UGEMM: Unary Computing Architecture for GEMM Applications
UGEMM: Unary Computing Architecture for GEMM Applications
复制标题
DOI：
10.1109/isca45697.2020.00040
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Di Wu-;Jingjie Li;Ruokai Yin;Hsuan Hsiao;Younghyun Kim;Joshua San Miguel
中科院分区：
文献类型：
--
作者：
Di Wu-;Jingjie Li;Ruokai Yin;Hsuan Hsiao;Younghyun Kim;Joshua San Miguel
通用矩阵乘法(GEMM)广泛应用于信号处理、机器学习和计算机视觉等领域。由于数字表示和计算的空间特性，传统的基于二进制计算的GEMM硬件体系结构在扩展时表现出较低的面积和能量效率。另一方面，一元计算可以用极其简单的处理单元来执行，通常只用一个逻辑门。但目前还没有一元GEMM的高效体系结构，本文提出了一种基于新型算术运算单元的面积和能量高效的一元GEMM体系结构uGEMM。所提出的设计放宽了先前对输入比特流施加的限制-低相关性和长数据流长度-并实现了比现有一元系统更好的面积和能量效率。此外，uGEMM的输出比特流表现出更高的精确度和更快的收敛速度，从而能够在资源受限的系统上实现动态能量精确度缩放。
General matrix multiplication (GEMM) is universal in various applications, such as signal processing, machine learning, and computer vision. Conventional GEMM hardware architectures based on binary computing exhibit low area and energy efficiency as they scale due to the spatial nature of number representation and computing. Unary computing, on the other hand, can be performed with extremely simple processing units, often just with a single logic gate. But currently there exist no efficient architectures for unary GEMM.In this paper, we present uGEMM, an area- and energy-efficient unary GEMM architecture enabled by novel arithmetic units. The proposed design relaxes previously-imposed constraints on input bit streams—low correlation and long stream length— and achieves superior area and energy efficiency over existing unary systems. Furthermore, uGEMM’s output bit streams exhibit higher accuracy and faster convergence, enabling dynamic energy-accuracy scaling on resource-constrained systems.