Conducting computational experiments for a module of integration of several computational clusters into single computational complex building unified communication environment
Keywords:
distributed computing, multicluster systems, cluster unification, cluster merge, parallel programming, MPJ-Express add-on, MPI, JavaAbstract
Given paper describes the new instrument of multicluster organization of distributed computations and gives its detailed description using key components and implementation issues as autonomous program module. The purpose of given module and attached broker is to provide framework and execution environment of parallel applications in multicluster computational environments for conducting computational experiments with applied problems of the numerical modeling of the filtration theory merging into unified computational complex several computational clusters. Therefore, built unified communication environment becomes multicluster distributed computational system for solving large scale сomputational problems. Library part of the module, used in program code of applied problems, is MPJ-Express framework add-on and developed using Java programming language. Using Java in developed add-on allows integration into wide range of computer platforms starting form standard desktop Windows systems and finishing with large Linux clusters, which ensures general rule of the ubiquitous computing. The work presented in given article is a part of grant funding project from Kazakhstan government.References
1. Foster I., Kesselman C., Tuecke S. The anatomy of the Grid: enabling scalable virtual organizations //International Journal of High Performance Computing Applications. – 2001. – Vol. 15(3). – P.200-222.
2. Lamanna M. The LHC computing grid project at CERN //Nuclear Instruments and Methods in Physics Research A: Accelerators, Spectrometers, Detectors and Associated Equipmen. – 2004. – Vol. 534, No. 1-2. – P. 1-6.
3. Pordes R. The Open Science Grid – its status and implementation architecture //JPCS Proceedings of International Conference on Computing in High Energy and Nuclear Physics (CHEP07). – 2007. – P.1-20.
4. Snytnikov N., Vshivkov V., Snytnikov V. Study of 3D dynamics of gravitating systems using supercomputers: methods and applications //Parallel Computing Technologies. – 2007. – P. 162-173.
5. Springel V., Yoshida N., White S.D.M. GADGET: a code for collisionless and gasdynamical cosmological simulation//New Astronomy. – 2001. – Vol. 6. – P. 79-117.
6. Balls G.T., Colella P. A finite difference domain decomposition method using local corrections for the solution of Poissons equation //Journal of Computational Physics. – 2002. – Vol. 180. – P. 25-53.
7. Hockney, R.W., Jesshope, C.R. Parallel Computers 2: Architecture, Programming and Algorithms. CRC Press. – 1988. – 642 p.
2. Lamanna M. The LHC computing grid project at CERN //Nuclear Instruments and Methods in Physics Research A: Accelerators, Spectrometers, Detectors and Associated Equipmen. – 2004. – Vol. 534, No. 1-2. – P. 1-6.
3. Pordes R. The Open Science Grid – its status and implementation architecture //JPCS Proceedings of International Conference on Computing in High Energy and Nuclear Physics (CHEP07). – 2007. – P.1-20.
4. Snytnikov N., Vshivkov V., Snytnikov V. Study of 3D dynamics of gravitating systems using supercomputers: methods and applications //Parallel Computing Technologies. – 2007. – P. 162-173.
5. Springel V., Yoshida N., White S.D.M. GADGET: a code for collisionless and gasdynamical cosmological simulation//New Astronomy. – 2001. – Vol. 6. – P. 79-117.
6. Balls G.T., Colella P. A finite difference domain decomposition method using local corrections for the solution of Poissons equation //Journal of Computational Physics. – 2002. – Vol. 180. – P. 25-53.
7. Hockney, R.W., Jesshope, C.R. Parallel Computers 2: Architecture, Programming and Algorithms. CRC Press. – 1988. – 642 p.
Downloads
Issue
Section
Computer Science
