Distributed supercomputing

Author

Marinescu, Dan C. ; Rice, John R. ; Waltsburger, B. ; Houstis, Catherine E. ; Kunz, Thomas ; Waldschmidt, Helmut

Author_Institution

Dept. of Comput. Sci., Purdue Univ., West Lafayette, IN, USA

fYear

1990

fDate

30 Sep-2 Oct 1990

Firstpage

381

Lastpage

387

Abstract

Several design issues for a distributed system capable of supporting high-performance scientific computing are discussed. Two systems prototypes, one based on an object-oriented implementation and a second supporting coscheduling, and their application to distributed partial differential equation (PDE) solvers are presented. The questions explored relate to the proper computation and communication paradigms and the architecture of such systems. The point of view is that in supercomputing the total execution time of an application is a critical performance measure of the system and scheduling policies need to reflect user´s needs rather be concerned only with requirements pertinent solely to resource utilization

Keywords

distributed processing; parallel processing; partial differential equations; performance evaluation; communication paradigms; coscheduling; distributed partial differential equation; distributed supercomputing; distributed system; high-performance scientific computing; object-oriented implementation; performance measure; resource utilization; systems prototypes; Aggregates; Application software; Computer networks; Distributed computing; Engines; High performance computing; Prototypes; Scientific computing; Supercomputers; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Distributed Computing Systems, 1990. Proceedings., Second IEEE Workshop on Future Trends of

Conference_Location

Cairo

Print_ISBN

0-8186-2088-9

Type

conf

DOI

10.1109/FTDCS.1990.138350

Filename

138350