Parallel Implementation of a Large-Scale 3-D Air Pollution Model (original) (raw)

Performance results of a large-scale air pollution model on two parallel computers

International Journal of Environment and Pollution, 2004

The size of the computational task obtained after the appropriate splitting and discretization procedures of the system of partial differential equations in large air pollution models is enormous. Even when computers with several GFLOPS top performance are in use, it is difficult to solve this problem efficiently and, furthermore, to prepare codes that can be used for operating purposes. Some performance-comparison results obtained by runs of the parallelized via MPI unified variable-grid version of the Danish Eulerian model for long-range transport of air pollutants on two parallel computer architectures are presented. The test numerical experiments are performed on a Beowulf-like cluster setup of four two-processor Macintosh G4 machines and a multiprocessor SUN (up to 32 processors). The Message Passing Interface (MPI) standard is used on both distributed and shared memory parallel computer platforms. Timing results, speed-up and parallel efficiency of the main computational stages as well as of the whole model are presented.

Flexible Two-Level Parallel Implementations of a Large Air Pollution Model

Large scale air pollution models are powerful tools, designed to meet the increasing demand in different environmental studies. The atmosphere is the most dynamic component of the environment, where the pollutants can quickly be moved in a very long distance. Therefore the advanced modeling must be done in a large computational domain. Moreover, all relevant physical, chemical and photochemical processes must be taken into account. The speed of these processes vary in a wide range. This fact implies that a small time step must be used in order to achieve both numerical stability and sufficient accuracy of the results. Thus the numerical treatment of such an air pollution model becomes in many cases a huge computational problem, a challenging task for the most powerful up-to-date supercomputers. The Danish Eulerian Model (DEM) is used in this work. The paper fo-cuses on the efficient parallel implementation of DEM on powerful parallel supercomputers. We present a variety of performance and scalability results, obtained on different parallel machines by using standard paral-lelization tools (MPI for distributed-memory parallelism and OpenMP for shared-memory parallelism). It is shown by experiments that MPI and OpenMP can both be used on separate levels of parallelism to get the best use of the clustered parallel machines. Application of the results in the environmental studies, related to high ozone concentrations in the air, is illustrated by some plots in the last section.

Performance Analysis of an Embarrassingly Parallel Application in Atmospheric Modeling

Research Journal of Applied Sciences, Engineering and Technology, 2015

This study aims at making a comparative study of various parallel programming models for a compute intensive application pertaining to Atmospheric modeling. Atmospheric modeling deals with predicting the behavior of atmosphere through mathematical equations governing the atmospheric fluid flows. The mathematical equations are nonlinear partial differential equations which are difficult to solve analytically. Thus fundamental governing equations of atmospheric motion are discretized into algebraic forms that are solved using numerical methods to obtain flow-field values at discrete points in time and/or space. Solving these equations often requires huge computational resource, which is normally available with high-speed supercomputers. Shallow Water equations provide a useful framework for the analysis of dynamics of large-scale atmospheric flow and for the analysis of various numerical methods that might be applied to the solution of these equations. In this study, Finite volume approach has been used for discretizing these equations that leads to a number of algebraic equations equal to the number of time instants at which the flow field values are to be evaluated. It is apparent that the application is embarrassingly parallel and its parallelization will suppress communication overhead. A High Performance Compute cluster has been employed for solving the equations involved in atmospheric modeling. Use of OpenMP and MPI APIs has paved the way to study the behavior of shared memory programming model and the message passing programming model in the context of such a highly compute intensive application. It is observed that no additional benefit can be enjoyed by creating too many software threads than the available hardware threads, as the execution resources should be shared among them.

Environmental modeling on massively parallel computers

Environmental Modelling & Software, 2000

In a previous work we studied the concurrent implementation of a numerical model, CONDIFP, developed for the analysis of depth-averaged convection-diffusion problems. Initial experiments were conducted on the Intel Touchstone Delta System, using up to 512 processors and different problem sizes. As for other computation-intensive applications, the results demonstrated an asymptotic trend to unity efficiency when the computational load dominates the communication load. This paper relates some other numerical experiences, in both one and two space dimensions with various choices of initial and boundary conditions, carried out on the Intel Paragon XP/S Model L38 with the aim to illustrate the parallel solver versatility and reliability.

A Hybrid Parallelization of Air Quality Model with MPI and OpenMP

Lecture Notes in Computer Science, 2012

This paper presents the parallelization of FARM, a 3D Eulerian chemical-transport model on structured and nested grids. The parallelization has been developed using the MPI library and OpenMP directives implementing a Master-Worker strategy. Benchmarking in different architectures is also discussed.

Parallel and GRID Implementation of a Large Scale Air Pollution Model

Lecture Notes in Computer Science, 2007

Large-scale environmental models are powerful tools, designed to meet the increasing demand in various environmental studies. The atmosphere is the most dynamic component of the environment, where the pollutants and other chemical species actively interact with each other, and can quickly be moved in a very long distance. Therefore the advanced modeling is usually done in a large computational domain. Moreover, all relevant physical, chemical and photochemical processes should be taken into account, which heavily depend on the meteorological conditions. All this makes the air pollution modeling a huge and rather difficult computational task, requiring a large amount of computational power. The most powerful supercomputers have been used for the development and test runs of such a model, the Danish Eulerin Model (DEM). Distributed parallel computing via MPI is one of the most efficient techniques in achieving good performance and getting results in real time. The quickly advancing GRID computing technology is another powerful tool that can be used to reach higher level of performance of such a huge model. Both techniques and their inherent problems are discussed in this paper. Results of numerical experiments are presented and analysed and some conclusions are drown, based on the experiments.

Using parallel computers in environmental modelling: a working example

Ecological Modelling, 1995

An application of the utilization of parallel supercomputers for a 3D eutrophication-diffusion macromodel of the Venice lagoon is presented. Problems encountered in program restructuration, in the choice and in the introduction of parallel algorithms for solving the diffusion equation are discussed, together with the approach used to exploit multitasking performances. Results obtained show that, through appropriate coding, execution times for a full year simulation of the model, involving the diffusion and the trophic interactions of eight state variables, with a time step of one hour, have been decreased by about an order of magnitude.

Parallel I/O optimization for an air pollution model

2005

This work presents and evaluates different I/O parallelization approaches for the Sulphur Transport Eurelian Model 2 (STEM-II), a large-scale pollution modelling application that is used to simulate air quality conditions. STEM-II is a computationally intensive application that requires of a multiprocessor environment for performing simulations in a reasonable response time. Due to the large amount of data that uses, the I/O becomes a critical factor for the application performance. This paper is focused in the study and optimization of this stage for distributed memory systems. Several parallelization approaches are presented and evaluated for a Cluster of PCs. Experimental results show that the efficient parallelization of the I/O achieves a significant reduction in the overall execution time.

Parallel Computations with Large-scale Air Pollution Models

2003

Large-scale mathematical models are very powerful tools in the efforts to provide more information and more detailed information about the pollution levels, especially about pollution levels which exceed certain critical values.. However, the model used must satisfy at least two conditions: (i) it must be verified that the model results are reliable and (ii) it should be possible to carry out different study by using the model. It is clear that comprehensive studies about relationships between different input parameters and the model results can only be carried out (a) if the numerical methods used in the model are sufficiently fast and (b) if the code runs efficiently on the available high-speed computers. Some results obtained recently by a new unified version of the Danish Eulerian Model will be presented in this paper.