Abstract
Optics can be used to build faster and more complex inter-connection networks for parallel processors. Such systems will be composed of arrays of electronic processing elements interconnected with three-dimensional free space optics. We call this a 3D optoelectronic computer. We show that for the conjugate gradient benchmark an architecture with an adequately fast reconfigurable interconnection network can outperform all parallel supercomputers, but its performance is not as impressive when a fixed network is used. In the case of the multigrid benchmark, the 3D optoelectronic architecture can perform orders of magnitude better than the best parallel supercomputers.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
D. Bailey, et al.: The NAS Parallel Benchmarks. RNR Tech. Rep. RNR-94-007 (1994)
G. A. Betzos and P. A. Mitkas: Performance evaluation of 3D optoelectronic computer architectures bAsed on the FFT and sorting benchmarks. Proc. MPPOI'95 (1995) 160–167
V. Morozov, J. Neff, H. Temkin, and A. Fedor: Analysis of a three-dimensional computer optical scheme based on bidirectional free-space optical interconnects. Opt. Eng., 34 (1995) 523–534
R. A. Nordin: Optical interconnects in electronic processing systems. Chapter 9 in Photonics in Switching, 1, Academic Press, 1993
S. Saini and D. Bailey: NAS parallel benchmark results 12-95. NAS Tech. Rep. NAS-95-021 (1995)
E. Schenfeld: Massively parallel processing with optical interconnections: what can be, should be and must not be done by optics. Opt. Comp., 10 (1995) 16–18
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Betzos, G.A., Mitkas, P.A. (1996). 3D optoelectronic computer architectures for the conjugate gradient and multigrid benchmark algorithms. In: Bougé, L., Fraigniaud, P., Mignotte, A., Robert, Y. (eds) Euro-Par'96 Parallel Processing. Euro-Par 1996. Lecture Notes in Computer Science, vol 1124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0024736
Download citation
DOI: https://doi.org/10.1007/BFb0024736
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61627-6
Online ISBN: 978-3-540-70636-6
eBook Packages: Springer Book Archive