{"title":"Multilogic Sense Amplifier With a Circuit for Dynamic Reference Voltage Generation","authors":"Yen-Jen Chang;Kun-Lin Tsai;Chun Cheng;Xu-Yao Chen","doi":"10.1109/TCSI.2025.3554533","DOIUrl":null,"url":null,"abstract":"The rapid development of artificial intelligence (AI) systems has engendered a considerable increase in the computational power required in data-intensive applications, including facial recognition and image processing applications. The conventional von Neumann architecture, in which large quantities of data are transmitted between processing units and memory units, creates a bottleneck in AI applications. In-memory computing (IMC) offers an efficient solution to this problem by enabling computations within memory units, thus reducing the need for data transmission. This paper proposes a multilogic sense amplifier (MSA) with a dynamic reference voltage (DRV) generation circuit (hereafter denoted as MSA-DRV) to enhance the performance and reduce the power consumption of static random-access memory (SRAM)-based IMC. The proposed MSA-DRV performs six logic operations, namely the AND, NAND, OR, NOR, XOR, and XNOR operations, within an SRAM array by using a novel DRV circuit. The DRV circuit enables the voltage threshold to be adaptively changed according to the requirements of different operations. Experimental results indicated that the proposed MSA-DRV had lower computational latency (on average 29.9% lower) and power consumption (on average 30.6% lower) than did a conventional sense amplifier design and reconfigurable assist sense amplifier. Thus, the proposed design can overcome the von Neumann bottleneck to facilitate high-speed, energy-efficient data processing, which is crucial for AI-based and other data-intensive applications.","PeriodicalId":13039,"journal":{"name":"IEEE Transactions on Circuits and Systems I: Regular Papers","volume":"72 8","pages":"4052-4063"},"PeriodicalIF":5.2000,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Circuits and Systems I: Regular Papers","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10947751/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
The rapid development of artificial intelligence (AI) systems has engendered a considerable increase in the computational power required in data-intensive applications, including facial recognition and image processing applications. The conventional von Neumann architecture, in which large quantities of data are transmitted between processing units and memory units, creates a bottleneck in AI applications. In-memory computing (IMC) offers an efficient solution to this problem by enabling computations within memory units, thus reducing the need for data transmission. This paper proposes a multilogic sense amplifier (MSA) with a dynamic reference voltage (DRV) generation circuit (hereafter denoted as MSA-DRV) to enhance the performance and reduce the power consumption of static random-access memory (SRAM)-based IMC. The proposed MSA-DRV performs six logic operations, namely the AND, NAND, OR, NOR, XOR, and XNOR operations, within an SRAM array by using a novel DRV circuit. The DRV circuit enables the voltage threshold to be adaptively changed according to the requirements of different operations. Experimental results indicated that the proposed MSA-DRV had lower computational latency (on average 29.9% lower) and power consumption (on average 30.6% lower) than did a conventional sense amplifier design and reconfigurable assist sense amplifier. Thus, the proposed design can overcome the von Neumann bottleneck to facilitate high-speed, energy-efficient data processing, which is crucial for AI-based and other data-intensive applications.
期刊介绍:
TCAS I publishes regular papers in the field specified by the theory, analysis, design, and practical implementations of circuits, and the application of circuit techniques to systems and to signal processing. Included is the whole spectrum from basic scientific theory to industrial applications. The field of interest covered includes: - Circuits: Analog, Digital and Mixed Signal Circuits and Systems - Nonlinear Circuits and Systems, Integrated Sensors, MEMS and Systems on Chip, Nanoscale Circuits and Systems, Optoelectronic - Circuits and Systems, Power Electronics and Systems - Software for Analog-and-Logic Circuits and Systems - Control aspects of Circuits and Systems.