AKGF: Automatic Kernel Generation for DNN on CPU-FPGA

doi:10.1093/comjnl/bxad086

	AKGF: Automatic Kernel Generation for DNN on CPU-FPGA
	Dong, Dong 1; Jiang, Hongxu 1; Diao, Boyu 2
	2023-08-11
发表期刊	COMPUTER JOURNAL
ISSN	0010-4620
页码	9
摘要	While tensor accelerated compilers have proven effective in deploying deep neural networks (DNN) on general-purpose hardware, optimizing for FPGA remains challenging due to the complex DNN architectures and the heterogeneous, semi-open compute units. This paper introduces the Automatic Kernel Generation for DNN on CPU-FPGA (AKGF) framework for efficient deployment of DNN on heterogeneous CPU-FPGA platforms. AKGF generates an intermediate representation (IR) of the DNN using TVM's Halide IR, annotates the operators of model layers in the IR to compute them on the corresponding hardware cores, and further optimizes the operator code for CPU and FPGA using ARM's function library and the polyhedral model to enhance model inference speed and power consumption. The experimental tests conducted on a CPU-FPGA board validate the effectiveness of AKGF, demonstrating significant acceleration ratios (up to 6.7x) compared to state-of-the-art accelerators while achieving a 2x power optimization. AKGF effectively leverages the computational capabilities of both CPU and FPGA for high-performance deployment of DNN on CPU-FPGA platforms.
关键词	DNN accelerated compilers polyhedral model heterogeneous computing CPU-FPGA
DOI	10.1093/comjnl/bxad086
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021ZD0110202]
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001051231100001
出版者	OXFORD UNIV PRESS
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21378
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Dong, Dong; Jiang, Hongxu; Diao, Boyu
作者单位	1.Beihang Univ, Beijing Key Lab Digital Media, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100086, Peoples R China
推荐引用方式 GB/T 7714	Dong, Dong,Jiang, Hongxu,Diao, Boyu. AKGF: Automatic Kernel Generation for DNN on CPU-FPGA[J]. COMPUTER JOURNAL,2023:9.
APA	Dong, Dong,Jiang, Hongxu,&Diao, Boyu.(2023).AKGF: Automatic Kernel Generation for DNN on CPU-FPGA.COMPUTER JOURNAL,9.
MLA	Dong, Dong,et al."AKGF: Automatic Kernel Generation for DNN on CPU-FPGA".COMPUTER JOURNAL (2023):9.