Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators

doi:10.1145/3631523

	Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators
	Li, Wanqian 1,2; Han, Yinhe 1; Chen, Xiaoming 1
	2024
发表期刊	ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS
ISSN	1084-4309
卷号	29 期号:1 页码:24
摘要	The resistive random-access memory (ReRAM) has widely been used to accelerate convolutional neural networks (CNNs) thanks to its analog in-memory computing capability. ReRAM crossbars not only store layers' weights, but also perform in-situ matrix-vector multiplications which are core operations of CNNs. To boost the performance of ReRAM-based CNN accelerators, crossbars can be duplicated to explore more intra-layer parallelism. The crossbar allocation scheme can significantly influence both the computing throughput and bandwidth requirements of ReRAM-based CNN accelerators. Under the resource constraints (i.e., crossbars and memory bandwidths), how to find the optimal number of crossbars for each layer to maximize the inference performance for an entire CNN is an unsolved problem. In this work, we find the optimal crossbar allocation scheme by mathematically modeling the problem as a constrained optimization problem and solving it with a dynamic programming based solver. Experiments demonstrate that ourmodel for CNN inference time is almost precise, and the proposed framework can obtain solutions with near-optimal inference time. We also emphasize that communication (i.e., data access) is an important factor and must also be considered when determining the optimal crossbar allocation scheme.
关键词	ReRAM crossbars CNN accelerator mathematical framework crossbar allocation
DOI	10.1145/3631523
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018YFA0701500] ; National Natural Science Foundation of China[62122076] ; National Natural Science Foundation of China[61834006] ; National Natural Science Foundation of China[62025404] ; Key Research Program of Frontier Sciences, CAS[ZDBS-LY-JSC012] ; Strategic Priority Research Program of CAS[XDB44000000] ; Innovation Funding of ICT, CAS[E261040]
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS记录号	WOS:001168397800021
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38805
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Xiaoming
作者单位	1.Chinese Acad Sci, Inst Comp Technol, 6 Kexueyuan S Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, 6 Kexueyuan S Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Wanqian,Han, Yinhe,Chen, Xiaoming. Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators[J]. ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS,2024,29(1):24.
APA	Li, Wanqian,Han, Yinhe,&Chen, Xiaoming.(2024).Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators.ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS,29(1),24.
MLA	Li, Wanqian,et al."Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators".ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS 29.1(2024):24.