Workload capacity considering NBTI degradation in multi-core systems

Jin Sun, Roman L Lysecky, Karthik Shankar, Avinash Kodi, Ahmed Louri, Meiling Wang

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

10 Citations (Scopus)

Abstract

As device feature sizes continue to shrink, long-term reliability such as Negative Bias Temperature Instability (NBTI) leads to low yields and short mean-time-to-failure (MTTF) in multi-core systems. This paper proposes a new workload balancing scheme based on device level fractional NBTI model to balance the workload among active cores while relaxing stressed ones. The proposed method employs the Capacity Rate (CR) provided by the NBTI model, applies Dynamic Zoning (DZ) algorithm to group cores into zones to process task flows, and then uses Dynamic Task Scheduling (DTS) to allocate tasks in each zone with balanced workload and minimum communication cost. Experimental results on 64-core system show that by allowing a small part of the cores to relax over a short time period (10 seconds), the proposed methodology improves multi-core system yield (percentage of core failures) by 20%, while extending MTTF by 30% with insignificant degradation in performance (less than 3%).

Original languageEnglish (US)
Title of host publicationProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Pages450-455
Number of pages6
DOIs
StatePublished - 2010
Event2010 15th Asia and South Pacific Design Automation Conference, ASP-DAC 2010 - Taipei, Taiwan, Province of China
Duration: Jan 18 2010Jan 21 2010

Other

Other2010 15th Asia and South Pacific Design Automation Conference, ASP-DAC 2010
CountryTaiwan, Province of China
CityTaipei
Period1/18/101/21/10

Fingerprint

Degradation
Zoning
Dynamic models
Scheduling
Communication
Negative bias temperature instability
Costs

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Sun, J., Lysecky, R. L., Shankar, K., Kodi, A., Louri, A., & Wang, M. (2010). Workload capacity considering NBTI degradation in multi-core systems. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC (pp. 450-455). [5419839] https://doi.org/10.1109/ASPDAC.2010.5419839

Workload capacity considering NBTI degradation in multi-core systems. / Sun, Jin; Lysecky, Roman L; Shankar, Karthik; Kodi, Avinash; Louri, Ahmed; Wang, Meiling.

Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. 2010. p. 450-455 5419839.

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

Sun, J, Lysecky, RL, Shankar, K, Kodi, A, Louri, A & Wang, M 2010, Workload capacity considering NBTI degradation in multi-core systems. in Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC., 5419839, pp. 450-455, 2010 15th Asia and South Pacific Design Automation Conference, ASP-DAC 2010, Taipei, Taiwan, Province of China, 1/18/10. https://doi.org/10.1109/ASPDAC.2010.5419839
Sun J, Lysecky RL, Shankar K, Kodi A, Louri A, Wang M. Workload capacity considering NBTI degradation in multi-core systems. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. 2010. p. 450-455. 5419839 https://doi.org/10.1109/ASPDAC.2010.5419839
Sun, Jin ; Lysecky, Roman L ; Shankar, Karthik ; Kodi, Avinash ; Louri, Ahmed ; Wang, Meiling. / Workload capacity considering NBTI degradation in multi-core systems. Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. 2010. pp. 450-455
@inproceedings{f982ac16349a46be905335d45c426c9b,
title = "Workload capacity considering NBTI degradation in multi-core systems",
abstract = "As device feature sizes continue to shrink, long-term reliability such as Negative Bias Temperature Instability (NBTI) leads to low yields and short mean-time-to-failure (MTTF) in multi-core systems. This paper proposes a new workload balancing scheme based on device level fractional NBTI model to balance the workload among active cores while relaxing stressed ones. The proposed method employs the Capacity Rate (CR) provided by the NBTI model, applies Dynamic Zoning (DZ) algorithm to group cores into zones to process task flows, and then uses Dynamic Task Scheduling (DTS) to allocate tasks in each zone with balanced workload and minimum communication cost. Experimental results on 64-core system show that by allowing a small part of the cores to relax over a short time period (10 seconds), the proposed methodology improves multi-core system yield (percentage of core failures) by 20{\%}, while extending MTTF by 30{\%} with insignificant degradation in performance (less than 3{\%}).",
author = "Jin Sun and Lysecky, {Roman L} and Karthik Shankar and Avinash Kodi and Ahmed Louri and Meiling Wang",
year = "2010",
doi = "10.1109/ASPDAC.2010.5419839",
language = "English (US)",
isbn = "9781424457656",
pages = "450--455",
booktitle = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",

}

TY - GEN

T1 - Workload capacity considering NBTI degradation in multi-core systems

AU - Sun, Jin

AU - Lysecky, Roman L

AU - Shankar, Karthik

AU - Kodi, Avinash

AU - Louri, Ahmed

AU - Wang, Meiling

PY - 2010

Y1 - 2010

N2 - As device feature sizes continue to shrink, long-term reliability such as Negative Bias Temperature Instability (NBTI) leads to low yields and short mean-time-to-failure (MTTF) in multi-core systems. This paper proposes a new workload balancing scheme based on device level fractional NBTI model to balance the workload among active cores while relaxing stressed ones. The proposed method employs the Capacity Rate (CR) provided by the NBTI model, applies Dynamic Zoning (DZ) algorithm to group cores into zones to process task flows, and then uses Dynamic Task Scheduling (DTS) to allocate tasks in each zone with balanced workload and minimum communication cost. Experimental results on 64-core system show that by allowing a small part of the cores to relax over a short time period (10 seconds), the proposed methodology improves multi-core system yield (percentage of core failures) by 20%, while extending MTTF by 30% with insignificant degradation in performance (less than 3%).

AB - As device feature sizes continue to shrink, long-term reliability such as Negative Bias Temperature Instability (NBTI) leads to low yields and short mean-time-to-failure (MTTF) in multi-core systems. This paper proposes a new workload balancing scheme based on device level fractional NBTI model to balance the workload among active cores while relaxing stressed ones. The proposed method employs the Capacity Rate (CR) provided by the NBTI model, applies Dynamic Zoning (DZ) algorithm to group cores into zones to process task flows, and then uses Dynamic Task Scheduling (DTS) to allocate tasks in each zone with balanced workload and minimum communication cost. Experimental results on 64-core system show that by allowing a small part of the cores to relax over a short time period (10 seconds), the proposed methodology improves multi-core system yield (percentage of core failures) by 20%, while extending MTTF by 30% with insignificant degradation in performance (less than 3%).

UR - http://www.scopus.com/inward/record.url?scp=77951213063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951213063&partnerID=8YFLogxK

U2 - 10.1109/ASPDAC.2010.5419839

DO - 10.1109/ASPDAC.2010.5419839

M3 - Conference contribution

AN - SCOPUS:77951213063

SN - 9781424457656

SP - 450

EP - 455

BT - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

ER -