GRAMC: General-purpose and reconfigurable analog matrix computing architecture

Autor:	Pan, Lunshuai, Wang, Shiqing, Zuo, Pushen, Sun, Zhong
Rok vydání:	2025
Předmět:	Computer Science - Hardware Architecture Computer Science - Emerging Technologies Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
Popis:	In-memory analog matrix computing (AMC) with resistive random-access memory (RRAM) represents a highly promising solution that solves matrix problems in one step. However, the existing AMC circuits each have a specific connection topology to implement a single computing function, lack of the universality as a matrix processor. In this work, we design a reconfigurable AMC macro for general-purpose matrix computations, which is achieved by configuring proper connections between memory array and amplifier circuits. Based on this macro, we develop a hybrid system that incorporates an on-chip write-verify scheme and digital functional modules, to deliver a general-purpose AMC solver for various applications. Comment: This paper has been accepted to DATE 2025
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2501.01586 Zobrazit plný text záznamu View this record from Arxiv