| |||||||
ShanghaiTech University Knowledge Management System
CUGEMM: Counter-Based Unary Computing Architecture for Energy-Efficient GEMM | |
2025 | |
会议录名称 | 2025 62TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC)
![]() |
发表状态 | 已投递待接收 |
摘要 | Unary computing is distinguished by its low hardware overhead and minimal power consumption, particularly excelling in multiplication tasks through bit-wise operations. However, conversions between binary and unary formats are commonly required in conventional unary computing systems, which may neutralize the hardware efficiency. In this work, we propose a unary multiplier that alleviates the cost of binary-to-unary converters by utilizing only one counter and one comparator for unary sequence generation. Leveraging a simple counting process, a counter with peripheral logic circuits is utilized to perform unary multiplication. Based on this technique, a general matrix multiplication (GEMM) unit, referred to as CUGEMM, is devised. To ensure a high accuracy in neural network computations, CUGEMM dynamically scales the small input values to avoid excessive accuracy loss. Experimental results reveal that the proposed CUGEMM achieves on average 14.71\% power reduction, while maintaining a high accuracy in ImageNet classification tasks compared to state-of-the-art (SoTA) designs. |
关键词 | Unary computing Matrix multiplication Deep learning accelerators Stochastic computing |
会议名称 | 2025 62th ACM/IEEE Design Automation Conference (DAC) |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/527146 |
专题 | 信息科学与技术学院_博士生 信息科学与技术学院_硕士生 信息科学与技术学院_本科生 信息科学与技术学院_PI研究组_刘思廷组 |
共同第一作者 | Jiang HL(姜红兰) |
通讯作者 | Gong YT(龚雨陶) |
作者单位 | 1.上海科技大学 2.上海交通大学 |
第一作者单位 | 上海科技大学 |
通讯作者单位 | 上海科技大学 |
第一作者的第一单位 | 上海科技大学 |
推荐引用方式 GB/T 7714 | Gong YT,Ni ZJ,Ying KX,et al. CUGEMM: Counter-Based Unary Computing Architecture for Energy-Efficient GEMM[C],2025. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。