Accuracy analysis of machine learning-based performance modeling for microprocessors

Yoshihiro Tanaka; Keitaro Oka; Takatsugu Ono; Koji Inoue

doi:10.1109/JEC-ECC.2016.7518973

Accuracy analysis of machine learning-based performance modeling for microprocessors

Yoshihiro Tanaka, Keitaro Oka, Takatsugu Ono, Koji Inoue

Department of I&E Visionaries

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

1 Citation (Scopus)

Abstract

This paper analyzes accuracy of performance models generated by machine learning-based empirical modeling methodology. Although the accuracy strongly depends on the quality of learning procedure, it is not clear what kind of learning algorithms and training data set (or feature) should be used. This paper inclusively explores the learning space of processor performance modeling as a case study. We focus on static architectural parameters as training data set such as cache size and clock frequency. Experimental results show that a tree-based non-linear regression modeling is superior to a stepwise linear regression modeling. Another observation is that clock frequency is the most important feature to improve prediction accuracy.

Original language	English
Title of host publication	Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	83-86
Number of pages	4
ISBN (Electronic)	9781467389365
DOIs	https://doi.org/10.1109/JEC-ECC.2016.7518973
Publication status	Published - Jul 21 2016
Event	4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016 - Cairo, Egypt Duration: May 31 2016 → Jun 2 2016

Publication series

Name	Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016

Other

Other	4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016
Country/Territory	Egypt
City	Cairo
Period	5/31/16 → 6/2/16

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Signal Processing
Computer Science Applications

Access to Document

10.1109/JEC-ECC.2016.7518973

Cite this

Tanaka, Y., Oka, K., Ono, T., & Inoue, K. (2016). Accuracy analysis of machine learning-based performance modeling for microprocessors. In Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016 (pp. 83-86). Article 7518973 (Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/JEC-ECC.2016.7518973

Accuracy analysis of machine learning-based performance modeling for microprocessors. / Tanaka, Yoshihiro; Oka, Keitaro; Ono, Takatsugu et al.
Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 83-86 7518973 (Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016).

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

Tanaka, Y, Oka, K, Ono, T & Inoue, K 2016, Accuracy analysis of machine learning-based performance modeling for microprocessors. in Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016., 7518973, Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016, Institute of Electrical and Electronics Engineers Inc., pp. 83-86, 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016, Cairo, Egypt, 5/31/16. https://doi.org/10.1109/JEC-ECC.2016.7518973

Tanaka Y, Oka K, Ono T , Inoue K. Accuracy analysis of machine learning-based performance modeling for microprocessors. In Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 83-86. 7518973. (Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016). doi: 10.1109/JEC-ECC.2016.7518973

Tanaka, Yoshihiro ; Oka, Keitaro ; Ono, Takatsugu et al. / Accuracy analysis of machine learning-based performance modeling for microprocessors. Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 83-86 (Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016).

@inproceedings{40fbbf7491b04bed815301918d736b13,

title = "Accuracy analysis of machine learning-based performance modeling for microprocessors",

abstract = "This paper analyzes accuracy of performance models generated by machine learning-based empirical modeling methodology. Although the accuracy strongly depends on the quality of learning procedure, it is not clear what kind of learning algorithms and training data set (or feature) should be used. This paper inclusively explores the learning space of processor performance modeling as a case study. We focus on static architectural parameters as training data set such as cache size and clock frequency. Experimental results show that a tree-based non-linear regression modeling is superior to a stepwise linear regression modeling. Another observation is that clock frequency is the most important feature to improve prediction accuracy.",

author = "Yoshihiro Tanaka and Keitaro Oka and Takatsugu Ono and Koji Inoue",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016 ; Conference date: 31-05-2016 Through 02-06-2016",

year = "2016",

month = jul,

day = "21",

doi = "10.1109/JEC-ECC.2016.7518973",

language = "English",

series = "Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016",

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

pages = "83--86",

booktitle = "Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016",

address = "United States",

}

TY - GEN

T1 - Accuracy analysis of machine learning-based performance modeling for microprocessors

AU - Tanaka, Yoshihiro

AU - Oka, Keitaro

AU - Ono, Takatsugu

AU - Inoue, Koji

PY - 2016/7/21

Y1 - 2016/7/21

N2 - This paper analyzes accuracy of performance models generated by machine learning-based empirical modeling methodology. Although the accuracy strongly depends on the quality of learning procedure, it is not clear what kind of learning algorithms and training data set (or feature) should be used. This paper inclusively explores the learning space of processor performance modeling as a case study. We focus on static architectural parameters as training data set such as cache size and clock frequency. Experimental results show that a tree-based non-linear regression modeling is superior to a stepwise linear regression modeling. Another observation is that clock frequency is the most important feature to improve prediction accuracy.

AB - This paper analyzes accuracy of performance models generated by machine learning-based empirical modeling methodology. Although the accuracy strongly depends on the quality of learning procedure, it is not clear what kind of learning algorithms and training data set (or feature) should be used. This paper inclusively explores the learning space of processor performance modeling as a case study. We focus on static architectural parameters as training data set such as cache size and clock frequency. Experimental results show that a tree-based non-linear regression modeling is superior to a stepwise linear regression modeling. Another observation is that clock frequency is the most important feature to improve prediction accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84991810169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991810169&partnerID=8YFLogxK

U2 - 10.1109/JEC-ECC.2016.7518973

DO - 10.1109/JEC-ECC.2016.7518973

M3 - Conference contribution

AN - SCOPUS:84991810169

T3 - Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016

SP - 83

EP - 86

BT - Proceedings of the 2016 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Japan-Egypt Conference on Electronic, Communication and Computers, JEC-ECC 2016

Y2 - 31 May 2016 through 2 June 2016

ER -

Accuracy analysis of machine learning-based performance modeling for microprocessors

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this