arrow
返回

Analytical Performance Estimation for Large-Scale Reconfigurable Dataflow Platforms

delete2021-08-12
delete0
PRE
AI
R
Ryota Yasudo *
J
José G. F. Coutinho
A
Ana-Lucia Varbanescu
W
Wayne Luk
H
Hideharu Amano
T
Tobias Becker
C
Ce Guo
DOI:10.1145/3452742delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Next-generation high-performance computing platforms will handle extreme data- and compute-intensive problems that are intractable with today's technology. A promising path in achieving the next leap in high-performance computing is to embrace heterogeneity and specialised computing in the form of reconfigurable accelerators such as FPGAs, which have been shown to speed up compute-intensive tasks with reduced power consumption. However, assessing the feasibility of large-scale heterogeneous systems requires fast and accurate performance prediction. This article proposes Performance Estimation for Reconfigurable Kernels and Systems (PERKS), a novel performance estimation framework for reconfigurable dataflow platforms. PERKS makes use of an analytical model with machine and application parameters for predicting the performance of multi-accelerator systems and detecting their bottlenecks. Model calibration is automatic, making the model flexible and usable for different machine configurations and applications, including hypothetical ones. Our experimental results show that PERKS can predict the performance of current workloads on reconfigurable dataflow platforms with an accuracy above 91%. The results also illustrate how the modelling scales to large workloads, and how performance impact of architectural features can be estimated in seconds.
Keyword:
Performance modelling
heterogeneous systems
reconfigurable dataflow platforms
FPGAs

期刊

ACM Transactions on Reconfigurable Technology and Systems 封面图
ACM Transactions on Reconfigurable Technology and Systems
IF:
2.8
论文数:
598
被引数:
810

机构

K
Keio University
学者数:
2.2W
论文数: 1.6W
被引数: 13
U
university of amsterdam
学者数:
6.0W
论文数: 5.1W
被引数: 94
H
Hiroshima University
学者数:
2.1W
论文数: 1.5W
被引数: 1.3W
I
Imperial College London
学者数:
8.3W
论文数: 7.3W
被引数: 11.1W
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
err分享
err收藏
学者 查看更多内容