Intelligent hotspot prediction for network-on-chip-based multicore systems

Elena Kakoulli, Vassos Soteriou Soteriou, Theocharis Theocharides

Research output: Contribution to journalArticle

Abstract

Hotspots are network-on-chip (NoC) routers or modules in multicore systems which occasionally receive packetized data from other networked element producers at a rate higher than they can consume it. This adverse phenomenon may greatly reduce the performance of NoCs, especially when wormhole flow-control is employed, as backpressure can cause the buffers of neighboring routers to quickly fill-up leading to a spatial spread in congestion. This can cause the network to saturate prematurely where in the worst scenario the NoC may be rendered unrecoverable. Thus, a hotspot prevention mechanism can be greatly beneficial, as it can potentially enable the interconnection system to adjust its behavior and prevent the rise of potential hotspots, subsequently sustaining NoC performance. The inherent unevenness of traffic patterns in an NoC-based general-purpose multicore system such as a chip multiprocessor, due to the diverse and unpredictable access patterns of applications, produces unexpected hotspots whose appearance cannot be known a priori, as application demands are not predetermined, making hotspot prediction and subsequently prevention difficult. In this paper, we present an artificial neural network-based (ANN) hotspot prediction mechanism that can be potentially used in tandem with a hotspot avoidance or congestion-control mechanism to handle unforeseen hotspot formations efficiently. The ANN uses online statistical data to dynamically monitor the interconnect fabric, and reactively predicts the location of an about to-be-formed hotspot(s), allowing enough time for the multicore system to react to these potential hotspots. Evaluation results indicate that a relatively lightweight ANN-based predictor can forecast hotspot formation(s) with an accuracy ranging from 65% to 92%.

Original languageEnglish (US)
Article number6152782
Pages (from-to)418-431
Number of pages14
JournalIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Volume31
Issue number3
DOIs
StatePublished - Mar 1 2012

Fingerprint

Neural networks
Routers
Flow control
Network-on-chip

Keywords

  • Multiprocessor interconnection
  • neural network hardware
  • on-chip network
  • ultralarge-scale integration

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Cite this

Intelligent hotspot prediction for network-on-chip-based multicore systems. / Kakoulli, Elena; Soteriou, Vassos Soteriou; Theocharides, Theocharis.

In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 31, No. 3, 6152782, 01.03.2012, p. 418-431.

Research output: Contribution to journalArticle

@article{f871fb6b8c1446ac93a8e401532cf9f7,
title = "Intelligent hotspot prediction for network-on-chip-based multicore systems",
abstract = "Hotspots are network-on-chip (NoC) routers or modules in multicore systems which occasionally receive packetized data from other networked element producers at a rate higher than they can consume it. This adverse phenomenon may greatly reduce the performance of NoCs, especially when wormhole flow-control is employed, as backpressure can cause the buffers of neighboring routers to quickly fill-up leading to a spatial spread in congestion. This can cause the network to saturate prematurely where in the worst scenario the NoC may be rendered unrecoverable. Thus, a hotspot prevention mechanism can be greatly beneficial, as it can potentially enable the interconnection system to adjust its behavior and prevent the rise of potential hotspots, subsequently sustaining NoC performance. The inherent unevenness of traffic patterns in an NoC-based general-purpose multicore system such as a chip multiprocessor, due to the diverse and unpredictable access patterns of applications, produces unexpected hotspots whose appearance cannot be known a priori, as application demands are not predetermined, making hotspot prediction and subsequently prevention difficult. In this paper, we present an artificial neural network-based (ANN) hotspot prediction mechanism that can be potentially used in tandem with a hotspot avoidance or congestion-control mechanism to handle unforeseen hotspot formations efficiently. The ANN uses online statistical data to dynamically monitor the interconnect fabric, and reactively predicts the location of an about to-be-formed hotspot(s), allowing enough time for the multicore system to react to these potential hotspots. Evaluation results indicate that a relatively lightweight ANN-based predictor can forecast hotspot formation(s) with an accuracy ranging from 65{\%} to 92{\%}.",
keywords = "Multiprocessor interconnection, neural network hardware, on-chip network, ultralarge-scale integration",
author = "Elena Kakoulli and Soteriou, {Vassos Soteriou} and Theocharis Theocharides",
year = "2012",
month = "3",
day = "1",
doi = "10.1109/TCAD.2011.2170568",
language = "English (US)",
volume = "31",
pages = "418--431",
journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",
issn = "0278-0070",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Intelligent hotspot prediction for network-on-chip-based multicore systems

AU - Kakoulli, Elena

AU - Soteriou, Vassos Soteriou

AU - Theocharides, Theocharis

PY - 2012/3/1

Y1 - 2012/3/1

N2 - Hotspots are network-on-chip (NoC) routers or modules in multicore systems which occasionally receive packetized data from other networked element producers at a rate higher than they can consume it. This adverse phenomenon may greatly reduce the performance of NoCs, especially when wormhole flow-control is employed, as backpressure can cause the buffers of neighboring routers to quickly fill-up leading to a spatial spread in congestion. This can cause the network to saturate prematurely where in the worst scenario the NoC may be rendered unrecoverable. Thus, a hotspot prevention mechanism can be greatly beneficial, as it can potentially enable the interconnection system to adjust its behavior and prevent the rise of potential hotspots, subsequently sustaining NoC performance. The inherent unevenness of traffic patterns in an NoC-based general-purpose multicore system such as a chip multiprocessor, due to the diverse and unpredictable access patterns of applications, produces unexpected hotspots whose appearance cannot be known a priori, as application demands are not predetermined, making hotspot prediction and subsequently prevention difficult. In this paper, we present an artificial neural network-based (ANN) hotspot prediction mechanism that can be potentially used in tandem with a hotspot avoidance or congestion-control mechanism to handle unforeseen hotspot formations efficiently. The ANN uses online statistical data to dynamically monitor the interconnect fabric, and reactively predicts the location of an about to-be-formed hotspot(s), allowing enough time for the multicore system to react to these potential hotspots. Evaluation results indicate that a relatively lightweight ANN-based predictor can forecast hotspot formation(s) with an accuracy ranging from 65% to 92%.

AB - Hotspots are network-on-chip (NoC) routers or modules in multicore systems which occasionally receive packetized data from other networked element producers at a rate higher than they can consume it. This adverse phenomenon may greatly reduce the performance of NoCs, especially when wormhole flow-control is employed, as backpressure can cause the buffers of neighboring routers to quickly fill-up leading to a spatial spread in congestion. This can cause the network to saturate prematurely where in the worst scenario the NoC may be rendered unrecoverable. Thus, a hotspot prevention mechanism can be greatly beneficial, as it can potentially enable the interconnection system to adjust its behavior and prevent the rise of potential hotspots, subsequently sustaining NoC performance. The inherent unevenness of traffic patterns in an NoC-based general-purpose multicore system such as a chip multiprocessor, due to the diverse and unpredictable access patterns of applications, produces unexpected hotspots whose appearance cannot be known a priori, as application demands are not predetermined, making hotspot prediction and subsequently prevention difficult. In this paper, we present an artificial neural network-based (ANN) hotspot prediction mechanism that can be potentially used in tandem with a hotspot avoidance or congestion-control mechanism to handle unforeseen hotspot formations efficiently. The ANN uses online statistical data to dynamically monitor the interconnect fabric, and reactively predicts the location of an about to-be-formed hotspot(s), allowing enough time for the multicore system to react to these potential hotspots. Evaluation results indicate that a relatively lightweight ANN-based predictor can forecast hotspot formation(s) with an accuracy ranging from 65% to 92%.

KW - Multiprocessor interconnection

KW - neural network hardware

KW - on-chip network

KW - ultralarge-scale integration

UR - http://www.scopus.com/inward/record.url?scp=84857311525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857311525&partnerID=8YFLogxK

U2 - 10.1109/TCAD.2011.2170568

DO - 10.1109/TCAD.2011.2170568

M3 - Article

VL - 31

SP - 418

EP - 431

JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

SN - 0278-0070

IS - 3

M1 - 6152782

ER -