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 language | English |
|---|---|
| Title of host publication | Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 317-320 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781728102139 |
| DOIs | |
| Publication status | Published - 2018 Dec 1 |
| Event | 17th International Conference on Field-Programmable Technology, FPT 2018 - Naha, Okinawa, Japan Duration: 2018 Dec 10 → 2018 Dec 14 |
Publication series
| Name | Proceedings - 2018 International Conference on Field-Programmable Technology, FPT 2018 |
|---|
Conference
| Conference | 17th International Conference on Field-Programmable Technology, FPT 2018 |
|---|---|
| Country | Japan |
| City | Naha, Okinawa |
| Period | 18/12/10 → 18/12/14 |
Fingerprint
Keywords
- exascale computing
- FPGAs
- heterogeneous systems
- Performance modelling
- reconfigurable platforms
ASJC Scopus subject areas
- Software
- Computer Science Applications
- Hardware and Architecture
Cite this
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 proceeding › Conference contribution
}
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 -