Cited By
View all- Nguyen MSerafin NHoe J(2020)Partial Reconfiguration for Design Optimization2020 30th International Conference on Field-Programmable Logic and Applications (FPL)10.1109/FPL50879.2020.00061(328-334)Online publication date: Aug-2020
Software-based Dynamic Overlays Require Fast, Fine-grained Partial Reconfiguration
Article No.: 13, Pages 1 - 6
Abstract
In this paper, we consider dynamic overlays which use fine-grained partial reconfiguration (PR) to continuously adapt to their software-based workload. In particular, we show how to modify a traditional (static) overlay developed for OpenVX into a dynamic overlay. We use a Xilinx FPGA, and show that the dynamic overlay needs unsupported features including faster PR, relocatability, and fine-grained configuration is needed for performance. Since these features are not available in Xilinx FPGAs, we estimate the application-level speedup they would provide. We find that vector custom instruction (VCI) chaining, which allow a VCI to directly cascade its result into another VCI is also essential. Overall, we find the static overlay achieves a speedup of roughly 20x faster than a Cortex-A9 processor, but with improved PR and chaining a speedup of 106x is attainable. While there have been calls for fast, fine-grained PR devices for decades, we believe that dynamic overlays may be the first true "killer application" that will justify adding these features to all FPGA devices.
References
[1]
Aklah, Z. T. A Hybrid Partially Reconfigurable Overlay Supporting Just-In-Time Assembly of Custom Accelerators on FPGAs. PhD thesis, 2017.
[2]
Hansen, S. G., et al. High speed partial runtime reconfiguration using enhanced ICAP hard macro. In IEEE IPDPSW (2011).
[3]
Intel. OpenVINO toolkit.
[4]
Janssen, B., et al. A dynamic partial reconfigurable overlay framework for python. In ARC (2018), Springer.
[5]
Koch, D., et al. An efficient FPGA overlay for portable custom instruction set extensions. In FPL (2013).
[6]
Kooti, H., and Bozorgzadeh, E. Reconfiguration-aware task graph scheduling. In IEEE EUC (2015).
[7]
Omidian, H., et al. Exploring automated space/time tradeoffs for OpenVX compute graphs. In IEEE ICFPT (2017).
[8]
Omidian, H., et al. An accelerated OpenVX overlay for pure software programmers. In IEEE ICFPT (2018).
[9]
Severance, A., et al. Soft vector processors with streaming pipelines. In FPGA 2014.
[10]
Severance, A., et al. Embedded supercomputing in FPGAs with the VectorBlox MXP matrix processor. In CODES+ISSS 2013 (2013).
[11]
Taheri, S., et al. Acceleration framework for FPGA implementation of OpenVX graph pipelines. Tech. rep., Center for Embedded and Cyber-Physical Systems, UC Irvine, 2018.
[12]
Tompkins, M. F. Optimization techniques for task allocation and scheduling in distributed multi-agent operations. PhD thesis, MIT, 2003.
[13]
Trimberger, S., et al. A time-multiplexed fpga. In FCCM 1997, IEEE.
[14]
Xiao, Z., et al. A partial reconfiguration controller for Altera Stratix V FPGAs. In FPL (2016).
[15]
Xilinx. Versal: The first adaptive compute acceleration platform (ACAP).
[16]
Xilinx. Xilinx OpenCV User Guide UG1233, January 2019.
Recommendations
FPGA Dynamic and Partial Reconfiguration: A Survey of Architectures, Methods, and Applications
Dynamic and partial reconfiguration are key differentiating capabilities of field programmable gate arrays (FPGAs). While they have been studied extensively in academic literature, they find limited use in deployed systems. We review FPGA ...
Real-time embedded systems powered by FPGA dynamic partial self-reconfiguration: a case study oriented to biometric recognition applications
This work aims to pave the way for an efficient open system architecture applied to embedded electronic applications to manage the processing of computationally complex algorithms at real-time and low-cost. The target is to define a standard ...
Fine-Grained Partial Runtime Reconfiguration on Virtex-5 FPGAs
FCCM '10: Proceedings of the 2010 18th IEEE Annual International Symposium on Field-Programmable Custom Computing MachinesThe architecture of Xilinx FPGAs, has changed remarkable with respect to their ability to implement runtime reconfigurable systems throughout the last generations. This paper will discuss these changes and reveal an on-FPGA communication architecture ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
June 2019
106 pages
ISBN:9781450372558
DOI:10.1145/3337801
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 06 June 2019
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
HEART 2019
HEART 2019: The 10th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies
June 6 - 7, 2019
Nagasaki, Japan
Acceptance Rates
HEART '19 Paper Acceptance Rate 12 of 29 submissions, 41%;
Overall Acceptance Rate 22 of 50 submissions, 44%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 73Total Downloads
- Downloads (Last 12 months)8
- Downloads (Last 6 weeks)1
Reflects downloads up to 30 Nov 2024
Other Metrics
Citations
Cited By
View all- Nguyen MSerafin NHoe J(2020)Partial Reconfiguration for Design Optimization2020 30th International Conference on Field-Programmable Logic and Applications (FPL)10.1109/FPL50879.2020.00061(328-334)Online publication date: Aug-2020
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in