Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects

Randy Morris; Avinash Kodi; Ahmed Louri

doi:10.1109/SLIP.2013.6681676

Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects

Randy Morris, Avinash Kodi, Ahmed Louri

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

As we integrate hundreds of cores in the future, energy-efficiency and scalability of Network-on-Chips (NoCs) has become a critical challenge. In order to achieve higher performance-per-Watt than traditional metallic interconnects, researchers are exploring alternate energy-effident emerging technology solutions. In this paper, we propose to combine two emerging technologies, namely 3D stacking and nanophotonics that can deliver high on-chip bandwidth and low energy/bit to achieve a high-throughput, reconfigurable and scalable NoC for many-core systems. Our simulation results indicate that the execution time can be reduced up to 25% and energy consumption reduced by 23% for Splash-2, PARSEC, SPEC CPU2006 and synthetic benchmarks for 64-core and 256-core versions.

Original language	English (US)
Title of host publication	2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013
Publisher	Association for Computing Machinery
ISBN (Print)	9781467361736
DOIs	https://doi.org/10.1109/SLIP.2013.6681676
State	Published - 2013
Event	2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013 - Austin, TX, United States Duration: Jun 2 2013 → Jun 2 2013

Publication series

Name	International Workshop on System Level Interconnect Prediction, SLIP

Other

Other	2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013
Country/Territory	United States
City	Austin, TX
Period	6/2/13 → 6/2/13

Keywords

Nanophotonics
NoCs
Reconfiguration

ASJC Scopus subject areas

Hardware and Architecture
Electrical and Electronic Engineering
Computer Science Applications
Applied Mathematics

Access to Document

10.1109/SLIP.2013.6681676

Cite this

Morris, R., Kodi, A., & Louri, A. (2013). Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects. In 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013 Article 6681676 (International Workshop on System Level Interconnect Prediction, SLIP). Association for Computing Machinery. https://doi.org/10.1109/SLIP.2013.6681676

Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects. / Morris, Randy; Kodi, Avinash; Louri, Ahmed.
2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013. Association for Computing Machinery, 2013. 6681676 (International Workshop on System Level Interconnect Prediction, SLIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Morris, R, Kodi, A & Louri, A 2013, Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects. in 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013., 6681676, International Workshop on System Level Interconnect Prediction, SLIP, Association for Computing Machinery, 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013, Austin, TX, United States, 6/2/13. https://doi.org/10.1109/SLIP.2013.6681676

Morris R, Kodi A, Louri A. Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects. In 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013. Association for Computing Machinery. 2013. 6681676. (International Workshop on System Level Interconnect Prediction, SLIP). doi: 10.1109/SLIP.2013.6681676

@inproceedings{769e1f6776734e3f9ed534599a56cab6,

title = "Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects",

abstract = "As we integrate hundreds of cores in the future, energy-efficiency and scalability of Network-on-Chips (NoCs) has become a critical challenge. In order to achieve higher performance-per-Watt than traditional metallic interconnects, researchers are exploring alternate energy-effident emerging technology solutions. In this paper, we propose to combine two emerging technologies, namely 3D stacking and nanophotonics that can deliver high on-chip bandwidth and low energy/bit to achieve a high-throughput, reconfigurable and scalable NoC for many-core systems. Our simulation results indicate that the execution time can be reduced up to 25% and energy consumption reduced by 23% for Splash-2, PARSEC, SPEC CPU2006 and synthetic benchmarks for 64-core and 256-core versions.",

keywords = "Nanophotonics, NoCs, Reconfiguration",

author = "Randy Morris and Avinash Kodi and Ahmed Louri",

year = "2013",

doi = "10.1109/SLIP.2013.6681676",

language = "English (US)",

isbn = "9781467361736",

series = "International Workshop on System Level Interconnect Prediction, SLIP",

publisher = "Association for Computing Machinery",

booktitle = "2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013",

note = "2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013 ; Conference date: 02-06-2013 Through 02-06-2013",

}

TY - GEN

T1 - Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects

AU - Morris, Randy

AU - Kodi, Avinash

AU - Louri, Ahmed

PY - 2013

Y1 - 2013

N2 - As we integrate hundreds of cores in the future, energy-efficiency and scalability of Network-on-Chips (NoCs) has become a critical challenge. In order to achieve higher performance-per-Watt than traditional metallic interconnects, researchers are exploring alternate energy-effident emerging technology solutions. In this paper, we propose to combine two emerging technologies, namely 3D stacking and nanophotonics that can deliver high on-chip bandwidth and low energy/bit to achieve a high-throughput, reconfigurable and scalable NoC for many-core systems. Our simulation results indicate that the execution time can be reduced up to 25% and energy consumption reduced by 23% for Splash-2, PARSEC, SPEC CPU2006 and synthetic benchmarks for 64-core and 256-core versions.

AB - As we integrate hundreds of cores in the future, energy-efficiency and scalability of Network-on-Chips (NoCs) has become a critical challenge. In order to achieve higher performance-per-Watt than traditional metallic interconnects, researchers are exploring alternate energy-effident emerging technology solutions. In this paper, we propose to combine two emerging technologies, namely 3D stacking and nanophotonics that can deliver high on-chip bandwidth and low energy/bit to achieve a high-throughput, reconfigurable and scalable NoC for many-core systems. Our simulation results indicate that the execution time can be reduced up to 25% and energy consumption reduced by 23% for Splash-2, PARSEC, SPEC CPU2006 and synthetic benchmarks for 64-core and 256-core versions.

KW - Nanophotonics

KW - NoCs

KW - Reconfiguration

UR - http://www.scopus.com/inward/record.url?scp=84893427301&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893427301&partnerID=8YFLogxK

U2 - 10.1109/SLIP.2013.6681676

DO - 10.1109/SLIP.2013.6681676

M3 - Conference contribution

AN - SCOPUS:84893427301

SN - 9781467361736

T3 - International Workshop on System Level Interconnect Prediction, SLIP

BT - 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013

PB - Association for Computing Machinery

T2 - 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction, SLIP 2013

Y2 - 2 June 2013 through 2 June 2013

ER -

Evaluating the scalability and performance of 3D stacked reconfigurable nanophotonic interconnects

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this