for() loops.
Clauses specified in OpenMP directives (see the descriptions Table 1) define the properties of these variables. You can append clauses to the OpenMP #pragma, for example:
#pragma omp parallel for shared(x, y) private(z)
Errors in shared()/private() variable declarations are some of the most common causes of errors in parallelized programming.
Reduction
Now you now know how to create threads and distribute the workload over multiple threads. However, how can you get all the threads to work on a collated result – for example, to total the values in an array? reduction() (Listing 2) handles this.
Listing 2
reduction()
The compiler creates a local copy of each variable in reduction() and initializes it independently of the operator (e.g., 0 for "+", 1 for "*"). If, say, three threads are each handling one third of the loop, the master thread adds up the subtotals at the end.
Who is Faster?
Debugging parallelized programs is an art form in its own right. It is particularly difficult to find errors that do not occur in serial programs and do not occur regularly in parallel processing. This category includes what are known as race conditions: different results on repeated runs of a program with multiple blocks that are executed parallel to one another, depending on which thread is fastest each time. The code in Listing 3 starts by filling an array in parallel and then goes on to calculate the sum of these values in parallel.
Listing 3
Avoiding Race Conditions
Without the OpenMP #pragma omp critical (sum_total) statement in line 13, the following race condition could occur:
- Thread 1 loads the current value of sum into a CPU register.
- Thread 2 loads the current value of sum into a CPU register.
- Thread 2 adds a[i+1] to the value in the register.
- Thread 2 writes the value in the register back to the sum variable.
- Thread 1 adds a[i] to the value in the register.
- Thread 1 writes the value in the register to the sum variable.
Because thread 2 overtakes thread 1 here, thus winning the "race," a[i+1] would not be added correctly. Although thread 2 calculates the sum and stores it in the sum variable, thread 1 overwrites it with an incorrect value.
The #pragma omp critical statement makes sure that this does not happen. All threads execute the critical code, but only one at any time. The example in Listing 3 thus performs the addition correctly without parallel threads messing up the results. For elementary operations (e.g., i++) #pragma omp atomic will atomically execute a command. Write access to shared() variables also should be protected by a #pragma omp critical statement.
« Previous 1 2 3 4 Next »
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters
Find SysAdmin Jobs
News
-
CarbonOS: A New Linux Distro with a Focus on User Experience
CarbonOS is a brand new, built-from-scratch Linux distribution that uses the Gnome desktop and has a special feature that makes it appealing to all types of users.
-
Kubuntu Focus Announces XE Gen 2 Linux Laptop
Another Kubuntu-based laptop has arrived to be your next ultra-portable powerhouse with a Linux heart.
-
MNT Seeks Financial Backing for New Seven-Inch Linux Laptop
MNT Pocket Reform is a tiny laptop that is modular, upgradable, recyclable, reusable, and ships with Debian Linux.
-
Ubuntu Flatpak Remix Adds Flatpak Support Preinstalled
If you're looking for a version of Ubuntu that includes Flatpak support out of the box, there's one clear option.
-
Gnome 44 Release Candidate Now Available
The Gnome 44 release candidate has officially arrived and adds a few changes into the mix.
-
Flathub Vying to Become the Standard Linux App Store
If the Flathub team has any say in the matter, their product will become the default tool for installing Linux apps in 2023.
-
Debian 12 to Ship with KDE Plasma 5.27
The Debian development team has shifted to the latest version of KDE for their testing branch.
-
Planet Computers Launches ARM-based Linux Desktop PCs
The firm that originally released a line of mobile keyboards has taken a different direction and has developed a new line of out-of-the-box mini Linux desktop computers.
-
Ubuntu No Longer Shipping with Flatpak
In a move that probably won’t come as a shock to many, Ubuntu and all of its official spins will no longer ship with Flatpak installed.
-
openSUSE Leap 15.5 Beta Now Available
The final version of the Leap 15 series of openSUSE is available for beta testing and offers only new software versions.