High-Scalability Parallelization of a Molecular Modeling Application: Performance and Productivity Comparison Between OpenMP and MPI Implementations

Brown, Russell; Sharapov, Ilya
October 2007
International Journal of Parallel Programming;Oct2007, Vol. 35 Issue 5, p441
Academic Journal
Important components of molecular modeling applications are estimation and minimization of the internal energy of a molecule. For macromolecules such as proteins and amino acids, energy estimation is performed using empirical equations known as force fields. Over the past several decades, much effort has been directed towards improving the accuracy of these equations, and the resulting increased accuracy has come at the expense of greater computational complexity. For example, the interactions between a protein and surrounding water molecules have been modeled with improved accuracy using the generalized Born solvation model, which increases the computational complexity to O ( n 3). Fortunately, many force-field calculations are amenable to parallel execution. This paper describes the steps that were required to transform the Born calculation from a serial program into a parallel program suitable for parallel execution in both the OpenMP and MPI environments. Measurements of the parallel performance on a symmetric multiprocessor reveal that the Born calculation scales well for up to 144 processors. In some cases the OpenMP implementation scales better than the MPI implementation, but in other cases the MPI implementation scales better than the OpenMP implementation. However, in all cases the OpenMP implementation performs better than the MPI implementation, and requires less programming effort as well.


Related Articles

  • Use of circular variance to quantify the deviation of a macromolecule from the spherical shape. Mezei, Mihaly // Journal of Mathematical Chemistry;Nov2015, Vol. 53 Issue 10, p2184 

    It is shown that the extent of deviation of a molecular shape from spherical can be characterized by comparing the distribution of the circular variances, a measure originally proposed to quantify angular spread, of the vectors from each atom to the rest of the molecule to the circular variance...

  • THE EFFECT OF 8 WEEKS SPECIFIC CORRECTIVE EXERCISE IN WATER AND LAND ON ANGLE OF KYPHOSIS AND SOME PULMONARY INDICES IN KYPHOTIC BOY STUDENTS. Azizi, Ali; Mahdavinejad, Reza; Tizabi, Amin Allah Taheri; Mazreno, Alireza Babai; Nodoushan, Ebrahim Salmani; Behdoust, Mohammad Reza // Sport Science;2012, Vol. 5 Issue 2, p62 

    The purpose of this study was to compare the effect of 8 weeks specific corrective exercise in water and land on the angle of kyphosis and some pulmonary indices in kyphotic students. Thirty males with increased normal thoracic kyphosis (kyphosis ≥40 degrees, 20.70 ±0.705 years old,...

  • Automatic energy calibration algorithm for an RBS setup. Silva, Tiago F.; Moro, Marcos V.; Added, Nemitala; Rizzutto, Marcia A.; Tabacniks, Manfredo H. // AIP Conference Proceedings;May2013, Vol. 1529 Issue 1, p131 

    This work describes a computer algorithm for automatic extraction of the energy calibration parameters from a Rutherford Back-Scattering Spectroscopy (RBS) spectrum. Parameters like the electronic gain, electronic offset and detection resolution (FWHM) of a RBS setup are usually determined using...

  • SQL SERVER & THE DATA WAREHOUSE Explosion. Thompson, Robert // DM Review;May2006, Vol. 16 Issue 5, p38 

    The article describes the problems facing the data warehouse manager with the expansion of data volumes, increasing demand and complexity of data warehousing systems. The structured query language server does not have the scalability credentials to match its functionality leadership. An...

  • Implementation of Scheduling Algorithms for On Chip Communications. Saravanakumar, U.; Rajasekar, K.; Rangarajan, R. // International Journal of Computer Applications;2013, Vol. 62, p35 

    Network on Chips (NoCs) replace traditional busses in highly integrated Multiprocessor System on Chips (MPSoCs). As SoCs, communication issues take much important in NoCs but they need to give contention free architecture with low latency. To meet the above need several methods like handshaking...

  • Java Versus .Net: A Comparative Analysis of Performance, Size and Complexity of Credit Card Authorization Systems. Ab. Hamid, S. Hafizah; Md. Nasir, M. Hairul N.; Hassan, H. // Journal of Applied Sciences;2009, Vol. 9 Issue 4, p689 

    This study presents a comparative analysis of the performance, size and complexity in both the Java and .NET platforms. Two identical prototypes of a credit card authorization engine were developed using the JAVA and .NET programming languages in order to measure and compare the performance of...

  • Comparison of OpenMP 3.0 and Other Task Parallel Frameworks on Unbalanced Task Graphs. Olivier, Stephen; Prins, Jan // International Journal of Parallel Programming;Oct2010, Vol. 38 Issue 5/6, p341 

    The UTS benchmark is used to evaluate the expression and performance of task parallelism in OpenMP 3.0 as implemented in a number of recently released compilers and run-time systems. UTS performs parallel search of an irregular and unpredictable search space, as arises, e.g., in combinatorial...

  • A New Scalable Framework for Emulating Huge Networks. Zahid, M.; Mezrioui, A.; Belmekki, A. // International Journal of Computer Applications;Feb2014, Vol. 88, p11 

    Network emulation and simulation tools are widely used for preproduction, studies and researches purposes. This success is due to the quality of result they provide compared to the real equipments. Another advantage of the network simulators is that the cost of studies and experiences are...

  • Programming a Hypercube Multicomputer. Ranka, Sanjay; Youngju Won; Sahni, Sartaj // IEEE Software;Sep88, Vol. 5 Issue 5, p69 

    Focuses on the programming of a hypercube multicomputers. Development of single-processor computers; Emphasis in high-speed computing; Determination of network organization.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics