Time squeezing for tiny devices

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

Abstract

Dynamic timing slack has emerged as a compelling opportunity for eliminating inefficiency in ultra-low power embedded systems. This slack arises when all the signals have propagated through logic paths well in advance of the clock signal. When it is properly identified, the system can exploit this unused cycle time for energy savings. In this paper, we describe compiler and architecture co-design that opens new opportunities for timing slack that are otherwise impossible. Through cross-layer optimization, we introduce novel mechanisms in the hardware and in the compiler that work together to improve the benefit of circuit-level timing speculation by effectively squeezing time during execution. This approach is particularly well-suited to tiny embedded devices. Our evaluation on a gate-level model of a complete processor shows that our co-design saves (on average) 40.5% of the original energy consumption (additional 16.5% compared to the existing clock scheduling technique) across 13 workloads while retaining transparency to developers.

Original languageEnglish (US)
Title of host publicationISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages657-670
Number of pages14
ISBN (Electronic)9781450366694
DOIs
StatePublished - Jun 22 2019
Event46th International Symposium on Computer Architecture, ISCA 2019 - Phoenix, United States
Duration: Jun 22 2019Jun 26 2019

Publication series

NameProceedings - International Symposium on Computer Architecture
ISSN (Print)1063-6897

Conference

Conference46th International Symposium on Computer Architecture, ISCA 2019
CountryUnited States
CityPhoenix
Period6/22/196/26/19

Fingerprint

Clocks
Embedded systems
Transparency
Energy conservation
Energy utilization
Scheduling
Hardware
Networks (circuits)

Keywords

  • Code generation
  • Timing slack
  • Timing speculation

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Fan, Y., Campanoni, S., & Joseph, R. E. (2019). Time squeezing for tiny devices. In ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture (pp. 657-670). (Proceedings - International Symposium on Computer Architecture). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3307650.3322268
Fan, Yuanbo ; Campanoni, Simone ; Joseph, Russell E. / Time squeezing for tiny devices. ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 657-670 (Proceedings - International Symposium on Computer Architecture).
@inproceedings{08eb6f5dc3ef44108efeeca04c915c49,
title = "Time squeezing for tiny devices",
abstract = "Dynamic timing slack has emerged as a compelling opportunity for eliminating inefficiency in ultra-low power embedded systems. This slack arises when all the signals have propagated through logic paths well in advance of the clock signal. When it is properly identified, the system can exploit this unused cycle time for energy savings. In this paper, we describe compiler and architecture co-design that opens new opportunities for timing slack that are otherwise impossible. Through cross-layer optimization, we introduce novel mechanisms in the hardware and in the compiler that work together to improve the benefit of circuit-level timing speculation by effectively squeezing time during execution. This approach is particularly well-suited to tiny embedded devices. Our evaluation on a gate-level model of a complete processor shows that our co-design saves (on average) 40.5{\%} of the original energy consumption (additional 16.5{\%} compared to the existing clock scheduling technique) across 13 workloads while retaining transparency to developers.",
keywords = "Code generation, Timing slack, Timing speculation",
author = "Yuanbo Fan and Simone Campanoni and Joseph, {Russell E}",
year = "2019",
month = "6",
day = "22",
doi = "10.1145/3307650.3322268",
language = "English (US)",
series = "Proceedings - International Symposium on Computer Architecture",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "657--670",
booktitle = "ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture",
address = "United States",

}

Fan, Y, Campanoni, S & Joseph, RE 2019, Time squeezing for tiny devices. in ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture. Proceedings - International Symposium on Computer Architecture, Institute of Electrical and Electronics Engineers Inc., pp. 657-670, 46th International Symposium on Computer Architecture, ISCA 2019, Phoenix, United States, 6/22/19. https://doi.org/10.1145/3307650.3322268

Time squeezing for tiny devices. / Fan, Yuanbo; Campanoni, Simone; Joseph, Russell E.

ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture. Institute of Electrical and Electronics Engineers Inc., 2019. p. 657-670 (Proceedings - International Symposium on Computer Architecture).

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

TY - GEN

T1 - Time squeezing for tiny devices

AU - Fan, Yuanbo

AU - Campanoni, Simone

AU - Joseph, Russell E

PY - 2019/6/22

Y1 - 2019/6/22

N2 - Dynamic timing slack has emerged as a compelling opportunity for eliminating inefficiency in ultra-low power embedded systems. This slack arises when all the signals have propagated through logic paths well in advance of the clock signal. When it is properly identified, the system can exploit this unused cycle time for energy savings. In this paper, we describe compiler and architecture co-design that opens new opportunities for timing slack that are otherwise impossible. Through cross-layer optimization, we introduce novel mechanisms in the hardware and in the compiler that work together to improve the benefit of circuit-level timing speculation by effectively squeezing time during execution. This approach is particularly well-suited to tiny embedded devices. Our evaluation on a gate-level model of a complete processor shows that our co-design saves (on average) 40.5% of the original energy consumption (additional 16.5% compared to the existing clock scheduling technique) across 13 workloads while retaining transparency to developers.

AB - Dynamic timing slack has emerged as a compelling opportunity for eliminating inefficiency in ultra-low power embedded systems. This slack arises when all the signals have propagated through logic paths well in advance of the clock signal. When it is properly identified, the system can exploit this unused cycle time for energy savings. In this paper, we describe compiler and architecture co-design that opens new opportunities for timing slack that are otherwise impossible. Through cross-layer optimization, we introduce novel mechanisms in the hardware and in the compiler that work together to improve the benefit of circuit-level timing speculation by effectively squeezing time during execution. This approach is particularly well-suited to tiny embedded devices. Our evaluation on a gate-level model of a complete processor shows that our co-design saves (on average) 40.5% of the original energy consumption (additional 16.5% compared to the existing clock scheduling technique) across 13 workloads while retaining transparency to developers.

KW - Code generation

KW - Timing slack

KW - Timing speculation

UR - http://www.scopus.com/inward/record.url?scp=85069507236&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069507236&partnerID=8YFLogxK

U2 - 10.1145/3307650.3322268

DO - 10.1145/3307650.3322268

M3 - Conference contribution

AN - SCOPUS:85069507236

T3 - Proceedings - International Symposium on Computer Architecture

SP - 657

EP - 670

BT - ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Fan Y, Campanoni S, Joseph RE. Time squeezing for tiny devices. In ISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture. Institute of Electrical and Electronics Engineers Inc. 2019. p. 657-670. (Proceedings - International Symposium on Computer Architecture). https://doi.org/10.1145/3307650.3322268