An online quality management framework for approximate communication in network-on-chips

Yuechen Chen, Ahmed Louri

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

Abstract

Approximate communication is being seriously considered as an effective technique for reducing power consumption and improving the communication efficiency of network-on-chips (NoCs). A major problem faced by these techniques is quality control: how do we ensure that the network will transmit data with sufficient accuracy for applications to produce acceptable results? Previous methods that addressed this issue require each application to calculate the approximation level for every piece of approximable data, which takes hundreds of cycles. So the approximation information is often not available when a request packet is transmitted. Therefore, the reply packet with the approximable data is transmitted with unnecessarily absolute accuracy, reducing the effectiveness of approximate communication. In this paper, we propose a hardware-based quality management framework for approximate communication to minimize the time needed for the approximation level calculation. The proposed framework employs a configuration algorithm to continuously adjust the quality of every piece of data based on the difference between the output quality and the application's quality requirement. When the proposed framework is implemented in a network, every request packet can be transmitted with the updated approximation level. This framework results in fewer flits in each data packet and reduces traffic in NoCs while meeting the quality requirements of applications. Our cycle-accurate simulation using the AxBench benchmark suite shows that the proposed online quality management framework can reduce network latency by up to 52% and dynamic power consumption by 59% compared to previous approximate communication techniques while ensuring 95% output quality. This hardware-software codesign incurs 1% area overhead over previous techniques.

Original languageEnglish (US)
Title of host publicationICS 2019 - International Conference on Supercomputing
PublisherAssociation for Computing Machinery
Pages217-226
Number of pages10
ISBN (Electronic)9781450360791
DOIs
StatePublished - Jun 26 2019
Event33rd ACM International Conference on Supercomputing, ICS 2019, held in conjunction with the Federated Computing Research Conference, FCRC 2019 - Phoenix, United States
Duration: Jun 26 2019 → …

Publication series

NameProceedings of the International Conference on Supercomputing

Conference

Conference33rd ACM International Conference on Supercomputing, ICS 2019, held in conjunction with the Federated Computing Research Conference, FCRC 2019
CountryUnited States
CityPhoenix
Period6/26/19 → …

Fingerprint

Quality management
Communication
Electric power utilization
Quality control
Network-on-chip
Hardware

Keywords

  • Approximate communication
  • Network-on-chips (NoCs)
  • Quality control

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Chen, Y., & Louri, A. (2019). An online quality management framework for approximate communication in network-on-chips. In ICS 2019 - International Conference on Supercomputing (pp. 217-226). (Proceedings of the International Conference on Supercomputing). Association for Computing Machinery. https://doi.org/10.1145/3330345.3330365

An online quality management framework for approximate communication in network-on-chips. / Chen, Yuechen; Louri, Ahmed.

ICS 2019 - International Conference on Supercomputing. Association for Computing Machinery, 2019. p. 217-226 (Proceedings of the International Conference on Supercomputing).

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

Chen, Y & Louri, A 2019, An online quality management framework for approximate communication in network-on-chips. in ICS 2019 - International Conference on Supercomputing. Proceedings of the International Conference on Supercomputing, Association for Computing Machinery, pp. 217-226, 33rd ACM International Conference on Supercomputing, ICS 2019, held in conjunction with the Federated Computing Research Conference, FCRC 2019, Phoenix, United States, 6/26/19. https://doi.org/10.1145/3330345.3330365
Chen Y, Louri A. An online quality management framework for approximate communication in network-on-chips. In ICS 2019 - International Conference on Supercomputing. Association for Computing Machinery. 2019. p. 217-226. (Proceedings of the International Conference on Supercomputing). https://doi.org/10.1145/3330345.3330365
Chen, Yuechen ; Louri, Ahmed. / An online quality management framework for approximate communication in network-on-chips. ICS 2019 - International Conference on Supercomputing. Association for Computing Machinery, 2019. pp. 217-226 (Proceedings of the International Conference on Supercomputing).
@inproceedings{d5d1cfcebd25430b8d722023a3c13462,
title = "An online quality management framework for approximate communication in network-on-chips",
abstract = "Approximate communication is being seriously considered as an effective technique for reducing power consumption and improving the communication efficiency of network-on-chips (NoCs). A major problem faced by these techniques is quality control: how do we ensure that the network will transmit data with sufficient accuracy for applications to produce acceptable results? Previous methods that addressed this issue require each application to calculate the approximation level for every piece of approximable data, which takes hundreds of cycles. So the approximation information is often not available when a request packet is transmitted. Therefore, the reply packet with the approximable data is transmitted with unnecessarily absolute accuracy, reducing the effectiveness of approximate communication. In this paper, we propose a hardware-based quality management framework for approximate communication to minimize the time needed for the approximation level calculation. The proposed framework employs a configuration algorithm to continuously adjust the quality of every piece of data based on the difference between the output quality and the application's quality requirement. When the proposed framework is implemented in a network, every request packet can be transmitted with the updated approximation level. This framework results in fewer flits in each data packet and reduces traffic in NoCs while meeting the quality requirements of applications. Our cycle-accurate simulation using the AxBench benchmark suite shows that the proposed online quality management framework can reduce network latency by up to 52{\%} and dynamic power consumption by 59{\%} compared to previous approximate communication techniques while ensuring 95{\%} output quality. This hardware-software codesign incurs 1{\%} area overhead over previous techniques.",
keywords = "Approximate communication, Network-on-chips (NoCs), Quality control",
author = "Yuechen Chen and Ahmed Louri",
year = "2019",
month = "6",
day = "26",
doi = "10.1145/3330345.3330365",
language = "English (US)",
series = "Proceedings of the International Conference on Supercomputing",
publisher = "Association for Computing Machinery",
pages = "217--226",
booktitle = "ICS 2019 - International Conference on Supercomputing",

}

TY - GEN

T1 - An online quality management framework for approximate communication in network-on-chips

AU - Chen, Yuechen

AU - Louri, Ahmed

PY - 2019/6/26

Y1 - 2019/6/26

N2 - Approximate communication is being seriously considered as an effective technique for reducing power consumption and improving the communication efficiency of network-on-chips (NoCs). A major problem faced by these techniques is quality control: how do we ensure that the network will transmit data with sufficient accuracy for applications to produce acceptable results? Previous methods that addressed this issue require each application to calculate the approximation level for every piece of approximable data, which takes hundreds of cycles. So the approximation information is often not available when a request packet is transmitted. Therefore, the reply packet with the approximable data is transmitted with unnecessarily absolute accuracy, reducing the effectiveness of approximate communication. In this paper, we propose a hardware-based quality management framework for approximate communication to minimize the time needed for the approximation level calculation. The proposed framework employs a configuration algorithm to continuously adjust the quality of every piece of data based on the difference between the output quality and the application's quality requirement. When the proposed framework is implemented in a network, every request packet can be transmitted with the updated approximation level. This framework results in fewer flits in each data packet and reduces traffic in NoCs while meeting the quality requirements of applications. Our cycle-accurate simulation using the AxBench benchmark suite shows that the proposed online quality management framework can reduce network latency by up to 52% and dynamic power consumption by 59% compared to previous approximate communication techniques while ensuring 95% output quality. This hardware-software codesign incurs 1% area overhead over previous techniques.

AB - Approximate communication is being seriously considered as an effective technique for reducing power consumption and improving the communication efficiency of network-on-chips (NoCs). A major problem faced by these techniques is quality control: how do we ensure that the network will transmit data with sufficient accuracy for applications to produce acceptable results? Previous methods that addressed this issue require each application to calculate the approximation level for every piece of approximable data, which takes hundreds of cycles. So the approximation information is often not available when a request packet is transmitted. Therefore, the reply packet with the approximable data is transmitted with unnecessarily absolute accuracy, reducing the effectiveness of approximate communication. In this paper, we propose a hardware-based quality management framework for approximate communication to minimize the time needed for the approximation level calculation. The proposed framework employs a configuration algorithm to continuously adjust the quality of every piece of data based on the difference between the output quality and the application's quality requirement. When the proposed framework is implemented in a network, every request packet can be transmitted with the updated approximation level. This framework results in fewer flits in each data packet and reduces traffic in NoCs while meeting the quality requirements of applications. Our cycle-accurate simulation using the AxBench benchmark suite shows that the proposed online quality management framework can reduce network latency by up to 52% and dynamic power consumption by 59% compared to previous approximate communication techniques while ensuring 95% output quality. This hardware-software codesign incurs 1% area overhead over previous techniques.

KW - Approximate communication

KW - Network-on-chips (NoCs)

KW - Quality control

UR - http://www.scopus.com/inward/record.url?scp=85074498156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074498156&partnerID=8YFLogxK

U2 - 10.1145/3330345.3330365

DO - 10.1145/3330345.3330365

M3 - Conference contribution

AN - SCOPUS:85074498156

T3 - Proceedings of the International Conference on Supercomputing

SP - 217

EP - 226

BT - ICS 2019 - International Conference on Supercomputing

PB - Association for Computing Machinery

ER -