Abstract
Proponents of data flow machines always emphasize the high potential for parallelization and the high performance on numerical applications reachable by that kind of architecture. On the other hand opponents critisize the additional overhead during run time and the difficulties of the memory management. In order to evaluate the cost effectiveness of dynamical data flow machines we compare a well known representative, the Monsoon designed at the MIT, with two vector processors, the Cray I and the Spark 2.0. This comparison is based on a theoretical model, which provides measures for the run time and the cost of the machines. As numerical workload we have chosen some kernels from the Livermore Loops benchmark. In this paper we briefly review the evaluation model, we describe the machines under consideration and finally we present our results of the comparison.
Preview
Unable to display preview. Download preview PDF.
References
Abolhassan F., Keller J., Paul W.J.; On the Cost-Effectiveness of PRAMs; Proc. of the 3rdIEEE Symposium on Parallel and Distributed Processing, IEEE Computer Society Press, 2–9, 1991
Arvind, Nikhil R.S.; Executing a Programm on the MIT Tagged-Token Dataflow Architecture; Proceedings of the PARLE Conference, Netherlands 1987
Auerbach D.J., Paul W.J., Bakker A.F., Lutz C., Rudge W.E. and Abraham F.F.; A Special Purpose Parallel Computer for Molecular Dynamics: Motivation, Design, Implementation, and Application; J. Phys. Chem., 91, 4881–4890, 1987
Aho A.V., Sethi R., Ullman J.D.; Compilers: Principles, Techniques, and Tools; Addison-Wesley, Reading, MA, 1985
Abolhassan F., Drefenstedt R., Keller J., Paul W.J., Scheerer D.; On the Physical Design of PRAMs; in Buchmann, Ganzinger, Paul (Hrsg.): Teubner-Texte zur Informatik, Teubner 1992, Bd. 1, 1–19
Cray Research, Inc.; Cray I Computer Systems, Mainframe Reference Manual HR-0029; Cray Research, Inc., 1982
Culler D.E.; Managing Parallelism and Resources in Scientific Dataflow Programs; Technical Report TR-446, MIT Lab. for Comp. Sci., Cambridge MA, 1990
Culler D.E., Papadopulos G.M.; The Explicit Token Store; CSG Memo 312, MIT Lab. for Comp. Sci., Cambridge MA, 1990
Drefenstedt R., Schmidt D.; On the Physical Design of Butterfly Networks for PRAMs; Proceedings of the 4thSymposium on the Frontiers of Massively Parallel Computation, McLean, Virginia, IEEE Computer Society Press, Los Alamitos, CA, 202–209, 1992
Feo J.T.; An Analysis of the Computational and Parallel Complexity of the Livermore Loops; Parallel Computing, Vol. 7, 163–185, 1988
Formella A.; Entwurf, Bau und Test eines Vektor-Prozessors mit parallel arbeitenden Operationseinheiten, Spark 2.0 Teil I; Diplomarbeit, Universität des Saarlandes, FB14 Informatik, 1989
Formella A.; Leistung und Güte numerischer Vektorrechnerarchitekturen; Dissertation, Universität des Saarlandes, FB14 Informatik, 1992
Formella A., Obé A., Paul W.J., Rauber T., Schmidt D.; The Spark 2.0 System — A Special Purpose Vector Processor with a VectorPascal Compiler; Proceedings of the Hawaii 25th International Symposium on System Science HICSS-25, Vol. 1, 547–558, 1992
Gurd, Kirkham, Watson; The Manchester Prototype Dataflow Computer; Comm. of the ACM, 28, 1985
Hiraki, Sekiguchi, Shimada; The SIGMA-1 Dataflow Supercomputer: A Challange for New Generation Computing Systems; Journal of Information Processing, 10(4), 1987
Hockney R.W., Jesshope C.R.; Parallel Computers 2: Architecture, Programming and Algorithms; Adam Hilger, Bristol and Philadelphia, 1990
Hennessy J.L., Patterson D.A.; Computer Architecture: A Quantitative Approach; Morgan Kaufmann Publishers, Inc., San Mateo, California, 1990
Martin J.L., Editor; Performance Evaluation of Supercomputers; Elsevier Science Publishers B.V., Amsterdam, 1988
McMahon F.H.; Fortran Kernels, MFlops, file modicikation date Feb 29; Lawrence Livermore National Laboratory, 1984
McMahon F.H.; L.L.N.L. Fortran Kernels: MFLOPS; Lawrence Livermore National Laboratory, 1986
McMahon F.H.; The Livermore Fortran Kernels Test of the Numerical Performance Range; Lawrence Livermore National Laboratory, 1988
Motorola; H4C Series Design Reference Guide; Motorola Inc., 1991
Nikhil R.S.; Id World Reference Manual; CSG Memo 317, MIT Lab. for Comp. Sci., Cambridge MA, 1987
Nikhil R.S.; Id Version 90.0 Reference Manual; CSG Memo 284-1, MIT Lab. for Comp. Sci., Cambridge MA, 1990
Obé A.; Entwurf, Bau und Test eines Vektor-Prozessors mit parallel arbeitenden Operationseinheiten, Spark 2.0 Teil III; Diplomarbeit, Universität des Saarlandes, FB14 Informatik, 1989
Papadopoulus G.M.; Implementation of a Gerneral Purpose Dataflow Multiprocessor; Technical Report TR-432, MIT Lab. for Comp. Sci., Cambridge MA, 1988
Papadopulos G.M., Culler D.E.; Monsoon: An Explicit Token Store Architecture; CSG Memo 306, MIT Lab. for Comp. Sci., Cambridge MA, 1990
Paul W.J., Müller S.M.; Towards a Formal Theory of Computer Architecture; Parcella 90, Research in Informatics, Akademie Verlag, S. 157–169, Berlin 1990
Russell M.R.; The Cray I Computer System; Comm. ACM, Vol. 21, no. 1, 63–72, 1978
Schmidt D.; Entwurf, Bau und Test eines Vektor-Prozessors mit parallel arbeitenden Operationseinheiten, Spark 2.0 Teil II; Diplomarbeit, Universität des Saarlandes, FB14 Informatik, 1989
Traub K.R., Papadopoulos G.M., Beckerle M.J., Hicks J.E., Young J.; Overview of the Monsoon Project; Motorola Technical Report MCRC-TR-15, Cambridge MA, 1991
Traub K.R.; A Compiler for the MIT TTDA; Technical Report TR-370, MIT Lab. for Comp. Sci., Cambridge MA, 1986
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Formella, A., Massonne, W., Paul, W.J. (1993). Cost effectiveness of data flow machines and vector processors. In: Meyer, F., Monien, B., Rosenberg, A.L. (eds) Parallel Architectures and Their Efficient Use. Nixdorf 1992. Lecture Notes in Computer Science, vol 678. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56731-3_7
Download citation
DOI: https://doi.org/10.1007/3-540-56731-3_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56731-8
Online ISBN: 978-3-540-47637-5
eBook Packages: Springer Book Archive