OpenMP Library Research Articles

Taking the MPI standard and the open MPI library to exascale

The Open MPI for Exascale (OMPI-X) project was one of two in the Exascale Computing Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with other MPI Forum members to champion several important features for inclusion in the MPI 4.0, 4.1, and upcoming 5.0 MPI standard versions, in support of the needs of exascale applications and systems. The team also worked with the larger Open MPI community to bring implementations of these new features and other enhancements into Open MPI, one of the leading open-source implementations of the MPI interface. This paper describes the motivation for the work of the OMPI-X project in the context of exascale computing needs, the nature of the resulting new capabilities in the MPI standard, and how they were implemented in the Open MPI library. Features include improved support for “MPI + X” programming models through partitioned communications and support for user-level threading, sessions, fault tolerance through the user-level fault mitigation (ULFM) and Reinit models, and other features. We also discuss enhancements to Open MPI providing improved performance and scalability for existing features, such as collective operations, one-sided operations, support for the Slingshot-11 interconnect of the initial exascale systems, and how the OMPI-X team worked to improve quality assurance for the Open MPI library, particularly on platforms of interest to the Department of Energy community.

A general purpose parallel Fortran code for grid projected concentration reconstruction from multidimensional particle distributions

Particle-based transport models are widely used for simulating the movement of pollutants in environmental systems. Unlike grid-based methods, particles naturally address advective transport without numerical dispersion. However, these models require concentration reconstruction from the discrete particle information. This is computationally demanding in multidimensional problems, posing a challenge for field-scale models requiring frequent reconstruction. Grid Projected Kernel Density Estimation (GPKDE) is a cell-averaged reconstruction with improvements in computational performance compared to classical KDE. Currently, no programs implementing this method are readily integrated into particle simulators, compatible with three-dimensional domains, and particles with unequal weights. This article introduces a Fortran code for general-purpose GPKDE, with modular functionalities facilitating the integration into external software. The program implements locally adaptive kernel bandwidth selection and alternatives for the reconstruction from particles with non-uniform weights. The code is parallelized with the OpenMP library. Numerical test cases demonstrate the program’s applicability and scalability of the parallel implementation.

MODPATH-RW: A Random Walk Particle Tracking Code for Solute Transport in Heterogeneous Aquifers.

Random walk particle tracking (RWPT) is a discrete particle method that offers several advantages for simulating solute transport in heterogeneous geological systems. The formulation is a discrete solution to the advection-dispersion equation, yielding results that are not influenced by grid-related numerical dispersion. Numerical dispersion impacts the magnitude of concentrations and gradients obtained from classical grid-based solvers in advection-dominated problems with relatively large grid Péclet numbers. Accurate predictions of concentrations are crucial for reactive transport studies, and RWPT has been recognized for its potential benefits for this kind of application. This highlights the need for a solute transport program based on RWPT that can be seamlessly integrated with industry-standard groundwater flow models. This article presents a solute transport code that implements the RWPT method by extension of the particle tracking model MODPATH, which provides the base infrastructure for interacting with several variants of MODFLOW groundwater flow models. The implementation is achieved by developing a method for determining the exact cell-exit position of a particle undergoing simultaneous advection and dispersion, allowing for the sequential transfer of particles between flow model cells. The program is compatible with rectangular unstructured grids and integrates a module for the smoothed reconstruction of concentrations. In addition, the program incorporates parallel processing of particles using the OpenMP library, enabling faster simulations of solute transport in heterogeneous systems. Numerical test cases involving different applications in hydrogeology benchmark the RWPT model with well-known transport codes.

MPI reduction and broadcast algorithms for computer clusters with multistage interconnection networks

Algorithms for MPI Allreduce, Bcast and Reduce collective operations have been developed. They are based on the dynamic construction of process groups at all levels of the memory hierarchy within the computing node and levels of the multistage interconnection network. The description of the network topology is loaded from an external file. Аlgorithms are implemented on the basis of the Open MPI library in an isolated collective component. Experiments on a cluster with a two-tier InfiniBand EDR network have shown the effectiveness of the algorithms for messages up to 16KB.

PROPAGATION OF HYBRID DETONATION IN A HYDROGEN-OXYGEN MIXTURE WITH ALUMINUM PARTICLES IN A CHANNEL WITH EXPANSION

A physical and mathematical model of hybrid detonation of a mixture of hydrogen — oxygen — argon — aluminum particles is presented. Using this model, the influence of aluminum particles on the process of detonation propagation in a channel with expansion was studied. To speed up the results, the numerical model was extended using the Open MP libraries. As a result, it was found that the mode of propagation of hybrid detonation is affected by both the loading and the size of the particles. In general, the hybrid mixture is more resistant to changes in the geometry of the area to be filled.

Parallel Multi-Deque Partition Dual-Deque Merge sorting algorithm using OpenMP

Quicksort is an important algorithm that uses the divide and conquer concept, and it can be run to solve any problem. The performance of the algorithm can be improved by implementing this algorithm in parallel. In this paper, the parallel sorting algorithm named the Multi-Deque Partition Dual-Deque Merge Sorting algorithm (MPDMSort) is proposed and run on a shared memory system. This algorithm contains the Multi-Deque Partitioning phase, which is a block-based parallel partitioning algorithm, and the Dual-Deque Merging phase, which is a merging algorithm without compare-and-swap operations and sorts the small data with the sorting function of the standard template library. The OpenMP library, which is an application programming interface used to develop the parallel implementation of this algorithm, is implemented in MPDMSort. Two computers (one with an Intel Xeon Gold 6142 CPU and the other with an Intel Core i7-11700 CPU) running Ubuntu Linux are used in this experiment. The results show that MPDMSort is faster than parallel balanced quicksort and multiway merge sort on the large random distribution data. A speedup of 13.81times and speedup per thread of 0.86 can be obtained. Thus, developers can use these parallel partitioning and merging algorithms to improve the performance of related algorithms.

Real-time processing approaches for interactive room acoustic auralization in the rtSOFE

Room acoustic simulation of early reflections with the mirror-image method for arbitrary room geometries is an exponential problem, which, if computed to a high reflection order, will quickly exceed available computational and memory resources. The real-time Simulated Open Field Environment (rtSOFE) is freely available room-acoustic simulation and auralization software based on the mirror-image method. For auralization, rtSOFE synthesizes room impulse responses for each playback channel from the list of mirror images. A convolver program receives these seconds-long room impulse responses and convolves them for each sound source, sums across sources, and performs the playback equalization. Both programs perform computations in multiple threads in parallel using the OpenMP library. Many operations are implemented with Intel Advanced Vector Extensions (AVX) to increase processing speed. Image source trees are terminated after a definable number of invisible parent sources, keeping the number of computed mirrors manageable. With this, rtSOFE is capable of computing room impulse responses to high reflection orders in interactive real-time settings. I will present the software concept and discuss the approaches that speed up the computation.

FEATURES OF THE USE OF PARALLEL CALCULATIONS IN THE PACKAGE OF APPLICATION PROGRAMS «MIRELA+»

The article examines approaches to the optimization of structural calculations, which require a comprehensive analysis of deformation processes under the action of operational loads. The finite element method is usually used to solve such problems. Modeling of structures taking into account stress concentrators requires the use of large-sized calculation grids. In real operating conditions, most structural elements are under the influence of mechanical and thermal loads. The package of application programs «MIRELA+» is intended for solving problems of thermoelasticity of structures made of weakly compressible elastomers and composites with an elastomeric matrix. One of the stages of solving problems of thermoelasticity is the formation of stiffness matrices taking into account weak compressibility and thermal conductivity of finite elements. When forming the stiffness and thermal conductivity matrices, it is necessary to perform integration over the area of ​​the finite element. For elements of the same type, calculations are used according to the same procedure, and the number of such calculations determines the time to solve the problem. In the traditional approach, these calculations are performed sequentially. In the case of large grid sizes, the number and time of calculations increase, which requires optimization of calculations using parallel calculation algorithms. Using the OpenMP library, a parallel algorithm for forming the matrix of solving equations was built. The calculation of terms according to the quadrature scheme is included in the parallel area of ​​the algorithm. Filling of the stiffness matrix of the finite element takes place in the sequential region. The execution time of parallel calculations is determined by the slowest subtask. Using the moment scheme of finite elements, displacement and deformation are approximated by the same polynomials, which simplifies the calculation of integrals. Parallel programming algorithms for constructing solving equations of the “MIRELA+” program package have been developed. Solutions for calculation grids of different sizes have been obtained. The effect of parallelization on the calculation time was studied.

Multiprocessing for the Particle Tracking Model MODPATH.

Particle tracking has several important applications for solute transport studies in aquifer systems. Travel time distribution at observation points, particle coordinates in time and streamlines are some practical results providing information of expected transport patterns and interaction with boundary conditions. However, flow model complexity and simultaneous displacement of multiple particle groups leads to rapid increase of computational requirements. MODPATH is a particle tracking engine for MODFLOW models and source code displays potential for parallel processing of particles. This article addresses the implementation of this feature with the OpenMP library. Two synthetic aquifer applications are employed for performance tests on a desktop computer with increasing number of particles. Speed up analysis shows that dynamic thread scheduling is preferable for highly heterogeneous flows, providing processing adaptivity to the presence of slow particles. In simulations writing particles position in time, thread exclusive output files lead to higher speed up factors. Results show that above a threshold number of particles, simulation runtimes become independent of flow model grid complexity and are controlled by the large number of particles, then parallel processing reduces simulation runtimes for the particle tracking model MODPATH. Article impact statement: Parallel particles processing for MODPATH using the OpenMP library.

Shared Memory-based Algorithms for Vector Collective Operations of the MPI Standard

Algorithms for MPI_Scatterv, MPI_Gatherv, MPI_Allgatherv collective operations using the shared memory of multiprocessor SMP/NUMA systems are proposed. The algorithms use an approach based on copying message fragments via queues in a shared memory segment (Copy-In-Copy-Out). The algorithms were implemented based on Open MPI and the execution time is reduced on average by 20-40% for the MPI_Scatterv, MPI_Gatherv, MPI_Allgatherv operations compared to the coll/tuned component of the Open MPI library.

Analysis and optimization of Dual Parallel Partition Sorting with OpenMP

PurposeSorting is a very important algorithm to solve problems in computer science. The most well-known divide and conquer sorting algorithm is quicksort. It starts with dividing the data into subarrays and finally sorting them.Design/methodology/approachIn this paper, the algorithm named Dual Parallel Partition Sorting (DPPSort) is analyzed and optimized. It consists of a partitioning algorithm named Dual Parallel Partition (DPPartition). The DPPartition is analyzed and optimized in this paper and sorted with standard sorting functions named qsort and STLSort which are quicksort, and introsort algorithms, respectively. This algorithm is run on any shared memory/multicore systems. OpenMP library which supports multiprocessing programming is developed to be compatible with C/C++ standard library function. The authors’ algorithm recursively divides an unsorted array into two halves equally in parallel with Lomuto's partitioning and merge without compare-and-swap instructions. Then, qsort/STLSort is executed in parallel while the subarray is smaller than the sorting cutoff.FindingsIn the authors’ experiments, the 4-core Intel i7-6770 with Ubuntu Linux system is implemented. DPPSort is faster than qsort and STLSort up to 6.82× and 5.88× on Uint64 random distributions, respectively.Originality/valueThe authors can improve the performance of the parallel sorting algorithm by reducing the compare-and-swap instructions in the algorithm. This concept can be used to develop related problems to increase speedup of algorithms.

Marlics: A finite difference liquid crystal simulation package

In this paper we present Marlics (Maringá Liquid Crystal Simulator), a software written in C++ to obtain either the system dynamics, by using the Runge-Kutta method, or the minimum energy states with the Fast Inertial Relaxation Engine (FIRE) for both achiral and chiral nematic liquid crystals. The system solved by Marlics consists in the dynamical evolution for the Q-tensor in the Landau-de Gennes formalism for different geometries, including confined slab cells and spherical, liquid crystal droplets. Furthermore, the code accepts custom geometries, so the user may provide a particular geometry of interest to run simulations. The program takes as input a descriptive file giving the simulations parameters and initial conditions, generating a series of different snapshots distributed in time according to the users' needs. Several initial conditions are provided to help the user starting simulations direct to different goals. The code is organized in class modules, which can be modified by the user base to attend their further needs. Program summaryProgram Title: MarLicSCPC Library link to program files:https://doi.org/10.17632/xb728xftgv.1Code Ocean capsule:https://codeocean.com/capsule/5639788Licensing provisions: GNU General Public License v3.0Programming language: C++Supplementary material: In the S.I the user will find an input file example and the complete list of setup parameters.External routines: The code needs the GSL (Gnu scientific library), an implementation of the CBLas library and an implementation of the OpenMp library (optional).Nature of problem: Marlics was developed to simulate liquid crystal devices via solution of the Landau-de Gennes Equation.Solution method: The system of equations is solved using finite differences in both time and space. The time integration is performed using an explicit integrator with or without variable time-step. We also provide a relaxation engine (FIRE), which is specialized in finding equilibrium states of the same system of dynamical equations.Additional comments including restrictions and unusual features: The code is parallelized using OpenMp, consequently it can only be run in parallel with shared memory processors.The source code comes with the input files and scripts used to generate the results and figures showed in this work.

Real Harmonic Analysis on the Special Orthogonal Group

This paper presents theoretical analysis and software implementation for real harmonics analysis on the special orthogonal group. Noncommutative harmonic analysis for complex-valued functions on the special orthogonal group has been studied extensively. However, it is customary to treat real harmonic analysis as a special case of complex harmonic analysis, and there have been limited results developed specifically for real-valued functions. Here, we develop a set of explicit formulas for real-valued irreducible unitary representations on the special orthogonal group, and provide several operational properties, such as derivatives, sampling, and Clebsch-Gordon coefficients. Furthermore, we implement both of complex and real harmonics analysis on the special orthogonal group into an open source software package that utilizes parallel processing through the OpenMP library. The efficacy of the presented results are illustrated by benchmark studies and an application to spherical shape matching.

A parallel time series algorithm for searching similar sub-sequences

<p><span>Dynamic time warping (DTW) is an important metric for measuring similarity for most time series applications. The computations of DTW cost too much especially with the gigantic of sequence databases and lead to an urgent need for accelerating these computations. However, the multi-core cluster systems, which are available now, with their scalability and performance/cost ratio, meet the need for more powerful and efficient performance. This paper proposes a highly efficient parallel vectorized algorithm with high performance for computing DTW, addressed to multi-core clusters using the Intel quad-core Xeon co-processors. It deduces an efficient architecture. Implementations employ the potential of both message passing interface (MPI) and OpenMP libraries. The implementation is based on the OpenMP parallel programming technology and offloads execution mode, where part of the code sub-sequences on the processor side, which are uploaded to the co-processor for the DTW computations. The results of experiments confirm the effectiveness of the algorithm.</span></p>

High-performance pseudo-anonymization of virtual power plant data on a CPU cluster

The considerable move towards the use of renewable energy resources has been provided by the digitization of energy systems with the help of virtual power plants (VPPs). However, due to the coincidence of this move with the introduction of new technologies in information and communications, joining these systems raises concerns about the privacy of personal data. The only real-world approach widely used in this case is to anonymize or pseudonymize the information associated with individuals in data received from distributed measurement devices. In this paper, we propose the method of classifying received data packets into different flows and assigning different access levels for each flow. This method makes data pseudonymous. Before this step, the received data, which has a different format, is unionized. To implement this idea, a tuple space flow classification algorithm is parallelized on a CPU cluster using MPI and OpenMP according to different scenarios. The CPU cluster consists of one head node and two computational nodes for packet classification operations. In this research, two scenarios have been used to run the CPU algorithm in parallel. The first scenario uses MPI and the second scenario uses a combination of MPI and OpenMP libraries. Also, the Tuple Space algorithm has been implemented on the computing systems using the mentioned libraries in the form of two scenarios using OpenMP and MPI. According to our results, the increase in the number of processor cores is linearly correlated with the increase in the speed of classification. Furthermore, while MPI uses more memory than OpenMP, it helps to achieve a higher speed of classification. In the combined method, the maximum speed of flow classification can be achieved if the number of processes and threads is equal to the number of processor cores. In other words, when the sum of processes and threads does not outnumber CPU cores, the least classification time and memory usage can be achieved.

Parallel Hough Transform based on Object Dual and Pymp Library

Geometric shape detection in an image is a classical problem that leads to many applications, in cartography to highlight roads in a noisy image, in medical imaging to localize disease in a region and in agronomy to fight against weeds with pesticides. The Hough Transform method contributes effectively to the recognition of digital objects, as straight lines, circles and arbitrary objects. This paper deals with the theoretical comparisons of object dual based on the definition of Standard Hough Transform. It also focuses on parallelism of Hough Transform. A generic pseudo-code algorithm, using the Openmp library for the parallel computing of object dual is proposed in order to improve the execution time. In simulation, a triangular mesh superimposed on the image is implemented with the pymp library in python, in considering threads as inputs to read the image and to update the accumulator. The parallel computing presents reduction of the execution time accordingly to the rate of lit pixels in each virtual object and the number of threads. In perspectives, it will contribute to strenghen the developement of a toolkit for the Hough Transform method.

Application of parallel computing in finite element analysis of constructions

To optimize finite elements computational processes of the “MIRELA +” computing complex, parallel programming algorithms have been developed for creating stiffness matrices of finite elements and calculating the stress-strain. The parallel data processing is implemented using OpenMP library. On the basis of computational methods of experiments, the use of parallel computing algorithms at the beginning of solving problems with traditional finite element algorithms for large-dimensional grids has been established.

A Layered Mapping of Ada 202X to OpenMP

The OpenMP specification defines a set of compiler directives, library routines, and environment variables that together represent the OpenMP Application Programming Interface, and is currently defined for C, C++, and Fortran. The forthcoming version of Ada, currently dubbed Ada 202X, includes lightweight parallelism features, in particular parallel blocks and parallel loops. All versions of Ada, since its inception in 1983, have included "tasking," which corresponds to what are traditionally considered "heavyweight" parallelism features, or simply "concurrency" features. Ada "tasks" typically map to what are called "kernel threads," in that the operating system manages them and schedules them. However, one of the goals of lightweight parallelism is to reduce overhead by doing more of the management outside the kernel of the operating system, using a light-weight-thread (LWT) scheduler. The OpenMP library routines support both levels of threading, but for Ada 202X, the main interest is in making use of OpenMP for its lightweight thread scheduling capabilities.

Improving Matrix Multiplication Using Parallel Computing

Multiplication of large matrices requires a lot of computation time as its complexity is O(n3). Because most image processing applications require higher computational throughputs with minimum time, many sequential and parallel algorithms are developed. In this paper, a method of matrix multiplication was chosen, and analyzed. A performance analysis was evaluated, and it was seen that the chosen method was very powerful when dealing with matrices with large sizes and implementing the method using parallel computing based on openMP libraries.

Algorithmic Counting of Zero-Dimensional Finite Topological Spaces With Respect to the Covering Dimension

Taking the covering dimension dim as notion for the dimension of a topological space, we first specify the number zdimT0(n) of zero-dimensional T0-spaces on {1,…,n} and the number zdim(n) of zero-dimensional arbitrary topological spaces on {1,…,n} by means of two mappings po and P that yield the number po(n) of partial orders on {1,…,n} and the set P(n) of partitions of {1,…,n}, respectively. Algorithms for both mappings exist. Assuming one for po to be at hand, we use our specification of zdimT0(n) and modify one for P in such a way that it computes zdimT0(n) instead of P(n). The specification of zdim(n) then allows to compute this number from zdimT0(1) to zdimT0(n) and the Stirling numbers of the second kind S(n, 1) to S(n, n). The resulting algorithms have been implemented in C and we also present results of practical experiments with them. To considerably reduce the running times for computing zdimT0(n), we also describe a backtracking approach and its parallel implementation in C using the OpenMP library.