TY - GEN
T1 - A Python-based High-Level Programming Flow for CPU-FPGA Heterogeneous Systems
T2 - 2021 IEEE/ACM Workshop on Programming Environments for Heterogeneous Computing, PEHC 2021
AU - Huang, Sitao
AU - Wu, Kun
AU - Chalamalasetti, Sai Rahul
AU - El Hajj, Izzat
AU - Xu, Cong
AU - Faraboschi, Paolo
AU - Chen, Deming
N1 - Funding Information:
ACKNOWLEDGMENT This work is supported by Hewlett Packard Labs, Xilinx Center of Excellence at UIUC, Xilinx Adaptive Compute Cluster (XACC) initiative, IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR), and BAH HT 15-1158 contract.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The fast-growing complexity of new applications and new use scenarios poses serious challenges for computing systems. Heterogeneous systems consist of different types of processors and accelerators, and provide unique combined benefits of hard-ware acceleration from each individual component. CPU-FPGA heterogeneous systems provide both programmable logic and general-purpose processors, and they have demonstrated great flexibility, performance, and efficiency. Heterogeneous systems have been created and deployed in many different applications and scenarios. However, as system complexity and application complexity grow rapidly, programming and optimizing heterogeneous systems require great manual efforts and consume a lot of time. In this work, we propose a Python-based high-level programming framework to simplify programming and optimization of CPU-FPGA heterogeneous systems. The proposed high-level operations isolate underlying hardware details from programmers and provide more optimization opportunities for the compiler.
AB - The fast-growing complexity of new applications and new use scenarios poses serious challenges for computing systems. Heterogeneous systems consist of different types of processors and accelerators, and provide unique combined benefits of hard-ware acceleration from each individual component. CPU-FPGA heterogeneous systems provide both programmable logic and general-purpose processors, and they have demonstrated great flexibility, performance, and efficiency. Heterogeneous systems have been created and deployed in many different applications and scenarios. However, as system complexity and application complexity grow rapidly, programming and optimizing heterogeneous systems require great manual efforts and consume a lot of time. In this work, we propose a Python-based high-level programming framework to simplify programming and optimization of CPU-FPGA heterogeneous systems. The proposed high-level operations isolate underlying hardware details from programmers and provide more optimization opportunities for the compiler.
KW - compiler
KW - FPGA
KW - heterogeneous systems
KW - Python
UR - http://www.scopus.com/inward/record.url?scp=85124232635&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124232635&partnerID=8YFLogxK
U2 - 10.1109/PEHC54839.2021.00008
DO - 10.1109/PEHC54839.2021.00008
M3 - Conference contribution
AN - SCOPUS:85124232635
T3 - Proceedings of PEHC 2021: Workshop on Programming Environments for Heterogeneous Computing, Held in conjunction with SC 2021: The International Conference for High Performance Computing, Networking, Storage and Analysis
SP - 20
EP - 26
BT - Proceedings of PEHC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 November 2021
ER -