skip to main content
10.1145/223982.224364acmconferencesArticle/Chapter ViewAbstractPublication PagesiscaConference Proceedingsconference-collections
Article
Free access

Are crossbars really dead?: the case for optical multiprocessor interconnect systems

Published: 01 May 1995 Publication History

Abstract

Crossbar switches are rarely considered for large, scalable multiprocessor interconnect systems because they require O(n2) switching elements, are difficult to control efficiently and are hard to implement once their size becomes too large to fit on one integrated circuit. However these problems are technology dependent and a recent innovation in fiber optic devices has led to a new implementation of crossbar switches that does not share these problems while retaining the full advantages of a crossbar switch: low latency, high throughput, complete connectivity and multi-cast capability. Moreover, this new technology has several characteristics that allow a distributed control system which scales linearly in the number of attached nodes.The innovation that led to this research is an optical and-gate that can be used to demultiplex multiple high speed data streams that are carried on one common optical medium. Optical time domain multiplexing can combine the data from many nodes and broadcast the result back to all nodes. This paper discusses OTDM technology only to the extent necessary to understand its characteristics and capabilities. The main contribution lies in the description and analysis of interconnect architectures that utilize OTDM to achieve a level performance that is beyond electronic means. It is expected that cost-reduced OTDM systems will become competitive with the next generation of interconnect systems.

References

[1]
Inmos, IMS C104 Packet Routing Switch, The T900 Transputer Productes Overview Manual, April 1991
[2]
Triquint, Crosspoint Switch Products (TQS TCSO32BM), 1994, 2300 Owen St., Santa Clara, CA 95054
[3]
J.E Sokoloff, ER. Prucnal, I. Glesk, M. Kane, A Teraherz Optical Asymmetric Demultiplexer, IEEE Photonics Technology Letters, Vol. 5, No. 7, July 1993
[4]
Michel Chbat, Ph.D. Thesis, Dept. of Electrical Engineering, Princeton University, 1993, Table 4.1
[5]
I. Duling IiI, Ultrshort-Pulse Fiber Lasers at 1.5 Micrometers, Laser Tech Briefs, Spring 1994, Vol. 2, No. 2, p 38.
[6]
EA. Perrier, ER. Prucnal, High-Dimensionalit.v Shared- Medium Photonic Switch, IEEE Transactions on Communications, Vol. 41, No. i, January 1993, p.224
[7]
ER. Prucnal, J.E Sokoloff, I. Glesk, Time-Division Optical Mico-Area Networks, 27th Annual Hawaiian International Conference on System Sciences, January 1994
[8]
D.K. Jeong, et al., HotPads - Macro-Cells for Gigabit I/0, Hot Interconnect Symposium II, Stanford CA, August 1994
[9]
ER. Prucnal, M.A. Santoro, S.K. Sehgal, Ultrafast All-Optical Synchronous Multiple Access Fiber Networks, IEEE J. Select. Areas Communications, SAC-4 #9, pp 1484-1493, AON012
[10]
The First Networsk of Workstatins Workshop, October 4, 1994, San Jose, California
[11]
Agarwal, A.,Kubiatowicz J., Kranz, D., Lim, B., Yeung, D., D'Souza, G., Parkin, M. Sparcle: An Evolutionary Processor Design for Large-Scale Multiprocessors. IEEE Micro, June 1993, pages 48-6 I.
[12]
Lenoski, D. The Design and Analysis of DASH: A Scalable Directory-Based Multiproeessor. PhD Dissertation, Stanford University, December 1991.
[13]
A. Nowatzyk, G. Aybay, M. Browne, E. Kelly, M. Parkin, W. Radke, S. Vishin, S3.mp: Current Status and Future Directions, 4 Workshop on Shared Memory Multiprocessors, ISCA 1994, Chicago, Illinois
[14]
M. Borella, B. Mukherjee, F. Jia, S. Ramamurthy, D. Banerjee, J. Iness, Optical Interconnects for Multiprocesxor Architectures Using Wavelength-Division Multiplexing, 27th Annual Hawaiian International Conference on System Sciences, January 1994
[15]
J.C. Lu, L. Kleinrock, A Wavelength division multiple access protocol for high-speed local area networsk with a passive star topology, Performance Evaluation Journal, Vol. 16, No. 1-3, pp. 223-239, Nov. 1992
[16]
P.W. Dowd, Random Access Protocols for High Speed Interprocessor Communication based on an Optical Passive Star Topology, Journal of Lightwave Technology, ~oi. 9, pp. 799- 808, June 1991
[17]
ER. Prucnal, M.F. Krol, J.L. Stacy, Demonstration of a Rapidly Tunable Optical Time-Division Multiple Access Coder, Photonics Tech. Letters, Vol. 3, #2, pp 170-172, OTV015
[18]
IOT product information on integrated optical components, IOT GmbH, EO.Box 1252, D-68744 Waghausel-Kirrlach, Germany
[19]
A.G. Nowatzyk, M. Parkin, The S3.mp Interconnect System and TIC chip, Hot Interconnect Symposium, Stanford CA, August 1993

Cited By

View all
  • (2004)Communication Models for a Free-Space Optical Cross-Connect SwitchThe Journal of Supercomputing10.1023/A:102629472170427:1(19-48)Online publication date: 1-Jan-2004
  • (2000)A highly-scalable, rapidly-reconfigurable, multicasting-capable, 100-Gb/s photonic switched interconnect based upon OTDM technologyJournal of Lightwave Technology10.1109/50.90877418:12(1892-1904)Online publication date: 2000
  • (1998)OPTNETProceedings of the 12th international conference on Supercomputing10.1145/277830.277929(401-408)Online publication date: 13-Jul-1998
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
ISCA '95: Proceedings of the 22nd annual international symposium on Computer architecture
July 1995
426 pages
ISBN:0897916980
DOI:10.1145/223982
  • cover image ACM SIGARCH Computer Architecture News
    ACM SIGARCH Computer Architecture News  Volume 23, Issue 2
    Special Issue: Proceedings of the 22nd annual international symposium on Computer architecture (ISCA '95)
    May 1995
    412 pages
    ISSN:0163-5964
    DOI:10.1145/225830
    Issue’s Table of Contents
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 May 1995

Permissions

Request permissions for this article.

Check for updates

Qualifiers

  • Article

Conference

ISCA95
Sponsor:
ISCA95: International Conference on Computer Architecture
June 22 - 24, 1995
S. Margherita Ligure, Italy

Acceptance Rates

Overall Acceptance Rate 543 of 3,203 submissions, 17%

Upcoming Conference

ISCA '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)64
  • Downloads (Last 6 weeks)10
Reflects downloads up to 21 Sep 2024

Other Metrics

Citations

Cited By

View all
  • (2004)Communication Models for a Free-Space Optical Cross-Connect SwitchThe Journal of Supercomputing10.1023/A:102629472170427:1(19-48)Online publication date: 1-Jan-2004
  • (2000)A highly-scalable, rapidly-reconfigurable, multicasting-capable, 100-Gb/s photonic switched interconnect based upon OTDM technologyJournal of Lightwave Technology10.1109/50.90877418:12(1892-1904)Online publication date: 2000
  • (1998)OPTNETProceedings of the 12th international conference on Supercomputing10.1145/277830.277929(401-408)Online publication date: 13-Jul-1998
  • (1996)An Optical Interconnect Model for k-ary n-cube Wormhole NetworksProceedings of the 10th International Parallel Processing Symposium10.5555/645606.661200(666-672)Online publication date: 15-Apr-1996
  • (1996)Memory organization in multi-channel optical networksProceedings of the 10th international conference on Supercomputing10.1145/237578.237582(26-34)Online publication date: 1-Jan-1996
  • (1996)An optical interconnect model for k-ary n-cube wormhole networksProceedings of International Conference on Parallel Processing10.1109/IPPS.1996.508129(666-672)Online publication date: 1996
  • (1996)A hybrid cache coherence protocol for a decoupled multi-channel optical network: SPEED DMONProceedings of the 1996 ICPP Workshop on Challenges for Parallel Processing10.1109/ICPP.1996.537157(164-171)Online publication date: 1996
  • (2019)A Scalable Interconnection Network Architecture for Petaflops ComputingThe Journal of Supercomputing10.1023/B:SUPE.0000009318.91562.b027:2(103-128)Online publication date: 1-Jun-2019
  • (2005)Goodness of time-processor optimal PRAM simulationsEuro-Par'96 Parallel Processing10.1007/BFb0024716(303-306)Online publication date: 10-Jun-2005
  • (2003)Optoelectronic interconnection technology in the holms systemIEEE Journal of Selected Topics in Quantum Electronics10.1109/JSTQE.2003.8154929:2(624-635)Online publication date: Mar-2003
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Get Access

Login options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media