Throughput optimal task allocation under thermal constraints for multi-core processors

Vinay Hanumaiah, Ravishankar Rao, Sarma Vrudhula, Karam S. Chatha

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

28 Citations (Scopus)

Abstract

It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance of processors. Although DVFS and DFS can be used to extract higher performance from temperature and power constrained single core processors, the full potential of multicore performance cannot be exploited without the use of thread migration or task-to-core allocation schemes. In this paper, we formulate the problem of throughput-optimal task allocation on thermally constrained multi-core processors, and present a novel solution that includes optimal speed throttling. We show that the algorithms are implementable in real time and can be implemented in operating system's dynamic scheduling policy. The method presented here can result in a significant improvement in throughput over existing methods (5X over a naive scheme).

Original languageEnglish (US)
Title of host publicationProceedings - Design Automation Conference
Pages776-781
Number of pages6
StatePublished - 2009
Event2009 46th ACM/IEEE Design Automation Conference, DAC 2009 - San Francisco, CA, United States
Duration: Jul 26 2009Jul 31 2009

Other

Other2009 46th ACM/IEEE Design Automation Conference, DAC 2009
CountryUnited States
CitySan Francisco, CA
Period7/26/097/31/09

Fingerprint

Task Allocation
Multi-core Processor
Optimal Allocation
Throughput
Thermal gradients
Microprocessor chips
Dynamic Scheduling
Scheduling Policy
Scheduling
Microprocessor
Hot Spot
Operating Systems
System Dynamics
Thread
Temperature
Migration
High Performance
Gradient
Hot Temperature

Keywords

  • Multi-core processors
  • Optimal throughput
  • Task allocation
  • Thermal management
  • Thread migration

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Modeling and Simulation

Cite this

Hanumaiah, V., Rao, R., Vrudhula, S., & Chatha, K. S. (2009). Throughput optimal task allocation under thermal constraints for multi-core processors. In Proceedings - Design Automation Conference (pp. 776-781). [5227071]

Throughput optimal task allocation under thermal constraints for multi-core processors. / Hanumaiah, Vinay; Rao, Ravishankar; Vrudhula, Sarma; Chatha, Karam S.

Proceedings - Design Automation Conference. 2009. p. 776-781 5227071.

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

Hanumaiah, V, Rao, R, Vrudhula, S & Chatha, KS 2009, Throughput optimal task allocation under thermal constraints for multi-core processors. in Proceedings - Design Automation Conference., 5227071, pp. 776-781, 2009 46th ACM/IEEE Design Automation Conference, DAC 2009, San Francisco, CA, United States, 7/26/09.
Hanumaiah V, Rao R, Vrudhula S, Chatha KS. Throughput optimal task allocation under thermal constraints for multi-core processors. In Proceedings - Design Automation Conference. 2009. p. 776-781. 5227071
Hanumaiah, Vinay ; Rao, Ravishankar ; Vrudhula, Sarma ; Chatha, Karam S. / Throughput optimal task allocation under thermal constraints for multi-core processors. Proceedings - Design Automation Conference. 2009. pp. 776-781
@inproceedings{e664302c5a6e49808188c081088aaac5,
title = "Throughput optimal task allocation under thermal constraints for multi-core processors",
abstract = "It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance of processors. Although DVFS and DFS can be used to extract higher performance from temperature and power constrained single core processors, the full potential of multicore performance cannot be exploited without the use of thread migration or task-to-core allocation schemes. In this paper, we formulate the problem of throughput-optimal task allocation on thermally constrained multi-core processors, and present a novel solution that includes optimal speed throttling. We show that the algorithms are implementable in real time and can be implemented in operating system's dynamic scheduling policy. The method presented here can result in a significant improvement in throughput over existing methods (5X over a naive scheme).",
keywords = "Multi-core processors, Optimal throughput, Task allocation, Thermal management, Thread migration",
author = "Vinay Hanumaiah and Ravishankar Rao and Sarma Vrudhula and Chatha, {Karam S.}",
year = "2009",
language = "English (US)",
isbn = "9781605584973",
pages = "776--781",
booktitle = "Proceedings - Design Automation Conference",

}

TY - GEN

T1 - Throughput optimal task allocation under thermal constraints for multi-core processors

AU - Hanumaiah, Vinay

AU - Rao, Ravishankar

AU - Vrudhula, Sarma

AU - Chatha, Karam S.

PY - 2009

Y1 - 2009

N2 - It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance of processors. Although DVFS and DFS can be used to extract higher performance from temperature and power constrained single core processors, the full potential of multicore performance cannot be exploited without the use of thread migration or task-to-core allocation schemes. In this paper, we formulate the problem of throughput-optimal task allocation on thermally constrained multi-core processors, and present a novel solution that includes optimal speed throttling. We show that the algorithms are implementable in real time and can be implemented in operating system's dynamic scheduling policy. The method presented here can result in a significant improvement in throughput over existing methods (5X over a naive scheme).

AB - It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance of processors. Although DVFS and DFS can be used to extract higher performance from temperature and power constrained single core processors, the full potential of multicore performance cannot be exploited without the use of thread migration or task-to-core allocation schemes. In this paper, we formulate the problem of throughput-optimal task allocation on thermally constrained multi-core processors, and present a novel solution that includes optimal speed throttling. We show that the algorithms are implementable in real time and can be implemented in operating system's dynamic scheduling policy. The method presented here can result in a significant improvement in throughput over existing methods (5X over a naive scheme).

KW - Multi-core processors

KW - Optimal throughput

KW - Task allocation

KW - Thermal management

KW - Thread migration

UR - http://www.scopus.com/inward/record.url?scp=70350721931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350721931&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:70350721931

SN - 9781605584973

SP - 776

EP - 781

BT - Proceedings - Design Automation Conference

ER -