Abstract
The architecture and software of the high-performance computer system (HCS) "Siberia" is considered designed in the Computing Center of the Siberian Division of the USSR A. Sc. It is intended for the support of operation of the supercomputing center for global simulation and large-scale computations. The system is based on the large-block system design concept with various special-purpose processors, multiport memory modules, small-computers and even mainframes serving as building blocks. The HCS includes a central multimachine kernal surrounded by a set of special-purpose subsystems of vector-pipeline, vector-parallel and associative types.The HCS operation and application is supported by special parallel programming systems designed for representation of computer-intensive problems as communicating processes adapting to a number of accessible processors; by a resource monitor for controlling heterogeneous modules with different interfaces and by an interactive service system for improving the programmer's environment.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
E. Clementi, R. Caltabiano and others. Large-scale computations on a scalar, vector and parallel "supercomputer" and global ab initio simulations with a study on liquid water as an example. IBM DSD, KGH-86, November 14, 1986, pp.1–58.
E.Clementi and J.Detrich. Large scale parallel computation on a loosely coupled array of processors. In: J.J. Dongarra, editor, Experimental Parallel Computing Architectures, North-Holland, 1987, pp. 141–176.
D.Bergmark, P.Siegel. Parallelism at the Cornell National Supercomputer Facility. 4th Int. conference on supercomputing and 3d world supercomputer exhibition. Tutorial. Santa Clara, CA USA, 1989, pp.1–124.
E.J. Clementi and others. Large-scale computation on a scalar, vector and parallel "supercomputer", Parallel computing, 5, pp. 13–44, 1987.
S. Markov and others. High-performance computer complex. Strategy and evolution, Supercomputer, 31, VI-3, 1989, pp. 12–23.
P.Volcott, S.Goodman. High speed computers of the Soviet Union. Computer,Sept.1988, pp.32–41.
V.A.Anisimov, V.E.Malyshkin, N.N.Mirenkov. Parallel programming language for large-block parallel systems. Simultaneous processes, Novosibirsk, 1989, Computing Center, (Preprint, The USSR Academy of Sciences, Siberian Division., N 824, in Russian).
A.P.Vazhenin. Performance estimation of the algorithms for associative parallel processors, National seminar "Multiprocessor systems software" (abstracts of reports, in Russian), Kalinin, 1988, pp. 213–216.
A.A.Spiridonov. Interactive service system supporting special-purpose processors ES-2706. Ibid, pp. 86–88.
N.V.Kutchin, V.E.Malyshkin, S.A.Pankratov.Handling the resources of special-purpose processor in large-block parallel systems. In "High-performance computer systems and their software" (in Russian), Novosibirsk, 1987, pp. 29–37.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mirenkov, N.N. (1990). High-performance computer system "Siberia". In: Burkhart, H. (eds) CONPAR 90 — VAPP IV. VAPP CONPAR 1990 1990. Lecture Notes in Computer Science, vol 457. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-53065-7_156
Download citation
DOI: https://doi.org/10.1007/3-540-53065-7_156
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53065-7
Online ISBN: 978-3-540-46597-3
eBook Packages: Springer Book Archive