• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

用于布尔逻辑和搜索操作的双向且操作数可控的内存计算,采用行和列方向的静态随机存取存储器(RC-SRAM)。

Bi-Directional and Operand-Controllable In-Memory Computing for Boolean Logic and Search Operations with Row and Column Directional SRAM (RC-SRAM).

作者信息

Xiao Han, Zhao Ruiyong, Liu Yulan, Liu Yuanzhen, Chen Jing

机构信息

Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200031, China.

University of Chinese Academy of Sciences, Beijing 100049, China.

出版信息

Micromachines (Basel). 2024 Aug 22;15(8):1056. doi: 10.3390/mi15081056.

DOI:10.3390/mi15081056
PMID:39203707
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11356308/
Abstract

The von Neumann architecture is no longer sufficient for handling large-scale data. In-memory computing has emerged as the potent method for breaking through the memory bottleneck. A new 10T SRAM bitcell with row and column control lines called RC-SRAM is proposed in this article. The architecture based on RC-SRAM can achieve bi-directional and operand-controllable logic-in-memory and search operations through different signal configurations, which can comprehensively respond to various occasions and needs. Moreover, we propose threshold-controlled logic gates for sensing, which effectively reduces the circuit area and improves accuracy. We validate the RC-SRAM with a 28 nm CMOS technology, and the results show that the circuits are not only full featured and flexible for customization but also have a significant increase in the working frequency. At VDD = 0.9 V and T = 25 °C, the bi-directional search frequency is up to 775 MHz and 567 MHz, and the speeds for row and column Boolean logic reach 759 MHz and 683 MHz.

摘要

冯·诺依曼架构已不足以处理大规模数据。内存计算作为突破内存瓶颈的有效方法应运而生。本文提出了一种具有行和列控制线的新型10T SRAM存储单元,称为RC-SRAM。基于RC-SRAM的架构可通过不同的信号配置实现双向和操作数可控的内存逻辑及搜索操作,能全面应对各种场合和需求。此外,我们提出了用于传感的阈值控制逻辑门,有效减小了电路面积并提高了精度。我们采用28纳米CMOS技术对RC-SRAM进行了验证,结果表明这些电路不仅功能齐全且便于定制,工作频率也有显著提高。在VDD = 0.9 V和T = 25 °C时,双向搜索频率高达775 MHz和567 MHz,行和列布尔逻辑的速度分别达到759 MHz和683 MHz。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/4a99967635c2/micromachines-15-01056-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/00e4217d66cb/micromachines-15-01056-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a8b1dd9b0058/micromachines-15-01056-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/1a4af6187903/micromachines-15-01056-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/87ea4830fdd5/micromachines-15-01056-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a2b608a74c59/micromachines-15-01056-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/98eda42bf396/micromachines-15-01056-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/ce1f5132c1b9/micromachines-15-01056-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/8f9ab430eb72/micromachines-15-01056-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/0606051dc074/micromachines-15-01056-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a0c7cc0bd42e/micromachines-15-01056-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/42775d79b268/micromachines-15-01056-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/44354872ba3d/micromachines-15-01056-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/1e48ae93ccd5/micromachines-15-01056-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/6ff8512afaa8/micromachines-15-01056-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/4c9694d91e39/micromachines-15-01056-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/4a99967635c2/micromachines-15-01056-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/00e4217d66cb/micromachines-15-01056-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a8b1dd9b0058/micromachines-15-01056-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/1a4af6187903/micromachines-15-01056-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/87ea4830fdd5/micromachines-15-01056-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a2b608a74c59/micromachines-15-01056-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/98eda42bf396/micromachines-15-01056-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/ce1f5132c1b9/micromachines-15-01056-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/8f9ab430eb72/micromachines-15-01056-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/0606051dc074/micromachines-15-01056-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/a0c7cc0bd42e/micromachines-15-01056-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/42775d79b268/micromachines-15-01056-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/44354872ba3d/micromachines-15-01056-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/1e48ae93ccd5/micromachines-15-01056-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/6ff8512afaa8/micromachines-15-01056-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/4c9694d91e39/micromachines-15-01056-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3ec4/11356308/4a99967635c2/micromachines-15-01056-g017.jpg

相似文献

1
Bi-Directional and Operand-Controllable In-Memory Computing for Boolean Logic and Search Operations with Row and Column Directional SRAM (RC-SRAM).用于布尔逻辑和搜索操作的双向且操作数可控的内存计算,采用行和列方向的静态随机存取存储器(RC-SRAM)。
Micromachines (Basel). 2024 Aug 22;15(8):1056. doi: 10.3390/mi15081056.
2
DAM SRAM CORE: An Efficient High-Speed and Low-Power CIM SRAM CORE Design for Feature Extraction Convolutional Layers in Binary Neural Networks.DAM SRAM核心:一种用于二进制神经网络中特征提取卷积层的高效高速低功耗CIM SRAM核心设计。
Micromachines (Basel). 2024 Apr 30;15(5):617. doi: 10.3390/mi15050617.
3
Multifunctional computing-in-memory SRAM cells based on two-surface-channel MoS transistors.基于双表面沟道MoS晶体管的多功能内存计算SRAM单元。
iScience. 2021 Sep 16;24(10):103138. doi: 10.1016/j.isci.2021.103138. eCollection 2021 Oct 22.
4
Multi-Input Logic-in-Memory for Ultra-Low Power Non-Von Neumann Computing.用于超低功耗非冯·诺依曼计算的多输入内存逻辑
Micromachines (Basel). 2021 Oct 14;12(10):1243. doi: 10.3390/mi12101243.
5
FinFET 6T-SRAM All-Digital Compute-in-Memory for Artificial Intelligence Applications: An Overview and Analysis.用于人工智能应用的FinFET 6T-SRAM全数字内存计算:概述与分析
Micromachines (Basel). 2023 Jul 31;14(8):1535. doi: 10.3390/mi14081535.
6
A RRAM Integrated 4T SRAM with Self-Inhibit Resistive Switching Load by Pure CMOS Logic Process.一种采用纯CMOS逻辑工艺的具有自抑制电阻切换负载的RRAM集成4T SRAM。
Nanoscale Res Lett. 2017 Dec;12(1):418. doi: 10.1186/s11671-017-2191-9. Epub 2017 Jun 15.
7
A High-Precision Voltage-Quantization-Based Current-Mode Computing-in-Memory SRAM.一种基于高精度电压量化的电流模式内存计算SRAM。
Micromachines (Basel). 2023 Nov 29;14(12):2180. doi: 10.3390/mi14122180.
8
In-Memory Logic Operations and Neuromorphic Computing in Non-Volatile Random Access Memory.非易失性随机存取存储器中的内存逻辑运算与神经形态计算
Materials (Basel). 2020 Aug 10;13(16):3532. doi: 10.3390/ma13163532.
9
A 0.3 V PNN Based 10T SRAM with Pulse Control Based Read-Assist and Write Data-Aware Schemes for Low Power Applications.一种基于0.3V脉冲神经网络的10T静态随机存取存储器,采用基于脉冲控制的读辅助和写数据感知方案,用于低功耗应用。
Sensors (Basel). 2021 Oct 2;21(19):6591. doi: 10.3390/s21196591.
10
Content-Addressable Memories and Transformable Logic Circuits Based on Ferroelectric Reconfigurable Transistors for In-Memory Computing.基于铁电可重构晶体管的内容可寻址存储器及用于内存计算的可变换逻辑电路
ACS Nano. 2024 Jan 30;18(4):2763-2771. doi: 10.1021/acsnano.3c03900. Epub 2024 Jan 17.