ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures

Emmanuel Ofori-Attah; Michael Opoku Agyeman

doi:10.1145/3456146.3456169

ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures

Emmanuel Ofori-Attah, Michael Opoku Agyeman

Technology

Research output: Contribution to Book/Report › Conference Contribution › peer-review

Abstract

The percentage of inactive nodes or dark nodes (we refer to dark nodes as dumso) in many-core systems increases because of power dissipation caused by continuous scaling in technology. To address this challenge, existing work employ several techniques. Some techniques place the dumso nodes strategically between active nodes to alleviate the temperature by choosing the nodes which are far away from each other. However, this increases the latency between nodes which require inter communication leading to performance degradation. Others employ Dynamic Thermal Management (DTM) to vary the Voltage Frequency (V/F) Scaling of the nodes whilst Task migration is used to migrate tasks. In this paper, an Ageing Before Temperature Eletromigration-Aware Neighbour Allocation (ABENA) is proposed to alleviate the temperature of the nodes by using the Lifetime of nodes as the main parameter. Experiments show that our approach improves the lifetime of nodes.

Original language	English
Title of host publication	4th International Conference on Data Storage and Data Engineering
Publisher	Association for Computing Machinery (ACM)
ISBN (Print)	978-1-4503-8930-3
DOIs	https://doi.org/10.1145/3456146.3456169
Publication status	Published - 18 Feb 2021
Event	DSDE '21: 4th International Conference on Data Storage and Data Engineering - Duration: 18 Feb 2021 → 20 Feb 2021 Conference number: 4th

Publication series

Name	2021 4th International Conference on Data Storage and Data Engineering

Conference

Conference	DSDE '21
Period	18/02/21 → 20/02/21

Keywords

Many-Core
Dark-Silicon
Embedded Systems
Network-on-Chip
NoC

Access to Document

10.1145/3456146.3456169

Offori-Attah_Opoku_Agyeman_ACM_2021_ABENA_An_Ageing_Before_Temperature_Electromigration-Aware_Neighbour_Allocation_for_Many-Core_ArchitecturesAccepted author manuscript, 890 KB

Cite this

Ofori-Attah, E., & Opoku Agyeman, M. (2021). ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures. In 4th International Conference on Data Storage and Data Engineering (2021 4th International Conference on Data Storage and Data Engineering). Association for Computing Machinery (ACM). https://doi.org/10.1145/3456146.3456169

@inproceedings{3811130956af41dd8967b303aa2dc553,

title = "ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures",

abstract = "The percentage of inactive nodes or dark nodes (we refer to dark nodes as dumso) in many-core systems increases because of power dissipation caused by continuous scaling in technology. To address this challenge, existing work employ several techniques. Some techniques place the dumso nodes strategically between active nodes to alleviate the temperature by choosing the nodes which are far away from each other. However, this increases the latency between nodes which require inter communication leading to performance degradation. Others employ Dynamic Thermal Management (DTM) to vary the Voltage Frequency (V/F) Scaling of the nodes whilst Task migration is used to migrate tasks. In this paper, an Ageing Before Temperature Eletromigration-Aware Neighbour Allocation (ABENA) is proposed to alleviate the temperature of the nodes by using the Lifetime of nodes as the main parameter. Experiments show that our approach improves the lifetime of nodes.",

keywords = "Many-Core, Dark-Silicon, Embedded Systems, Network-on-Chip, NoC",

author = "Emmanuel Ofori-Attah and {Opoku Agyeman}, Michael",

year = "2021",

month = feb,

day = "18",

doi = "10.1145/3456146.3456169",

language = "English",

isbn = "978-1-4503-8930-3",

series = "2021 4th International Conference on Data Storage and Data Engineering",

publisher = "Association for Computing Machinery (ACM)",

booktitle = "4th International Conference on Data Storage and Data Engineering",

address = "United States",

note = "DSDE '21 : 4th International Conference on Data Storage and Data Engineering ; Conference date: 18-02-2021 Through 20-02-2021",

}

Ofori-Attah, E & Opoku Agyeman, M 2021, ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures. in 4th International Conference on Data Storage and Data Engineering. 2021 4th International Conference on Data Storage and Data Engineering, Association for Computing Machinery (ACM), DSDE '21, 18/02/21. https://doi.org/10.1145/3456146.3456169

ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures. / Ofori-Attah, Emmanuel; Opoku Agyeman, Michael.
4th International Conference on Data Storage and Data Engineering. Association for Computing Machinery (ACM), 2021. (2021 4th International Conference on Data Storage and Data Engineering).

Research output: Contribution to Book/Report › Conference Contribution › peer-review

TY - GEN

T1 - ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures

AU - Ofori-Attah, Emmanuel

AU - Opoku Agyeman, Michael

N1 - Conference code: 4th

PY - 2021/2/18

Y1 - 2021/2/18

N2 - The percentage of inactive nodes or dark nodes (we refer to dark nodes as dumso) in many-core systems increases because of power dissipation caused by continuous scaling in technology. To address this challenge, existing work employ several techniques. Some techniques place the dumso nodes strategically between active nodes to alleviate the temperature by choosing the nodes which are far away from each other. However, this increases the latency between nodes which require inter communication leading to performance degradation. Others employ Dynamic Thermal Management (DTM) to vary the Voltage Frequency (V/F) Scaling of the nodes whilst Task migration is used to migrate tasks. In this paper, an Ageing Before Temperature Eletromigration-Aware Neighbour Allocation (ABENA) is proposed to alleviate the temperature of the nodes by using the Lifetime of nodes as the main parameter. Experiments show that our approach improves the lifetime of nodes.

AB - The percentage of inactive nodes or dark nodes (we refer to dark nodes as dumso) in many-core systems increases because of power dissipation caused by continuous scaling in technology. To address this challenge, existing work employ several techniques. Some techniques place the dumso nodes strategically between active nodes to alleviate the temperature by choosing the nodes which are far away from each other. However, this increases the latency between nodes which require inter communication leading to performance degradation. Others employ Dynamic Thermal Management (DTM) to vary the Voltage Frequency (V/F) Scaling of the nodes whilst Task migration is used to migrate tasks. In this paper, an Ageing Before Temperature Eletromigration-Aware Neighbour Allocation (ABENA) is proposed to alleviate the temperature of the nodes by using the Lifetime of nodes as the main parameter. Experiments show that our approach improves the lifetime of nodes.

KW - Many-Core

KW - Dark-Silicon

KW - Embedded Systems

KW - Network-on-Chip

KW - NoC

U2 - 10.1145/3456146.3456169

DO - 10.1145/3456146.3456169

M3 - Conference Contribution

SN - 978-1-4503-8930-3

T3 - 2021 4th International Conference on Data Storage and Data Engineering

BT - 4th International Conference on Data Storage and Data Engineering

PB - Association for Computing Machinery (ACM)

T2 - DSDE '21

Y2 - 18 February 2021 through 20 February 2021

ER -

ABENA: An Ageing before Temperature Electromigration-Aware Neighbour Allocation for Many-Core Architectures

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this