OSA's Digital Library

Applied Optics

Applied Optics

APPLICATIONS-CENTERED RESEARCH IN OPTICS

  • Vol. 42, Iss. 17 — Jun. 10, 2003
  • pp: 3407–3417

SYMNET: An Optical Interconnection Network for Scalable High-Performance Symmetric Multiprocessors

Ahmed Louri and Avinash Karanth Kodi  »View Author Affiliations


Applied Optics, Vol. 42, Issue 17, pp. 3407-3417 (2003)
http://dx.doi.org/10.1364/AO.42.003407


View Full Text Article

Acrobat PDF (248 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

We address the primary limitation of the bandwidth to satisfy the demands for address transactions in future cache-coherent symmetric multiprocessors (SMPs). It is widely known that the bus speed and the coherence overhead limit the snoop/address bandwidth needed to broadcast address transactions to all processors. As a solution, we propose a scalable address subnetwork called symmetric multiprocessor network (SYMNET) in which address requests and snoop responses of SMPs are implemented optically. SYMNET not only has the ability to pipeline address requests, but also multiple address requests from different processors can propagate through the address subnetwork simultaneously. This is in contrast with all electrical bus-based SMPs, where only a single request is broadcast on the physical address bus at any given point in time. The simultaneous propagation of multiple address requests in SYMNET increases the available address bandwidth and lowers the latency of the network, but the preservation of cache coherence can no longer be maintained with the usual fast snooping protocols. A modified snooping cache-coherence protocol, coherence in SYMNET (COSYM) is introduced to solve the coherence problem. We evaluated SYMNET with a subset of Splash-2 benchmarks and compared it with the electrical bus-based MOESI (modified, owned, exclusive, shared, invalid) protocol. Our simulation studies have shown a 5–66% improvement in execution time for COSYM as compared with MOESI for various applications. Simulations have also shown that the average latency for a transaction to complete by use of COSYM protocol was 5–78% better than the MOESI protocol. SYMNET can scale up to hundreds of processors while still using fast snooping-based cache-coherence protocols, and additional performance gains may be attained with further improvement in optical device technology.

© 2003 Optical Society of America

OCIS Codes
(200.4650) Optics in computing : Optical interconnects

Citation
Ahmed Louri and Avinash Karanth Kodi, "SYMNET: An Optical Interconnection Network for Scalable High-Performance Symmetric Multiprocessors," Appl. Opt. 42, 3407-3417 (2003)
http://www.opticsinfobase.org/ao/abstract.cfm?URI=ao-42-17-3407


Sort:  Author  |  Year  |  Journal  |  Reset

References

  1. D. E. Culler, J. P. Singh, and A. Gupta, Parallel Computer Architecture: A Hardware/Software Approach (Morgan Kaufmann, 1999).
  2. A. Charlesworth, “The sun Fireplane SMP interconnect in the Sunfire 3800–6800,” in Hot Interconnects 9, IEEE Comput. Society, Los Alamitus, Calif., 37–42 (2001) www.hotl.org.
  3. F. Pong, M. Dubois, and K. Lee, “Design and performance of SMPs with asynchronous caches,” Tech. Rep. HPL-1999–149, Hewlett Packard, HP Laboratories, Palo Alto, Calif. (1999).
  4. D. A. Patterson and J. L. Hennesey, Computer Architecture: A Quantitative Approach, 2nd ed. (Morgan Kaufman, Los Altos, Calif., 1996).
  5. P. Sweazey and A. J. Smith, “A class of compatible cache consistency protocols and their support by the IEEE futurebus,” in Proceedings of the 13th Annual International Symposium on Computer Architecture, ISCA, 414–423 (1986).
  6. D. A. B. Miller, “Rationale and challenges for optical interconnects to electronic chips,” Proc. IEEE 88, 728–749 (2000).
  7. J. H. Collet, W. Hlayhel, and D. Litaize, “Parallel optical interconnects may reduce the communication bottleneck in symmetric multiprocessors,” Appl. Opt. 40, 3371–3378 (2001).
  8. A. Charlesworth, “Starfire: Extending the SMP envelope,” IEEE Micro. 18, 39–49 (1998).
  9. A. Singhal, D. Broniarczyk, F. Cerauskis, J. Price, L. Yuan, C. Cheng, D. Doblar, S. Fosth, N. Agarwal, K. Harvey, E. Hagersten, and B. Liencres, “Gigaplane: A high performance bus for large SMPs,” in Proceedings Hot Interconnects 4, IEEE Computer Society, Los Alamitos, Calif., 97–112 (1996) www.hotl.org.
  10. M. M. Martin, D. J. Sorin, A. Ailamaki, A. R. Alameldeen, R. M. Dickson, C. J. Mauer, M. Plakal, M. D. Hill, and D. A. Wood, “Timestamp snooping: An approach for extending SMPs,” in Proceedings of the Ninth International Conference on Architectural Support for Programming Languages and Operating Systems, ACM, Cambridge, Mass., November 13–15, 25–36 (2000).
  11. D. J. Sorin, M. Plakal, A. E. Condon, M. D. Hill, M. M. Martin, and D. A. Wood, “Specifying and verifying a broadcast and a multicast snooping cache coherence protocol,” IEEE Transactions on Parallel and Distributed Systems, 13 (2002).
  12. M. M. K. Martin, D. J. Sorin, Mark D. Hill, and David A. Wood, “Bandwidth adaptive snooping,” in 8th International Symposium on High Performance Computer Architecture (HPCA), 224–235 (2002).
  13. J. H. Collet, D. Litaize, J. V. Campenhut, C. Jesshope, M. Desmulliez, H. Thienpont, J. Goodman, and A. Louri, “Architectural approaches to the role of optics in mono and multiprocessor machines,” Appl. Opt. 39, 671–682 (2000).
  14. Y. Liu, “Heterogeneous integration of OE arrays with SI electronics and microoptics,” in Proceedings of the Electronic Components and Technology Conference, 864–869 (2001).
  15. Y. S. Liu, R. J. Wojnarowski, W. A. Hennessy, J. P. Bristow, Y. Liu, A. Peczalski, J. Rowlette, A. Plotts, J. Stack, M. Kader-Kallen, J. Yardley, L. Eldada, R. M. Osgood, R. Scarmozzino, S. H. Lee, V. Ozgus, and S. Patra, “Polymer optical interconnect technology (point)-optoelectronic packaging and interconnect for board and backplane applications,” in Proceedings of the Electronic Components and Technology Conference, 308–315 (1996).
  16. A. V. Krishnamoorthy, K. W. Goossen, L. M. F. Chirovsky, R. G. Rozier, P. Chandramani, S. P. Hui, J. Lopata, J. A. Walker, and L. A. D’Asaro, “16 × 16 VCSEL array flip-chip bonded to CMOS VLSI circuit,” IEEE Photonics Tech. Lett. 12, 1073–1075 (2000).
  17. A. Lindstrom, “Parallel links transform networking equipment,” FiberSystems International, 29–32 (2002).
  18. D. M. Chiarulli, S. P. Levitan, R. G. Melhem, M. Bidnurkar, R. Ditmore, G. Gravenstreter, Z. Guo, C. Qiao, M. F. Sakr, and J. P. Teza, “Optoelectronic buses for high-performance computing,” in Proc. IEEE, 82, 1701–1710 (1994).
  19. C. S. Woo, M. Ohara, E. Torrie, J. P. Singh, and A. Gupta, “The splash-2 programs: Characterization and methodological considerations,” in Proceedings of the 22nd Annual International Symposium on Computer Architecture, ACM, ISCA ’95, Santa Margherita Ligure, Italy, 24–37 (1995).
  20. P. Lukowicz, “The photobus smart pixel interconnection system for symmetric multiprocessing using workstation clusters,” in 6th International Conference on Parallel Interconnects, IEEE, Anchorage, Al, 106–113 (1999).
  21. J.-H. Ha and T. M. Pinkston, “The speed cache coherence for an optical multiaccess interconnect architecture,” in Proceedings of the 2nd International Conference on Massively Parallel Processing Using Optical Interconnections, IEEE, San Antonio, Tex.98–107 (1995).
  22. P. Dowd, J. Perreault, J. Chu, D. C. Hoffmeister, R. Minnich, D. Burns, F. Hady, Y. J. Chen, and M. Dagenais, “Lightning network and systems architecture,” J. Lightwave Technol. 14, 1371–1387 (1996).
  23. B. Webb and A. Louri, “A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems,” IEEE Transactions on Parallel and Distributed Systems, 11, 444–458 (2000).
  24. K. Bogineni and P. W. Dowd, “A collisionless multiple access protocol for wavelength division multiplexed star-coupled configuration: Architecture and performance analysis,” J. Lightwave Technol. 10, 1688–1699 (1992).
  25. A. V. Krishnamoorthy and K. W. Goossen, “Optoelectronic-VLSI: Photonic integrated with VLSI circuits,” IEEE J. Sel. Top. Quantum Electron. 4, 899–912 (1998).
  26. L. Eldada and L. W. Shacklette, “Advances in polymer integrated optics,” IEEE J. Sel. Top. Quantum Electron. 6, 54–68 (2000).
  27. S. S. Saini, Y. Hu, Z. Dilli, R. Grover, M. Dagenais, F. G. Johnson, D. R. Stone, H. Shen, W. Zhou, and J. Pamulapati, “Integrated 1 × 2 loss-less Y-junction splitter on a passive active resonant coupler platform,” in Conference Lasers and Electro-Optics 423–424 (2000).
  28. R. Pu, E. M. Hayes, C. W. Wilmsen, K. D. Ohoquette, H. Q. Hou, and K. M. Geib, “Comparison of techniques for bonding VCSELs directly to ICs,” J. Opt. Soc. Am. A 1, 324–329 (1999).
  29. H. J. J. Yeh and J. S. Smith, “Integration of GaAs vertical cavity surface emitting laser on Si by substrate removal,” Appl. Phys. Lett. 64, 1466–1468 (1994).
  30. T. Sakamoto, H. Tsuda, M. Hikita, T. Kagawa, K. Tateno, and C. Amano, “Optical interconnection using VCSELs and polymeric waveguide circuits,” J. Lightwave Technol. 11, 1487–1492 (2000).
  31. I. Ikodinovic, A. Milenkovic, V. Milutinovic, and D. Magdic, “Limes: A multiprocessor simulation environment for PC platforms,” in Third Conference on Parallel Processing and Applied Mathematics, Institute of Mathematics & Computer Science, Technical University of Czestochowa, PPAM ’99, Kazimierz Dolny, Poland.
  32. A. K. Kodi and A. Louri, “Optical interconnects for large-scale symmetric multiprocessor networks,” in Optics in Computing, SPIE, Vol. 1, Taiwan, April 2002, 7–9 (2002).

Cited By

Alert me when this paper is cited

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.


« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited