Abstract
The parallelization of numerical programs for distributed-memory multiprocessing systems in SUPERB is guided by a distribution of the data structures onto a set of processes. Since processes can only access their local address space, explicit communication has to be inserted to provide access to non-local data. This paper discusses an approach for the optimization of communication, which is vital for obtaining efficient parallel programs.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
Literatur
C.D. Callahan, K. Kennedy, Compiling programs for distributed-memory multiprocessors,J.Supercomputing, Vol.2, pp.151–169, (Oct.1988)
C.D. Callahan, A Global Approach to Detection of Parallelism, Ph.D. Dissertation, Rice University, Houston, Texas (1987)
R.G.Cytron, Compile-Time Scheduling and Optimization for Asynchronous Machines, Ph.D. Dissertation, Department of Computer Science, University of Illinois at Urbana-Champaign (Oct.1984)
G.C.Fox, P.Messina, The Caltech Concurrent Computation Program Annual Report 1986–1987, California Institue of Technology, Report C3P-487, (Jan. 1988)
G. Fox, P. Messina, Report on the Caltech Concurrent Computation Program, Caltech, Report C3P-685, (1988)
H.M. Gerndt, Array Distribution in SUPERB, Proceedings of the 3rd International Conference on Supercomputing 1989, pp.164–174, ACM, (1989)
H.M. Gerndt, Parallelization for Distributed-Memory Multiprocessing Systems, Ph.D. Dissertation, University Bonn, Informatik Institutsberichte, (1989)
H.M.Gerndt, H.P.Zima, MIMD parallelization for SUPRENUM, In: E.N. Houstis, T.S. Papatheodorou, C.C. Polychronopoulos (Eds.), Proc. 1st International Conference on Supercomputing, Athens, Greece (June 1987), LNCS 297, pp. 278–293
W.K. Giloi, SUPRENUM: A trendsetter in modern supercomputer development,Parallel Computing 7 (1988),283–296
F. Irigoin, Partitionnement des Boucles Imbriquees, Ph.D.Dissertation, Ecole Nationale Superieure des Mines de Paris, (1987)
Ken Kennedy, Hans P. Zima, Virtual Shared Memory for Distributed-Memory Machines, Proc. 9th Int. Hypercube Conf. 1989, Monterey, USA
D.J. Kuck, A Survey of Parallel Machine Organization and Programming, Computing Surveys, Vol.9, No.1, (March 1977), pp.29–59
L. Lamport, The Parallel Execution of DO Loops, Comm. ACM 17(2), pp.83–93 (Feb.1974)
D.A. Padua, D.J. Kuck, High-Speed Multiprocessors and Compilation Techniques, IEEE Transactions on Computers, Vol C-29, No.9, (Sep. 1980), pp.763–776
A.Rogers, K.Pingali.: Process Decomposition Through Locality of Reference, Proc. ACM SIGPLAN 1989 Conference on Programming Language Design and Implementation, 69–80
H.P. Zima, H.J. Bast, M. Gerndt, SUPERB — A Tool for Semi Automatic MIMD/SIMD Parallelization, Parallel Computing 6(1988), pp.1–18
H.P.Zima, H.J.Bast, M.Gerndt, P.J.Hoppen, Semi-Automatic Parallelization of Fortran Programs,In: HΣndler et. al.: CONPAR86, Lecture Notes in Computer Science 237, pp. 287–294
Hans P.Zima, Das SUPRENUM System: Architektur,Software und Anwendungen. In: U.Kastens,F.S.Rammig(Eds.),Proc.GI/ITG-Fachtagung Architektur und Betrieb von Rechensystemen,Informatik Fachberichte 168,1–20,Springer Verlag,Berlin
Hans P.Zima, Barbara Chapman, Supercompilers for Parallel and Vector Computers, ACM Press Frontier Series, ACM Press, New York and Addison-Wesley, Reading, Massachusetts (to appear 1990)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gerndt, H.M., Zima, H.P. (1990). Optimizing communication in SUPERB. 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_109
Download citation
DOI: https://doi.org/10.1007/3-540-53065-7_109
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