Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications

Marcelo Brandalero; Antonio Carlos S. Beck; Luigi Carro; Muhammad Shafique

doi:10.1145/3195970.3195993

Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications

Marcelo Brandalero, Antonio Carlos S. Beck, Luigi Carro, Muhammad Shafique

Electrical Engineering

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

Abstract

Approximate functional unit designs have the potential to reduce power consumption significantly compared to their precise counterparts; however, few works have investigated composing them to build generic accelerators. In this work, we do a design-space exploration of state-of-the-art approximate designs, propose a flow for designing approximate coarse-grained reconfigurable arrays (CGRAs), and discuss compilation and runtime reconfiguration issues. We compare the energy savings of precise and approximate reconfigurable acceleration and show that the latter can provide up to 50% additional power savings under a 10% quality loss constraint for the applications in the AxBench suite.

Original language	English (US)
Title of host publication	Proceedings of the 55th Annual Design Automation Conference, DAC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781450357005
DOIs	https://doi.org/10.1145/3195970.3195993
State	Published - Jun 24 2018
Event	55th Annual Design Automation Conference, DAC 2018 - San Francisco, United States Duration: Jun 24 2018 → Jun 29 2018

Publication series

Name	Proceedings - Design Automation Conference
Volume	Part F137710
ISSN (Print)	0738-100X

Other

Other	55th Annual Design Automation Conference, DAC 2018
Country/Territory	United States
City	San Francisco
Period	6/24/18 → 6/29/18

Keywords

Approximate computing
Coarse-grained reconfigurable architecture
Dark silicon

ASJC Scopus subject areas

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

Access to Document

10.1145/3195970.3195993

Cite this

Brandalero, M., Beck, A. C. S., Carro, L., & Shafique, M. (2018). Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications. In Proceedings of the 55th Annual Design Automation Conference, DAC 2018 Article a160 (Proceedings - Design Automation Conference; Vol. Part F137710). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3195970.3195993

Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications. / Brandalero, Marcelo; Beck, Antonio Carlos S.; Carro, Luigi et al.
Proceedings of the 55th Annual Design Automation Conference, DAC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. a160 (Proceedings - Design Automation Conference; Vol. Part F137710).

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

Brandalero, M, Beck, ACS, Carro, L & Shafique, M 2018, Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications. in Proceedings of the 55th Annual Design Automation Conference, DAC 2018., a160, Proceedings - Design Automation Conference, vol. Part F137710, Institute of Electrical and Electronics Engineers Inc., 55th Annual Design Automation Conference, DAC 2018, San Francisco, United States, 6/24/18. https://doi.org/10.1145/3195970.3195993

@inproceedings{88886938d66646d0943b7a7d39cd4e09,

title = "Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications",

abstract = "Approximate functional unit designs have the potential to reduce power consumption significantly compared to their precise counterparts; however, few works have investigated composing them to build generic accelerators. In this work, we do a design-space exploration of state-of-the-art approximate designs, propose a flow for designing approximate coarse-grained reconfigurable arrays (CGRAs), and discuss compilation and runtime reconfiguration issues. We compare the energy savings of precise and approximate reconfigurable acceleration and show that the latter can provide up to 50% additional power savings under a 10% quality loss constraint for the applications in the AxBench suite.",

keywords = "Approximate computing, Coarse-grained reconfigurable architecture, Dark silicon",

author = "Marcelo Brandalero and Beck, {Antonio Carlos S.} and Luigi Carro and Muhammad Shafique",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 55th Annual Design Automation Conference, DAC 2018 ; Conference date: 24-06-2018 Through 29-06-2018",

year = "2018",

month = jun,

day = "24",

doi = "10.1145/3195970.3195993",

language = "English (US)",

isbn = "9781450357005",

series = "Proceedings - Design Automation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 55th Annual Design Automation Conference, DAC 2018",

}

TY - GEN

T1 - Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications

AU - Brandalero, Marcelo

AU - Beck, Antonio Carlos S.

AU - Carro, Luigi

AU - Shafique, Muhammad

PY - 2018/6/24

Y1 - 2018/6/24

N2 - Approximate functional unit designs have the potential to reduce power consumption significantly compared to their precise counterparts; however, few works have investigated composing them to build generic accelerators. In this work, we do a design-space exploration of state-of-the-art approximate designs, propose a flow for designing approximate coarse-grained reconfigurable arrays (CGRAs), and discuss compilation and runtime reconfiguration issues. We compare the energy savings of precise and approximate reconfigurable acceleration and show that the latter can provide up to 50% additional power savings under a 10% quality loss constraint for the applications in the AxBench suite.

AB - Approximate functional unit designs have the potential to reduce power consumption significantly compared to their precise counterparts; however, few works have investigated composing them to build generic accelerators. In this work, we do a design-space exploration of state-of-the-art approximate designs, propose a flow for designing approximate coarse-grained reconfigurable arrays (CGRAs), and discuss compilation and runtime reconfiguration issues. We compare the energy savings of precise and approximate reconfigurable acceleration and show that the latter can provide up to 50% additional power savings under a 10% quality loss constraint for the applications in the AxBench suite.

KW - Approximate computing

KW - Coarse-grained reconfigurable architecture

KW - Dark silicon

UR - http://www.scopus.com/inward/record.url?scp=85053689666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053689666&partnerID=8YFLogxK

U2 - 10.1145/3195970.3195993

DO - 10.1145/3195970.3195993

M3 - Conference contribution

AN - SCOPUS:85053689666

SN - 9781450357005

T3 - Proceedings - Design Automation Conference

BT - Proceedings of the 55th Annual Design Automation Conference, DAC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 55th Annual Design Automation Conference, DAC 2018

Y2 - 24 June 2018 through 29 June 2018

ER -

Approximate on-the-fly coarse-grained reconfigurable acceleration for general-purpose applications

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this