Galaxy: A high-performance energy-efficient multi-chip architecture using photonic interconnects

Yigit Demir, Yan Pan, Seukwoo Song, Nikos Hardavellas, John Kim, Gokhan Memik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Citations (Scopus)

Abstract

The scalability trends of modern semiconductor technology lead to increasingly dense multicore chips. Unfortunately, physical limitations in area, power, off-chip bandwidth, and yield constrain single-chip designs to a relatively small number of cores, beyond which scaling becomes impractical. Multi-chip designs overcome these constraints, and can reach scales impossible to realize with conventional single-chip architectures. However, to deliver commensurate performance, multi-chip architectures require a cross-chip interconnect with bandwidth, latency, and energy consumption well beyond the reach of electrical signaling. We propose Galaxy, an architecture that enables the construction of a many-core "virtual chip" by connecting multiple smaller chiplets through optical fibers. The low optical loss of fibers allows the flexible placement of chiplets, and offers simpler packaging, power, and heat requirements. At the same time, the low latency and high bandwidth density of optical signaling maintain the tight coupling of cores, allowing the virtual chip to match the performance of a single chip that is not subject to area, power, and bandwidth limitations. Our results indicate that Galaxy attains speedup of 2.2x over the best single-chip alternatives with electrical or photonic interconnects (3.4x maximum), and 2.6x smaller energy-delay product (6.8x maximum). We show that Galaxy scales to 4K cores and attains 2.5x speedup at 6x lower laser power compared to a Macrochip with silicon waveguides.

Original languageEnglish (US)
Title of host publicationICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing
PublisherAssociation for Computing Machinery
Pages303-312
Number of pages10
ISBN (Print)9781450326421
DOIs
StatePublished - Jan 1 2014
Event28th ACM International Conference on Supercomputing, ICS 2014 - Munich, Germany
Duration: Jun 10 2014Jun 13 2014

Publication series

NameProceedings of the International Conference on Supercomputing

Other

Other28th ACM International Conference on Supercomputing, ICS 2014
CountryGermany
CityMunich
Period6/10/146/13/14

Fingerprint

Galaxies
Photonics
Bandwidth
Optical losses
Scalability
Optical fibers
Packaging
Waveguides
Energy utilization
Semiconductor materials
Silicon
Fibers
Lasers

Keywords

  • energy efficiency
  • interconnection networks
  • nanophotonics

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Demir, Y., Pan, Y., Song, S., Hardavellas, N., Kim, J., & Memik, G. (2014). Galaxy: A high-performance energy-efficient multi-chip architecture using photonic interconnects. In ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing (pp. 303-312). (Proceedings of the International Conference on Supercomputing). Association for Computing Machinery. https://doi.org/10.1145/2597652.2597664
Demir, Yigit ; Pan, Yan ; Song, Seukwoo ; Hardavellas, Nikos ; Kim, John ; Memik, Gokhan. / Galaxy : A high-performance energy-efficient multi-chip architecture using photonic interconnects. ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing. Association for Computing Machinery, 2014. pp. 303-312 (Proceedings of the International Conference on Supercomputing).
@inproceedings{f7a84d092ba647e2ae41419de39329aa,
title = "Galaxy: A high-performance energy-efficient multi-chip architecture using photonic interconnects",
abstract = "The scalability trends of modern semiconductor technology lead to increasingly dense multicore chips. Unfortunately, physical limitations in area, power, off-chip bandwidth, and yield constrain single-chip designs to a relatively small number of cores, beyond which scaling becomes impractical. Multi-chip designs overcome these constraints, and can reach scales impossible to realize with conventional single-chip architectures. However, to deliver commensurate performance, multi-chip architectures require a cross-chip interconnect with bandwidth, latency, and energy consumption well beyond the reach of electrical signaling. We propose Galaxy, an architecture that enables the construction of a many-core {"}virtual chip{"} by connecting multiple smaller chiplets through optical fibers. The low optical loss of fibers allows the flexible placement of chiplets, and offers simpler packaging, power, and heat requirements. At the same time, the low latency and high bandwidth density of optical signaling maintain the tight coupling of cores, allowing the virtual chip to match the performance of a single chip that is not subject to area, power, and bandwidth limitations. Our results indicate that Galaxy attains speedup of 2.2x over the best single-chip alternatives with electrical or photonic interconnects (3.4x maximum), and 2.6x smaller energy-delay product (6.8x maximum). We show that Galaxy scales to 4K cores and attains 2.5x speedup at 6x lower laser power compared to a Macrochip with silicon waveguides.",
keywords = "energy efficiency, interconnection networks, nanophotonics",
author = "Yigit Demir and Yan Pan and Seukwoo Song and Nikos Hardavellas and John Kim and Gokhan Memik",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2597652.2597664",
language = "English (US)",
isbn = "9781450326421",
series = "Proceedings of the International Conference on Supercomputing",
publisher = "Association for Computing Machinery",
pages = "303--312",
booktitle = "ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing",

}

Demir, Y, Pan, Y, Song, S, Hardavellas, N, Kim, J & Memik, G 2014, Galaxy: A high-performance energy-efficient multi-chip architecture using photonic interconnects. in ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing. Proceedings of the International Conference on Supercomputing, Association for Computing Machinery, pp. 303-312, 28th ACM International Conference on Supercomputing, ICS 2014, Munich, Germany, 6/10/14. https://doi.org/10.1145/2597652.2597664

Galaxy : A high-performance energy-efficient multi-chip architecture using photonic interconnects. / Demir, Yigit; Pan, Yan; Song, Seukwoo; Hardavellas, Nikos; Kim, John; Memik, Gokhan.

ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing. Association for Computing Machinery, 2014. p. 303-312 (Proceedings of the International Conference on Supercomputing).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Galaxy

T2 - A high-performance energy-efficient multi-chip architecture using photonic interconnects

AU - Demir, Yigit

AU - Pan, Yan

AU - Song, Seukwoo

AU - Hardavellas, Nikos

AU - Kim, John

AU - Memik, Gokhan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The scalability trends of modern semiconductor technology lead to increasingly dense multicore chips. Unfortunately, physical limitations in area, power, off-chip bandwidth, and yield constrain single-chip designs to a relatively small number of cores, beyond which scaling becomes impractical. Multi-chip designs overcome these constraints, and can reach scales impossible to realize with conventional single-chip architectures. However, to deliver commensurate performance, multi-chip architectures require a cross-chip interconnect with bandwidth, latency, and energy consumption well beyond the reach of electrical signaling. We propose Galaxy, an architecture that enables the construction of a many-core "virtual chip" by connecting multiple smaller chiplets through optical fibers. The low optical loss of fibers allows the flexible placement of chiplets, and offers simpler packaging, power, and heat requirements. At the same time, the low latency and high bandwidth density of optical signaling maintain the tight coupling of cores, allowing the virtual chip to match the performance of a single chip that is not subject to area, power, and bandwidth limitations. Our results indicate that Galaxy attains speedup of 2.2x over the best single-chip alternatives with electrical or photonic interconnects (3.4x maximum), and 2.6x smaller energy-delay product (6.8x maximum). We show that Galaxy scales to 4K cores and attains 2.5x speedup at 6x lower laser power compared to a Macrochip with silicon waveguides.

AB - The scalability trends of modern semiconductor technology lead to increasingly dense multicore chips. Unfortunately, physical limitations in area, power, off-chip bandwidth, and yield constrain single-chip designs to a relatively small number of cores, beyond which scaling becomes impractical. Multi-chip designs overcome these constraints, and can reach scales impossible to realize with conventional single-chip architectures. However, to deliver commensurate performance, multi-chip architectures require a cross-chip interconnect with bandwidth, latency, and energy consumption well beyond the reach of electrical signaling. We propose Galaxy, an architecture that enables the construction of a many-core "virtual chip" by connecting multiple smaller chiplets through optical fibers. The low optical loss of fibers allows the flexible placement of chiplets, and offers simpler packaging, power, and heat requirements. At the same time, the low latency and high bandwidth density of optical signaling maintain the tight coupling of cores, allowing the virtual chip to match the performance of a single chip that is not subject to area, power, and bandwidth limitations. Our results indicate that Galaxy attains speedup of 2.2x over the best single-chip alternatives with electrical or photonic interconnects (3.4x maximum), and 2.6x smaller energy-delay product (6.8x maximum). We show that Galaxy scales to 4K cores and attains 2.5x speedup at 6x lower laser power compared to a Macrochip with silicon waveguides.

KW - energy efficiency

KW - interconnection networks

KW - nanophotonics

UR - http://www.scopus.com/inward/record.url?scp=84903788778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903788778&partnerID=8YFLogxK

U2 - 10.1145/2597652.2597664

DO - 10.1145/2597652.2597664

M3 - Conference contribution

AN - SCOPUS:84903788778

SN - 9781450326421

T3 - Proceedings of the International Conference on Supercomputing

SP - 303

EP - 312

BT - ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing

PB - Association for Computing Machinery

ER -

Demir Y, Pan Y, Song S, Hardavellas N, Kim J, Memik G. Galaxy: A high-performance energy-efficient multi-chip architecture using photonic interconnects. In ICS 2014 - Proceedings of the 28th ACM International Conference on Supercomputing. Association for Computing Machinery. 2014. p. 303-312. (Proceedings of the International Conference on Supercomputing). https://doi.org/10.1145/2597652.2597664