Performance Estimation for Exascale Reconfigurable Dataflow Platforms

Ryota Yasudo, Jose Coutinho, Ana Varbanescu, Wayne Luk, Hideharu Amano, Tobias Becker

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

Abstract

The next generation high-performance computing platforms will need to support exascale computing. A promising path in achieving exascale is to embrace heterogeneity and specialised computing in the form of reconfigurable accelerators. However, assessing the feasibility of heterogeneous exascale systems requires fast and accurate performance prediction. This paper proposes PERKS, a novel performance estimation frame-work for reconfigurable dataflow platforms (RDPs). PERKS uses machine and application parameters to build an analytical model for predicting the performance of multi-Accelerator systems. Moreover, model calibration is automatic, making the model flexible and usable for different machine configurations and applications. Our experimental results demonstrate that PERKS can predict the performance of current workloads and RDPs with an accuracy above 95%. We also demonstrate how the modelling scales to exascale workloads and exascale platforms.

Original languageEnglish
Title of host publicationProceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages317-320
Number of pages4
ISBN (Electronic)9781728102139
DOIs
Publication statusPublished - 2018 Dec 1
Event17th International Conference on Field-Programmable Technology, FPT 2018 - Naha, Okinawa, Japan
Duration: 2018 Dec 102018 Dec 14

Publication series

NameProceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018

Conference

Conference17th International Conference on Field-Programmable Technology, FPT 2018
CountryJapan
CityNaha, Okinawa
Period18/12/1018/12/14

Fingerprint

Particle accelerators
Analytical models
Calibration

Keywords

  • exascale computing
  • FPGAs
  • heterogeneous systems
  • Performance modelling
  • reconfigurable platforms

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Hardware and Architecture

Cite this

Yasudo, R., Coutinho, J., Varbanescu, A., Luk, W., Amano, H., & Becker, T. (2018). Performance Estimation for Exascale Reconfigurable Dataflow Platforms. In Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018 (pp. 317-320). [8742283] (Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FPT.2018.00062

Performance Estimation for Exascale Reconfigurable Dataflow Platforms. / Yasudo, Ryota; Coutinho, Jose; Varbanescu, Ana; Luk, Wayne; Amano, Hideharu; Becker, Tobias.

Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 317-320 8742283 (Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018).

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

Yasudo, R, Coutinho, J, Varbanescu, A, Luk, W, Amano, H & Becker, T 2018, Performance Estimation for Exascale Reconfigurable Dataflow Platforms. in Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018., 8742283, Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018, Institute of Electrical and Electronics Engineers Inc., pp. 317-320, 17th International Conference on Field-Programmable Technology, FPT 2018, Naha, Okinawa, Japan, 18/12/10. https://doi.org/10.1109/FPT.2018.00062
Yasudo R, Coutinho J, Varbanescu A, Luk W, Amano H, Becker T. Performance Estimation for Exascale Reconfigurable Dataflow Platforms. In Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 317-320. 8742283. (Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018). https://doi.org/10.1109/FPT.2018.00062
Yasudo, Ryota ; Coutinho, Jose ; Varbanescu, Ana ; Luk, Wayne ; Amano, Hideharu ; Becker, Tobias. / Performance Estimation for Exascale Reconfigurable Dataflow Platforms. Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 317-320 (Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018).
@inproceedings{d1baa27084ee4514baa666e27ff67128,
title = "Performance Estimation for Exascale Reconfigurable Dataflow Platforms",
abstract = "The next generation high-performance computing platforms will need to support exascale computing. A promising path in achieving exascale is to embrace heterogeneity and specialised computing in the form of reconfigurable accelerators. However, assessing the feasibility of heterogeneous exascale systems requires fast and accurate performance prediction. This paper proposes PERKS, a novel performance estimation frame-work for reconfigurable dataflow platforms (RDPs). PERKS uses machine and application parameters to build an analytical model for predicting the performance of multi-Accelerator systems. Moreover, model calibration is automatic, making the model flexible and usable for different machine configurations and applications. Our experimental results demonstrate that PERKS can predict the performance of current workloads and RDPs with an accuracy above 95{\%}. We also demonstrate how the modelling scales to exascale workloads and exascale platforms.",
keywords = "exascale computing, FPGAs, heterogeneous systems, Performance modelling, reconfigurable platforms",
author = "Ryota Yasudo and Jose Coutinho and Ana Varbanescu and Wayne Luk and Hideharu Amano and Tobias Becker",
year = "2018",
month = "12",
day = "1",
doi = "10.1109/FPT.2018.00062",
language = "English",
series = "Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "317--320",
booktitle = "Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018",

}

TY - GEN

T1 - Performance Estimation for Exascale Reconfigurable Dataflow Platforms

AU - Yasudo, Ryota

AU - Coutinho, Jose

AU - Varbanescu, Ana

AU - Luk, Wayne

AU - Amano, Hideharu

AU - Becker, Tobias

PY - 2018/12/1

Y1 - 2018/12/1

N2 - The next generation high-performance computing platforms will need to support exascale computing. A promising path in achieving exascale is to embrace heterogeneity and specialised computing in the form of reconfigurable accelerators. However, assessing the feasibility of heterogeneous exascale systems requires fast and accurate performance prediction. This paper proposes PERKS, a novel performance estimation frame-work for reconfigurable dataflow platforms (RDPs). PERKS uses machine and application parameters to build an analytical model for predicting the performance of multi-Accelerator systems. Moreover, model calibration is automatic, making the model flexible and usable for different machine configurations and applications. Our experimental results demonstrate that PERKS can predict the performance of current workloads and RDPs with an accuracy above 95%. We also demonstrate how the modelling scales to exascale workloads and exascale platforms.

AB - The next generation high-performance computing platforms will need to support exascale computing. A promising path in achieving exascale is to embrace heterogeneity and specialised computing in the form of reconfigurable accelerators. However, assessing the feasibility of heterogeneous exascale systems requires fast and accurate performance prediction. This paper proposes PERKS, a novel performance estimation frame-work for reconfigurable dataflow platforms (RDPs). PERKS uses machine and application parameters to build an analytical model for predicting the performance of multi-Accelerator systems. Moreover, model calibration is automatic, making the model flexible and usable for different machine configurations and applications. Our experimental results demonstrate that PERKS can predict the performance of current workloads and RDPs with an accuracy above 95%. We also demonstrate how the modelling scales to exascale workloads and exascale platforms.

KW - exascale computing

KW - FPGAs

KW - heterogeneous systems

KW - Performance modelling

KW - reconfigurable platforms

UR - http://www.scopus.com/inward/record.url?scp=85068319351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068319351&partnerID=8YFLogxK

U2 - 10.1109/FPT.2018.00062

DO - 10.1109/FPT.2018.00062

M3 - Conference contribution

T3 - Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018

SP - 317

EP - 320

BT - Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -