An trace-driven performance prediction method for exploring noc design optimization

Naoya Niwa, Tomohiro Totoki, Hiroki Matsutani, Michihiro Koibuchi, Hideharu Amano

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

Abstract

The performance prediction for a NoC-based Chip Multi-Processor (CMP) is one of the main design concerns. Generally, there is a trade-off between accuracy and time overhead on the performance prediction of computer systems. In particular, the time overhead is proportional or exponential to the number of cores when using a cycle-accurate full-system simulation, such as gem5. In this study, we propose an accurate and scalable method to predict the influence of design NoC parameters on its performance. Our method counts the number of execution cycles when employing the target NoC based on the statistics of one-time execution of a full-system simulation using a fully-connected NoC. To evaluate the accuracy and execution time overhead, we use the case that randomly generates allocations of processors with 3D mesh topology NoC. Its Mean Absolute Percentage Error of the estimated cycles is about 4.7%, and the Maximum Absolute Percentage Error is about 8.5%.

Original languageEnglish
Title of host publicationProceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-185
Number of pages4
ISBN (Electronic)9781538691847
DOIs
Publication statusPublished - 2018 Dec 26
Event6th International Symposium on Computing and Networking Workshops, CANDARW 2018 - Takayama, Japan
Duration: 2018 Nov 272018 Nov 30

Publication series

NameProceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018

Conference

Conference6th International Symposium on Computing and Networking Workshops, CANDARW 2018
CountryJapan
CityTakayama
Period18/11/2718/11/30

Fingerprint

Performance Prediction
Trace
System Simulation
Cycle
Execution Time
Percentage
Chip multiprocessors
Count
Computer systems
Trade-offs
Directly proportional
Topology
Network on chip
Design optimization
Network-on-chip
Prediction
Statistics
Mesh
Predict
Target

Keywords

  • Network-on-Chip
  • Optimization
  • Performance prediction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Statistics, Probability and Uncertainty
  • Computer Science Applications

Cite this

Niwa, N., Totoki, T., Matsutani, H., Koibuchi, M., & Amano, H. (2018). An trace-driven performance prediction method for exploring noc design optimization. In Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018 (pp. 182-185). [8590896] (Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CANDARW.2018.00042

An trace-driven performance prediction method for exploring noc design optimization. / Niwa, Naoya; Totoki, Tomohiro; Matsutani, Hiroki; Koibuchi, Michihiro; Amano, Hideharu.

Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 182-185 8590896 (Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018).

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

Niwa, N, Totoki, T, Matsutani, H, Koibuchi, M & Amano, H 2018, An trace-driven performance prediction method for exploring noc design optimization. in Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018., 8590896, Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, Institute of Electrical and Electronics Engineers Inc., pp. 182-185, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, Takayama, Japan, 18/11/27. https://doi.org/10.1109/CANDARW.2018.00042
Niwa N, Totoki T, Matsutani H, Koibuchi M, Amano H. An trace-driven performance prediction method for exploring noc design optimization. In Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 182-185. 8590896. (Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018). https://doi.org/10.1109/CANDARW.2018.00042
Niwa, Naoya ; Totoki, Tomohiro ; Matsutani, Hiroki ; Koibuchi, Michihiro ; Amano, Hideharu. / An trace-driven performance prediction method for exploring noc design optimization. Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 182-185 (Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018).
@inproceedings{7ff8a6c5acc843cfb2630d836160ab50,
title = "An trace-driven performance prediction method for exploring noc design optimization",
abstract = "The performance prediction for a NoC-based Chip Multi-Processor (CMP) is one of the main design concerns. Generally, there is a trade-off between accuracy and time overhead on the performance prediction of computer systems. In particular, the time overhead is proportional or exponential to the number of cores when using a cycle-accurate full-system simulation, such as gem5. In this study, we propose an accurate and scalable method to predict the influence of design NoC parameters on its performance. Our method counts the number of execution cycles when employing the target NoC based on the statistics of one-time execution of a full-system simulation using a fully-connected NoC. To evaluate the accuracy and execution time overhead, we use the case that randomly generates allocations of processors with 3D mesh topology NoC. Its Mean Absolute Percentage Error of the estimated cycles is about 4.7{\%}, and the Maximum Absolute Percentage Error is about 8.5{\%}.",
keywords = "Network-on-Chip, Optimization, Performance prediction",
author = "Naoya Niwa and Tomohiro Totoki and Hiroki Matsutani and Michihiro Koibuchi and Hideharu Amano",
year = "2018",
month = "12",
day = "26",
doi = "10.1109/CANDARW.2018.00042",
language = "English",
series = "Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "182--185",
booktitle = "Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018",

}

TY - GEN

T1 - An trace-driven performance prediction method for exploring noc design optimization

AU - Niwa, Naoya

AU - Totoki, Tomohiro

AU - Matsutani, Hiroki

AU - Koibuchi, Michihiro

AU - Amano, Hideharu

PY - 2018/12/26

Y1 - 2018/12/26

N2 - The performance prediction for a NoC-based Chip Multi-Processor (CMP) is one of the main design concerns. Generally, there is a trade-off between accuracy and time overhead on the performance prediction of computer systems. In particular, the time overhead is proportional or exponential to the number of cores when using a cycle-accurate full-system simulation, such as gem5. In this study, we propose an accurate and scalable method to predict the influence of design NoC parameters on its performance. Our method counts the number of execution cycles when employing the target NoC based on the statistics of one-time execution of a full-system simulation using a fully-connected NoC. To evaluate the accuracy and execution time overhead, we use the case that randomly generates allocations of processors with 3D mesh topology NoC. Its Mean Absolute Percentage Error of the estimated cycles is about 4.7%, and the Maximum Absolute Percentage Error is about 8.5%.

AB - The performance prediction for a NoC-based Chip Multi-Processor (CMP) is one of the main design concerns. Generally, there is a trade-off between accuracy and time overhead on the performance prediction of computer systems. In particular, the time overhead is proportional or exponential to the number of cores when using a cycle-accurate full-system simulation, such as gem5. In this study, we propose an accurate and scalable method to predict the influence of design NoC parameters on its performance. Our method counts the number of execution cycles when employing the target NoC based on the statistics of one-time execution of a full-system simulation using a fully-connected NoC. To evaluate the accuracy and execution time overhead, we use the case that randomly generates allocations of processors with 3D mesh topology NoC. Its Mean Absolute Percentage Error of the estimated cycles is about 4.7%, and the Maximum Absolute Percentage Error is about 8.5%.

KW - Network-on-Chip

KW - Optimization

KW - Performance prediction

UR - http://www.scopus.com/inward/record.url?scp=85061448351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061448351&partnerID=8YFLogxK

U2 - 10.1109/CANDARW.2018.00042

DO - 10.1109/CANDARW.2018.00042

M3 - Conference contribution

T3 - Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018

SP - 182

EP - 185

BT - Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -