Abstract

We investigate the advantages and disadvantages of different loopback buffer architectures for optical switches and compare their performance via simulation. The simulation results show that, without the use of virtual output queuing, the head-of-line blocking can be alleviated by wavelength parallelism when each separate queue in a loopback buffer has multiple transmitters. Furthermore, the proposed two-level flow control can eliminate packet drop at the switch, resolve rate mismatching due to output queuing at switch outputs, and ensure that congestion occurring at the hotspot port will not affect the performance of non-congested ports.

© 2011 OSA

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. L. A. Barroso and U. Hölzle, "Introduction," The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, Morgan & Claypool, 2009, pp. 1‒11.
  2. X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.
  3. "Data center architecture overview," Cisco Data Center Infrastructure 2.5 Design Guide, Cisco, 2007, pp. 7‒16[Online]. Available: http://www.cisco.com/univercd/cc/td/doc/solution/dcidg21.pdf.
  4. M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," Proc. ACM SIGCOMM 2008 Conf. Data Communication, 2008, pp. 63‒74.
  5. "Architectural overview," InfiniBand Architecture Specification Volume 1, Release 1.0, 2001, pp. 61‒63[Online]. Available: http://www.infinibandta.org/specs.
  6. N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.
  7. G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.
  8. J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.
  9. B. Webb and A. Louri, "A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems," IEEE Trans. Parallel Distrib. Syst. 11, (5), 444‒458 (2000).
    [CrossRef]
  10. A. Louri and A. Kodi, "An optical interconnection network and a modified snooping protocol for the design of large-scale symmetric multiprocessors (SMPs)," IEEE Trans. Parallel Distrib. Syst. 15, (11), 1093‒1104 (2004).
    [CrossRef]
  11. R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
    [CrossRef]
  12. C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
    [CrossRef]
  13. R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
    [CrossRef]
  14. C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
    [CrossRef]
  15. O. Liboiron-Ladouceur, A. Shacham, B. A. Small, B. G. Lee, H. Wang, C. P. Lai, A. Biberman, and K. Bergman, "The data vortex optical packet switched interconnection network," J. Lightwave Technol. 26, (13), 1777‒1789 (2008).
    [CrossRef]
  16. K. Bergman, D. Keezer, and S. Wills, "Design, demonstration and evaluation of an all optical processor memory-interconnection network for petaflop supercomputing," ACS Interconnects Workshop, 2010, p. 16[Online]. Available: http://lightwave.ee.columbia.edu/?s=research&p=high-performance_computing_systems#dv.
  17. H. Yang and S. J. B. Yoo, "Combined input and output all-optical variable buffered switch architecture for future optical routers," IEEE Photon. Technol. Lett. 17, 1292‒1294 (2005).
    [CrossRef]
  18. S. J. B. Yoo, "Optical packet and burst switching technologies for the future photonic Internet," J. Lightwave Technol. 24, 4468‒4492 (2006).
    [CrossRef]
  19. S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
    [CrossRef]
  20. M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
    [CrossRef]
  21. W. D. Zhong and R. S. Tucker, "Wavelength routing-based photonic packet buffers and their applications in photonic packet switching systems," J. Lightwave Technol. 16, (10), 1737‒1745 (1998).
    [CrossRef]
  22. D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
    [CrossRef]
  23. M. C. Chia, D. K. Hunter, I. Andonovic, P. Ball, I. Wright, S. P. Ferguson, K. M. Guild, and M. J. O’Mahony, "Packet loss and delay performance of feedback and feed-forward arrayed-waveguide gratings-based optical packet switches with WDM inputs-outputs," J. Lightwave Technol. 19, (9), 1241‒1254 (2011).
    [CrossRef]
  24. Z. Zhang and Y. Yang, "Performance analysis of optical packet switches enhanced with electronic buffering," Proc. IEEE Int. Symp. Parallel & Distributed Processing, 2009, pp. 1‒9.
  25. Z. Guo, Z. Zhang, and Y. Yang, "Performance modeling of hybrid optical packet switches with shared buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1530‒1538.
  26. L. Liu, Z. Zhang, and Y. Yang, "Packet scheduling in a low-latency optical switch with wavelength division multiplexing and electronic buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1692‒1700.
  27. S. J. B. Yoo, "Wavelength conversion technologies for WDM network applications," J. Lightwave Technol. 14, (6), 955‒966 (1996).
    [CrossRef]

2011

2008

2007

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

2006

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

S. J. B. Yoo, "Optical packet and burst switching technologies for the future photonic Internet," J. Lightwave Technol. 24, 4468‒4492 (2006).
[CrossRef]

2005

H. Yang and S. J. B. Yoo, "Combined input and output all-optical variable buffered switch architecture for future optical routers," IEEE Photon. Technol. Lett. 17, 1292‒1294 (2005).
[CrossRef]

2004

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

A. Louri and A. Kodi, "An optical interconnection network and a modified snooping protocol for the design of large-scale symmetric multiprocessors (SMPs)," IEEE Trans. Parallel Distrib. Syst. 15, (11), 1093‒1104 (2004).
[CrossRef]

2003

S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
[CrossRef]

M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
[CrossRef]

2002

R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
[CrossRef]

2000

B. Webb and A. Louri, "A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems," IEEE Trans. Parallel Distrib. Syst. 11, (5), 444‒458 (2000).
[CrossRef]

1998

W. D. Zhong and R. S. Tucker, "Wavelength routing-based photonic packet buffers and their applications in photonic packet switching systems," J. Lightwave Technol. 16, (10), 1737‒1745 (1998).
[CrossRef]

D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
[CrossRef]

1996

S. J. B. Yoo, "Wavelength conversion technologies for WDM network applications," J. Lightwave Technol. 14, (6), 955‒966 (1996).
[CrossRef]

Abel, F.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Abts, D.

J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.

Akella, V.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Al-Fares, M.

M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," Proc. ACM SIGCOMM 2008 Conf. Data Communication, 2008, pp. 63‒74.

Andersen, D. G.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Andonovic, I.

Ball, P.

Banerjee, D.

D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
[CrossRef]

Barroso, L. A.

L. A. Barroso and U. Hölzle, "Introduction," The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, Morgan & Claypool, 2009, pp. 1‒11.

Baw, C.

R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
[CrossRef]

Bazzaz, H. H.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Bergman, K.

O. Liboiron-Ladouceur, A. Shacham, B. A. Small, B. G. Lee, H. Wang, C. P. Lai, A. Biberman, and K. Bergman, "The data vortex optical packet switched interconnection network," J. Lightwave Technol. 26, (13), 1777‒1789 (2008).
[CrossRef]

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

K. Bergman, D. Keezer, and S. Wills, "Design, demonstration and evaluation of an all optical processor memory-interconnection network for petaflop supercomputing," ACS Interconnects Workshop, 2010, p. 16[Online]. Available: http://lightwave.ee.columbia.edu/?s=research&p=high-performance_computing_systems#dv.

Biberman, A.

Bregni, S.

S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
[CrossRef]

Chamberlain, R.

R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
[CrossRef]

Chia, M. C.

Dally, W. J.

J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.

Dill, P.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Fainman, Y.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Farrington, N.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Ferguson, S. P.

Frank, J.

D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
[CrossRef]

Franklin, M.

R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
[CrossRef]

Grzybowski, R.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Grzybowski, R. R.

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

Guild, K. M.

Guo, Z.

Z. Guo, Z. Zhang, and Y. Yang, "Performance modeling of hybrid optical packet switches with shared buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1530‒1538.

Gusat, M.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Hawkins, C.

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

Hemenway, R.

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

Hemenway, R. R.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Hölzle, U.

L. A. Barroso and U. Hölzle, "Introduction," The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, Morgan & Claypool, 2009, pp. 1‒11.

Hunter, D. K.

Iliadis, I.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Kaminsky, M.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Keezer, D.

K. Bergman, D. Keezer, and S. Wills, "Design, demonstration and evaluation of an all optical processor memory-interconnection network for petaflop supercomputing," ACS Interconnects Workshop, 2010, p. 16[Online]. Available: http://lightwave.ee.columbia.edu/?s=research&p=high-performance_computing_systems#dv.

Kim, J.

J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.

Kodi, A.

A. Louri and A. Kodi, "An optical interconnection network and a modified snooping protocol for the design of large-scale symmetric multiprocessors (SMPs)," IEEE Trans. Parallel Distrib. Syst. 15, (11), 1093‒1104 (2004).
[CrossRef]

Kozuch, M.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Krishnamurthy, R.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Lai, C. P.

Lee, B. G.

Liboiron-Ladouceur, O.

Liu, L.

L. Liu, Z. Zhang, and Y. Yang, "Packet scheduling in a low-latency optical switch with wavelength division multiplexing and electronic buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1692‒1700.

Loukissas, A.

M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," Proc. ACM SIGCOMM 2008 Conf. Data Communication, 2008, pp. 63‒74.

Louri, A.

A. Louri and A. Kodi, "An optical interconnection network and a modified snooping protocol for the design of large-scale symmetric multiprocessors (SMPs)," IEEE Trans. Parallel Distrib. Syst. 15, (11), 1093‒1104 (2004).
[CrossRef]

B. Webb and A. Louri, "A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems," IEEE Trans. Parallel Distrib. Syst. 11, (5), 444‒458 (2000).
[CrossRef]

Luijten, R.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

Maier, M.

M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
[CrossRef]

Mejia, P.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Minkenberg, C.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

Mukherjee, B.

D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
[CrossRef]

Muller, P.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Ng, T. S. E.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

O’Mahony, M. J.

Papagiannaki, K.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Papen, G.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Pattavina, A.

S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
[CrossRef]

Porter, G.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Proietti, R.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Radhakrishnan, S.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Reisslein, M.

M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
[CrossRef]

Ryan, M.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Scheutzow, M.

M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
[CrossRef]

Schiattarella, E.

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

Scott, S.

J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.

Shacham, A.

Small, B. A.

O. Liboiron-Ladouceur, A. Shacham, B. A. Small, B. G. Lee, H. Wang, C. P. Lai, A. Biberman, and K. Bergman, "The data vortex optical packet switched interconnection network," J. Lightwave Technol. 26, (13), 1777‒1789 (2008).
[CrossRef]

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

Subramanya, V.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

Tucker, R. S.

Vahdat, A.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," Proc. ACM SIGCOMM 2008 Conf. Data Communication, 2008, pp. 63‒74.

Vegetti, G.

S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
[CrossRef]

Wang, G.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

Wang, H.

Webb, B.

B. Webb and A. Louri, "A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems," IEEE Trans. Parallel Distrib. Syst. 11, (5), 444‒458 (2000).
[CrossRef]

Wills, D. S.

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

Wills, S.

K. Bergman, D. Keezer, and S. Wills, "Design, demonstration and evaluation of an all optical processor memory-interconnection network for petaflop supercomputing," ACS Interconnects Workshop, 2010, p. 16[Online]. Available: http://lightwave.ee.columbia.edu/?s=research&p=high-performance_computing_systems#dv.

Wright, I.

Yang, H.

H. Yang and S. J. B. Yoo, "Combined input and output all-optical variable buffered switch architecture for future optical routers," IEEE Photon. Technol. Lett. 17, 1292‒1294 (2005).
[CrossRef]

Yang, Y.

Z. Guo, Z. Zhang, and Y. Yang, "Performance modeling of hybrid optical packet switches with shared buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1530‒1538.

L. Liu, Z. Zhang, and Y. Yang, "Packet scheduling in a low-latency optical switch with wavelength division multiplexing and electronic buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1692‒1700.

Z. Zhang and Y. Yang, "Performance analysis of optical packet switches enhanced with electronic buffering," Proc. IEEE Int. Symp. Parallel & Distributed Processing, 2009, pp. 1‒9.

Ye, X.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Yin, Y.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Yoo, S. J. B.

S. J. B. Yoo, "Optical packet and burst switching technologies for the future photonic Internet," J. Lightwave Technol. 24, 4468‒4492 (2006).
[CrossRef]

H. Yang and S. J. B. Yoo, "Combined input and output all-optical variable buffered switch architecture for future optical routers," IEEE Photon. Technol. Lett. 17, 1292‒1294 (2005).
[CrossRef]

S. J. B. Yoo, "Wavelength conversion technologies for WDM network applications," J. Lightwave Technol. 14, (6), 955‒966 (1996).
[CrossRef]

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

Zhang, Z.

Z. Guo, Z. Zhang, and Y. Yang, "Performance modeling of hybrid optical packet switches with shared buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1530‒1538.

Z. Zhang and Y. Yang, "Performance analysis of optical packet switches enhanced with electronic buffering," Proc. IEEE Int. Symp. Parallel & Distributed Processing, 2009, pp. 1‒9.

L. Liu, Z. Zhang, and Y. Yang, "Packet scheduling in a low-latency optical switch with wavelength division multiplexing and electronic buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1692‒1700.

Zhong, W. D.

IEEE J. Sel. Areas Commun.

S. Bregni, A. Pattavina, and G. Vegetti, "Architectures and performance of AWG-based optical switching nodes for IP networks," IEEE J. Sel. Areas Commun. 21, (7), 1113‒1121 (2003).
[CrossRef]

M. Maier, M. Scheutzow, and M. Reisslein, "The arrayed-waveguide grating-based single-hop WDM network: An architecture for efficient multicasting," IEEE J. Sel. Areas Commun. 21, (9), 1414‒1432 (2003).
[CrossRef]

D. Banerjee, J. Frank, and B. Mukherjee, "Passive optical network architecture based on waveguide grating routers," IEEE J. Sel. Areas Commun. 16, (7), 1040‒1050 (1998).
[CrossRef]

IEEE Micro

C. Minkenberg, F. Abel, P. Muller, R. Krishnamurthy, M. Gusat, P. Dill, I. Iliadis, R. Luijten, R. R. Hemenway, R. Grzybowski, and E. Schiattarella, "Designing a crossbar scheduler for HPC applications," IEEE Micro 26, (3), 58‒71 (2006).
[CrossRef]

IEEE Photon. Technol. Lett.

H. Yang and S. J. B. Yoo, "Combined input and output all-optical variable buffered switch architecture for future optical routers," IEEE Photon. Technol. Lett. 17, 1292‒1294 (2005).
[CrossRef]

IEEE Trans. Parallel Distrib. Syst.

C. Hawkins, B. A. Small, D. S. Wills, and K. Bergman, "The data vortex, an all optical path multicomputer interconnection network," IEEE Trans. Parallel Distrib. Syst. 18, (3), 409‒420 (2007).
[CrossRef]

B. Webb and A. Louri, "A class of highly scalable optical crossbar-connected interconnection networks (SOCNs) for parallel computing systems," IEEE Trans. Parallel Distrib. Syst. 11, (5), 444‒458 (2000).
[CrossRef]

A. Louri and A. Kodi, "An optical interconnection network and a modified snooping protocol for the design of large-scale symmetric multiprocessors (SMPs)," IEEE Trans. Parallel Distrib. Syst. 15, (11), 1093‒1104 (2004).
[CrossRef]

R. Chamberlain, M. Franklin, and C. Baw, "Gemini: An optical interconnection network for parallel processing," IEEE Trans. Parallel Distrib. Syst. 13, (10), 1038‒1055 (2002).
[CrossRef]

J. Lightwave Technol.

J. Optical Netw.

R. Hemenway, R. R. Grzybowski, C. Minkenberg, and R. Luijten, "Optical-packet-switched interconnect for supercomputer applications," J. Optical Netw. 3, 900‒913 (2004).
[CrossRef]

Other

Z. Zhang and Y. Yang, "Performance analysis of optical packet switches enhanced with electronic buffering," Proc. IEEE Int. Symp. Parallel & Distributed Processing, 2009, pp. 1‒9.

Z. Guo, Z. Zhang, and Y. Yang, "Performance modeling of hybrid optical packet switches with shared buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1530‒1538.

L. Liu, Z. Zhang, and Y. Yang, "Packet scheduling in a low-latency optical switch with wavelength division multiplexing and electronic buffer," Proc. 30th IEEE Int. Conf. Computer Communications, 2011, pp. 1692‒1700.

L. A. Barroso and U. Hölzle, "Introduction," The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, Morgan & Claypool, 2009, pp. 1‒11.

X. Ye, P. Mejia, Y. Yin, R. Proietti, S. J. B. Yoo, and V. Akella, "DOS—A scalable optical switch for datacenters," Proc. ACM/IEEE Symp. Architectures for Networking and Communications Systems, 2010, pp. 1‒12.

"Data center architecture overview," Cisco Data Center Infrastructure 2.5 Design Guide, Cisco, 2007, pp. 7‒16[Online]. Available: http://www.cisco.com/univercd/cc/td/doc/solution/dcidg21.pdf.

M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," Proc. ACM SIGCOMM 2008 Conf. Data Communication, 2008, pp. 63‒74.

"Architectural overview," InfiniBand Architecture Specification Volume 1, Release 1.0, 2001, pp. 61‒63[Online]. Available: http://www.infinibandta.org/specs.

N. Farrington, G. Porter, S. Radhakrishnan, H. H. Bazzaz, V. Subramanya, Y. Fainman, G. Papen, and A. Vahdat, "Helios: A hybrid electrical/optical switch architecture for modular data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 339‒350.

G. Wang, D. G. Andersen, M. Kaminsky, K. Papagiannaki, T. S. E. Ng, M. Kozuch, and M. Ryan, "c-Through: Part-time optics in data centers," Proc. ACM SIGCOMM 2010 Conf. Data Communication, 2010, pp. 327‒338.

J. Kim, W. J. Dally, S. Scott, and D. Abts, "Technology-driven, highly-scalable dragonfly topology," Proc. 35th Int. Symp. Computer Architecture, 2008, pp. 77‒88.

K. Bergman, D. Keezer, and S. Wills, "Design, demonstration and evaluation of an all optical processor memory-interconnection network for petaflop supercomputing," ACS Interconnects Workshop, 2010, p. 16[Online]. Available: http://lightwave.ee.columbia.edu/?s=research&p=high-performance_computing_systems#dv.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (19)

Fig. 1
Fig. 1

(Color online) Overview of the proposed optical hybrid switch architecture. OLG: optical label generator; PE: packet encapsulation; LE: label extractor; FDL: fiber delay line; PA: packet aggregation; O/E: optical-to-electrical converter; E/O: electrical-to-optical converter; TX: transmitter; RX: receiver; L ( i ) : label from node i.

Fig. 2
Fig. 2

(Color online) A block diagram of a traditional electrical switch.

Fig. 3
Fig. 3

(Color online) The shared loopback buffer.

Fig. 4
Fig. 4

(Color online) The distributed loopback buffer occupies one AWGR input, with each queue having one transmitter.

Fig. 5
Fig. 5

(Color online) The distributed loopback buffer occupies N AWGR ports, with each queue having multiple transmitters.

Fig. 6
Fig. 6

(Color online) The mixed loopback buffer occupies N / r AWGR inputs, with each queue having multiple transmitters.

Fig. 7
Fig. 7

(Color online) The end-to-end latency comparison of different loopback buffers: (a) under uniform random traffic, OQ is the ideal output queue, k = N ; (b) the hotpot port under hotspot traffic; and (c) non-hotspot ports under hotspot traffic.

Fig. 8
Fig. 8

(Color online) The injected traffic and the throughput comparisons for different loopback buffers under uniform random traffic and hotspot traffic.

Fig. 9
Fig. 9

The buffer latency distribution comparison for different loopback buffers under uniform random traffic.

Fig. 10
Fig. 10

The contention probability breakdown comparison for different loopback buffers under hotspot traffic: (a) the hotspot port; (b) non-hotspot ports.

Fig. 11
Fig. 11

(Color online) The occupancy comparison for the different loopback buffer structures: (a) under uniform random traffic; (b) under hotspot traffic.

Fig. 12
Fig. 12

(Color online) The proposed two-level flow control for the optical hybrid switch. OLG: optical label generator; PE: packet encapsulation; LE: label extractor; FDL: fiber delay line; PA: packet aggregation; O/E: optical-to-electrical converter; E/O: electrical-to-optical converter; TX: transmitter; RX: receiver; L ( i ) : label from node i.

Fig. 13
Fig. 13

(Color online) The end-to-end latency comparison: (a) under uniform random traffic, OQ is the ideal output queue, k = N ; (b) under hotspot traffic.

Fig. 14
Fig. 14

The end-to-end latency breakdown comparison of the SLB and the DLB for different OCA RX output rates under uniform random traffic. Pkt TX: packet transmission latency; Switch: the delay at the switch, including delay at the loopback buffer; OCA: the delay at the OCA TX and OCA RX, a: SLB, k 1 = 1 ; b: DLB 2TX, k 1 = 1 ; c: SLB, k 1 = k ; d: DLB 2TX, k 1 = k .

Fig. 15
Fig. 15

(Color online) The injected traffic and the throughput comparisons under uniform random traffic and hotspot traffic.

Fig. 16
Fig. 16

The contention probability breakdown for different loopback buffers under uniform random traffic.

Fig. 17
Fig. 17

The contention probability breakdown for different loopback buffers under hotspot traffic.

Fig. 18
Fig. 18

(Color online) The occupancy comparison of different loopback buffers: (a) under uniform random traffic; (b) under hotspot traffic.

Fig. 19
Fig. 19

(Color online) Flow control trigger frequencies under hotspot traffic (FC1: the OCA flow control; FC2: the loopback buffer flow control).

Tables (1)

Tables Icon

Table I Comparison of Different Loopback Buffers