Design of a bufferless photonic CIos network-on-chip architecture

Yu Hsiang Kao, H. Jonathan Chao

Research output: Contribution to journalArticle

Abstract

On-chip photonic waveguides have been proposed as a feasible replacement for the long interconnects that cause speed and power bottlenecks. Along with recent advancements in nanophotonic technologies, we believe that combining on-chip waveguides with high-radix Network on Chip (NoC) topologies is a promising way to improve NoC performance. In this paper, we propose the BufferLess phOtonic ClOs Network (BLOCON) to exploit silicon photonics. We propose a scheduling algorithm named Sustained and Informed Dual Round-Robin Matching (SIDRRM) to solve the output contention problem, a path allocation scheme named Distributed and Informed Path Allocation (DIPA) to solve the Clos network routing problem, and a methodology to achieve an optimal off-chip laser-power budget. In the simulation results, we show that with SIDRRM and DIPA, BLOCON improves the delay and on-chip power performance of the compared electrical and photonic NoC architectures over synthetic traffic patterns and SPLASH-2 traces.

Original languageEnglish (US)
Article number6331481
Pages (from-to)764-776
Number of pages13
JournalIEEE Transactions on Computers
Volume63
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Photonics
Chip
Path
Waveguide
Silicon Photonics
Nanophotonics
Waveguides
Routing Problem
Interconnect
Contention
Scheduling Algorithm
Network routing
Replacement
Scheduling algorithms
Trace
Traffic
Laser
Topology
Design
Network on chip

Keywords

  • bufferless NoC
  • Clos network
  • Network-on-chip
  • silicon photonics

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Design of a bufferless photonic CIos network-on-chip architecture. / Kao, Yu Hsiang; Chao, H. Jonathan.

In: IEEE Transactions on Computers, Vol. 63, No. 3, 6331481, 2014, p. 764-776.

Research output: Contribution to journalArticle

@article{d560adbb7489491ea9a3899406f2c053,
title = "Design of a bufferless photonic CIos network-on-chip architecture",
abstract = "On-chip photonic waveguides have been proposed as a feasible replacement for the long interconnects that cause speed and power bottlenecks. Along with recent advancements in nanophotonic technologies, we believe that combining on-chip waveguides with high-radix Network on Chip (NoC) topologies is a promising way to improve NoC performance. In this paper, we propose the BufferLess phOtonic ClOs Network (BLOCON) to exploit silicon photonics. We propose a scheduling algorithm named Sustained and Informed Dual Round-Robin Matching (SIDRRM) to solve the output contention problem, a path allocation scheme named Distributed and Informed Path Allocation (DIPA) to solve the Clos network routing problem, and a methodology to achieve an optimal off-chip laser-power budget. In the simulation results, we show that with SIDRRM and DIPA, BLOCON improves the delay and on-chip power performance of the compared electrical and photonic NoC architectures over synthetic traffic patterns and SPLASH-2 traces.",
keywords = "bufferless NoC, Clos network, Network-on-chip, silicon photonics",
author = "Kao, {Yu Hsiang} and Chao, {H. Jonathan}",
year = "2014",
doi = "10.1109/TC.2012.250",
language = "English (US)",
volume = "63",
pages = "764--776",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Design of a bufferless photonic CIos network-on-chip architecture

AU - Kao, Yu Hsiang

AU - Chao, H. Jonathan

PY - 2014

Y1 - 2014

N2 - On-chip photonic waveguides have been proposed as a feasible replacement for the long interconnects that cause speed and power bottlenecks. Along with recent advancements in nanophotonic technologies, we believe that combining on-chip waveguides with high-radix Network on Chip (NoC) topologies is a promising way to improve NoC performance. In this paper, we propose the BufferLess phOtonic ClOs Network (BLOCON) to exploit silicon photonics. We propose a scheduling algorithm named Sustained and Informed Dual Round-Robin Matching (SIDRRM) to solve the output contention problem, a path allocation scheme named Distributed and Informed Path Allocation (DIPA) to solve the Clos network routing problem, and a methodology to achieve an optimal off-chip laser-power budget. In the simulation results, we show that with SIDRRM and DIPA, BLOCON improves the delay and on-chip power performance of the compared electrical and photonic NoC architectures over synthetic traffic patterns and SPLASH-2 traces.

AB - On-chip photonic waveguides have been proposed as a feasible replacement for the long interconnects that cause speed and power bottlenecks. Along with recent advancements in nanophotonic technologies, we believe that combining on-chip waveguides with high-radix Network on Chip (NoC) topologies is a promising way to improve NoC performance. In this paper, we propose the BufferLess phOtonic ClOs Network (BLOCON) to exploit silicon photonics. We propose a scheduling algorithm named Sustained and Informed Dual Round-Robin Matching (SIDRRM) to solve the output contention problem, a path allocation scheme named Distributed and Informed Path Allocation (DIPA) to solve the Clos network routing problem, and a methodology to achieve an optimal off-chip laser-power budget. In the simulation results, we show that with SIDRRM and DIPA, BLOCON improves the delay and on-chip power performance of the compared electrical and photonic NoC architectures over synthetic traffic patterns and SPLASH-2 traces.

KW - bufferless NoC

KW - Clos network

KW - Network-on-chip

KW - silicon photonics

UR - http://www.scopus.com/inward/record.url?scp=84897487941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897487941&partnerID=8YFLogxK

U2 - 10.1109/TC.2012.250

DO - 10.1109/TC.2012.250

M3 - Article

AN - SCOPUS:84897487941

VL - 63

SP - 764

EP - 776

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 3

M1 - 6331481

ER -