Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC

Changjiang Gou; Anne Benoit; Mingsong Chen; Loris Marchal; Tongquan Wei

doi:10.1109/PADSW.2018.8644620

Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC

Changjiang Gou^*
, Anne Benoit
, Mingsong Chen
, Loris Marchal
, Tongquan Wei

^*Corresponding author for this work

Software Engineering Institute

École normale supérieure de Lyon
East China Normal University
Georgia Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

Multi-Processor System-on-Chip (MPSoC) has emerged as a promising platform to meet the increasing performance demand of embedded applications. However, due to limited energy budget, it is hard to guarantee that applications on MPSoC can be accomplished on time with a required throughput. The situation becomes even worse for applications with high reliability requirements, since extra energy will be inevitably consumed by task re-executions or duplicated tasks. Based on Dynamic Voltage and Frequency Scaling (DVFS) and task duplication techniques, this paper presents a novel energy-efficient scheduling model, which aims at minimizing the overall energy consumption of MPSoC applications under both throughput and reliability constraints. The problem is shown to be NP-complete, and several polynomial-time heuristics are proposed to tackle this problem. Comprehensive simulations on both synthetic and real application graphs show that our proposed heuristics can meet all the given constraints, while reducing the energy consumption.

Original language	English
Title of host publication	Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018
Publisher	IEEE Computer Society
Pages	577-586
Number of pages	10
ISBN (Electronic)	9781538673089
DOIs	https://doi.org/10.1109/PADSW.2018.8644620
State	Published - 2 Jul 2018
Event	24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018 - Singapore, Singapore Duration: 11 Dec 2018 → 13 Dec 2018

Publication series

Name	Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
Volume	2018-December
ISSN (Print)	1521-9097

Conference

Conference	24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018
Country/Territory	Singapore
City	Singapore
Period	11/12/18 → 13/12/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

MPSoC
Scheduling
energy minimization
reliability
throughput

Access to Document

10.1109/PADSW.2018.8644620

Cite this

Gou, C., Benoit, A., Chen, M., Marchal, L., & Wei, T. (2018). Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC. In Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018 (pp. 577-586). Article 8644620 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2018-December). IEEE Computer Society. https://doi.org/10.1109/PADSW.2018.8644620

Gou, Changjiang ; Benoit, Anne ; Chen, Mingsong et al. / Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC. Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018. IEEE Computer Society, 2018. pp. 577-586 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS).

@inproceedings{75bc2feefbeb405eb9887eb9c3acf631,

title = "Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC",

abstract = "Multi-Processor System-on-Chip (MPSoC) has emerged as a promising platform to meet the increasing performance demand of embedded applications. However, due to limited energy budget, it is hard to guarantee that applications on MPSoC can be accomplished on time with a required throughput. The situation becomes even worse for applications with high reliability requirements, since extra energy will be inevitably consumed by task re-executions or duplicated tasks. Based on Dynamic Voltage and Frequency Scaling (DVFS) and task duplication techniques, this paper presents a novel energy-efficient scheduling model, which aims at minimizing the overall energy consumption of MPSoC applications under both throughput and reliability constraints. The problem is shown to be NP-complete, and several polynomial-time heuristics are proposed to tackle this problem. Comprehensive simulations on both synthetic and real application graphs show that our proposed heuristics can meet all the given constraints, while reducing the energy consumption.",

keywords = "MPSoC, Scheduling, energy minimization, reliability, throughput",

author = "Changjiang Gou and Anne Benoit and Mingsong Chen and Loris Marchal and Tongquan Wei",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018 ; Conference date: 11-12-2018 Through 13-12-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/PADSW.2018.8644620",

language = "英语",

series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",

publisher = "IEEE Computer Society",

pages = "577--586",

booktitle = "Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018",

address = "美国",

}

Gou, C, Benoit, A, Chen, M, Marchal, L & Wei, T 2018, Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC. in Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018., 8644620, Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS, vol. 2018-December, IEEE Computer Society, pp. 577-586, 24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018, Singapore, Singapore, 11/12/18. https://doi.org/10.1109/PADSW.2018.8644620

Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC. / Gou, Changjiang; Benoit, Anne; Chen, Mingsong et al.
Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018. IEEE Computer Society, 2018. p. 577-586 8644620 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC

AU - Gou, Changjiang

AU - Benoit, Anne

AU - Chen, Mingsong

AU - Marchal, Loris

AU - Wei, Tongquan

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Multi-Processor System-on-Chip (MPSoC) has emerged as a promising platform to meet the increasing performance demand of embedded applications. However, due to limited energy budget, it is hard to guarantee that applications on MPSoC can be accomplished on time with a required throughput. The situation becomes even worse for applications with high reliability requirements, since extra energy will be inevitably consumed by task re-executions or duplicated tasks. Based on Dynamic Voltage and Frequency Scaling (DVFS) and task duplication techniques, this paper presents a novel energy-efficient scheduling model, which aims at minimizing the overall energy consumption of MPSoC applications under both throughput and reliability constraints. The problem is shown to be NP-complete, and several polynomial-time heuristics are proposed to tackle this problem. Comprehensive simulations on both synthetic and real application graphs show that our proposed heuristics can meet all the given constraints, while reducing the energy consumption.

AB - Multi-Processor System-on-Chip (MPSoC) has emerged as a promising platform to meet the increasing performance demand of embedded applications. However, due to limited energy budget, it is hard to guarantee that applications on MPSoC can be accomplished on time with a required throughput. The situation becomes even worse for applications with high reliability requirements, since extra energy will be inevitably consumed by task re-executions or duplicated tasks. Based on Dynamic Voltage and Frequency Scaling (DVFS) and task duplication techniques, this paper presents a novel energy-efficient scheduling model, which aims at minimizing the overall energy consumption of MPSoC applications under both throughput and reliability constraints. The problem is shown to be NP-complete, and several polynomial-time heuristics are proposed to tackle this problem. Comprehensive simulations on both synthetic and real application graphs show that our proposed heuristics can meet all the given constraints, while reducing the energy consumption.

KW - MPSoC

KW - Scheduling

KW - energy minimization

KW - reliability

KW - throughput

UR - https://www.scopus.com/pages/publications/85063336150

U2 - 10.1109/PADSW.2018.8644620

DO - 10.1109/PADSW.2018.8644620

M3 - 会议稿件

AN - SCOPUS:85063336150

T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

SP - 577

EP - 586

BT - Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018

PB - IEEE Computer Society

T2 - 24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018

Y2 - 11 December 2018 through 13 December 2018

ER -

Gou C, Benoit A, Chen M, Marchal L, Wei T. Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC. In Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018. IEEE Computer Society. 2018. p. 577-586. 8644620. (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS). doi: 10.1109/PADSW.2018.8644620

Reliability-Aware Energy Optimization for Throughput-Constrained Applications on MPSoC

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this