A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress

Ye Wang; Jian Dong; Yanxin Liu; Chunpei Wang; Gang Qu

doi:10.1109/EMSOFT51651.2020.9244043

A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress

Ye Wang
, Jian Dong
, Yanxin Liu
, Chunpei Wang
, Gang Qu

School of Computer Science and Technology, Harbin Institute of Technology
University of Maryland, College Park

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

3 Scopus citations

Abstract

We report our ongoing work towards a machine learning based runtime approximate computing (AC) approach that can be applied on the data flow graph representation of any software program. This approach can utilize runtime inputs together with prior information of the software to identify and approximate the noncritical portion of a computation with low runtime overhead. Some preliminary experimental results show that compared with previous runtime AC approaches, our approach can significantly reduce the time overhead with little loss on the energy efficiency and computation accuracy.

Original language	English
Title of host publication	Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020
Editors	Tulika Mitra, Andreas Gerstlauer
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	37-39
Number of pages	3
ISBN (Electronic)	9781728191959
DOIs	https://doi.org/10.1109/EMSOFT51651.2020.9244043
State	Published - 20 Sep 2020
Externally published	Yes
Event	14th Turkish National Software Engineering Symposium, UYMS 2020 - Istanbul, Turkey Duration: 7 Oct 2020 → 9 Oct 2020

Publication series

Name	Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020

Conference

Conference	14th Turkish National Software Engineering Symposium, UYMS 2020
Country/Territory	Turkey
City	Istanbul
Period	7/10/20 → 9/10/20

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

approximate computing
data flow graph
energy efficiency
machine learning
runtime

Access to Document

10.1109/EMSOFT51651.2020.9244043

Cite this

Wang, Y., Dong, J., Liu, Y., Wang, C., & Qu, G. (2020). A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress. In T. Mitra, & A. Gerstlauer (Eds.), Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020 (pp. 37-39). Article 9244043 (Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMSOFT51651.2020.9244043

Wang, Ye ; Dong, Jian ; Liu, Yanxin et al. / A Machine Learning based Approximate Computing Approach on Data Flow Graphs : Work-in-Progress. Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020. editor / Tulika Mitra ; Andreas Gerstlauer. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 37-39 (Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020).

@inproceedings{be70955c871546b78689ed8ef831d3a8,

title = "A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress",

abstract = "We report our ongoing work towards a machine learning based runtime approximate computing (AC) approach that can be applied on the data flow graph representation of any software program. This approach can utilize runtime inputs together with prior information of the software to identify and approximate the noncritical portion of a computation with low runtime overhead. Some preliminary experimental results show that compared with previous runtime AC approaches, our approach can significantly reduce the time overhead with little loss on the energy efficiency and computation accuracy.",

keywords = "approximate computing, data flow graph, energy efficiency, machine learning, runtime",

author = "Ye Wang and Jian Dong and Yanxin Liu and Chunpei Wang and Gang Qu",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 14th Turkish National Software Engineering Symposium, UYMS 2020 ; Conference date: 07-10-2020 Through 09-10-2020",

year = "2020",

month = sep,

day = "20",

doi = "10.1109/EMSOFT51651.2020.9244043",

language = "英语",

series = "Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020",

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

pages = "37--39",

editor = "Tulika Mitra and Andreas Gerstlauer",

booktitle = "Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020",

address = "美国",

}

Wang, Y, Dong, J, Liu, Y, Wang, C & Qu, G 2020, A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress. in T Mitra & A Gerstlauer (eds), Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020., 9244043, Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020, Institute of Electrical and Electronics Engineers Inc., pp. 37-39, 14th Turkish National Software Engineering Symposium, UYMS 2020, Istanbul, Turkey, 7/10/20. https://doi.org/10.1109/EMSOFT51651.2020.9244043

A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress. / Wang, Ye; Dong, Jian; Liu, Yanxin et al.
Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020. ed. / Tulika Mitra; Andreas Gerstlauer. Institute of Electrical and Electronics Engineers Inc., 2020. p. 37-39 9244043 (Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020).

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

TY - GEN

T1 - A Machine Learning based Approximate Computing Approach on Data Flow Graphs

T2 - 14th Turkish National Software Engineering Symposium, UYMS 2020

AU - Wang, Ye

AU - Dong, Jian

AU - Liu, Yanxin

AU - Wang, Chunpei

AU - Qu, Gang

PY - 2020/9/20

Y1 - 2020/9/20

N2 - We report our ongoing work towards a machine learning based runtime approximate computing (AC) approach that can be applied on the data flow graph representation of any software program. This approach can utilize runtime inputs together with prior information of the software to identify and approximate the noncritical portion of a computation with low runtime overhead. Some preliminary experimental results show that compared with previous runtime AC approaches, our approach can significantly reduce the time overhead with little loss on the energy efficiency and computation accuracy.

AB - We report our ongoing work towards a machine learning based runtime approximate computing (AC) approach that can be applied on the data flow graph representation of any software program. This approach can utilize runtime inputs together with prior information of the software to identify and approximate the noncritical portion of a computation with low runtime overhead. Some preliminary experimental results show that compared with previous runtime AC approaches, our approach can significantly reduce the time overhead with little loss on the energy efficiency and computation accuracy.

KW - approximate computing

KW - data flow graph

KW - energy efficiency

KW - machine learning

KW - runtime

UR - https://www.scopus.com/pages/publications/85097653851

U2 - 10.1109/EMSOFT51651.2020.9244043

DO - 10.1109/EMSOFT51651.2020.9244043

M3 - 会议稿件

AN - SCOPUS:85097653851

T3 - Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020

SP - 37

EP - 39

BT - Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020

A2 - Mitra, Tulika

A2 - Gerstlauer, Andreas

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 7 October 2020 through 9 October 2020

ER -

Wang Y, Dong J, Liu Y, Wang C, Qu G. A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress. In Mitra T, Gerstlauer A, editors, Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 37-39. 9244043. (Proceedings of the 2020 International Conference on Embedded Software, EMSOFT 2020). doi: 10.1109/EMSOFT51651.2020.9244043

A Machine Learning based Approximate Computing Approach on Data Flow Graphs: Work-in-Progress

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this