相关实验视频

Updated: Sep 15, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

存储器内存对象检测,使用128 Mb的C-Doped Ge2Sb2Te5PCM芯片进行检测

Chenchen Xie¹, Yuqi Li², Longhao Yan²

¹State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, 200050, China.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)

|July 17, 2025

概括

这项研究引入了一种新的内存内存计算系统,用于高效的对象检测. 与传统的GPU相比,该系统显著提高了计算机视觉任务的能源效率和计算吞吐量.

科学领域:

计算机视觉计算机视觉
材料科学材料科学材料科学
电气工程电气工程

背景情况:

传统的边缘计算与现代物体检测模型的计算需求作斗争.
最先进的对象检测需要大量的计算能力和内存,限制了边缘设备的功能.

研究的目的:

开发一种高效的内存计算系统,使用相变内存进行对象检测.
为边缘AI解决传统计算平台的局限性.

主要方法:

制造一个128 Mb的相变内存芯片.
实现内存向量矩阵乘法和最大计算.
采用混合精度重量映射策略,以减少能源消耗和对高精度模拟数字转换器 (ADC) 的依赖.

主要成果:

在40nm节点中实现了99.99999%的内存产量.
在相应的网络性能下,ADC能耗降低了高达22.3×.
与GPU实现相比,展示了4,180倍更高的能源效率和228倍更大的计算吞吐量.

结论:

记忆内存计算为边缘对象检测提供了高效的解决方案.
开发的系统在能源效率和速度方面明显超过了GPU性能.
混合精度策略对于优化内存计算操作至关重要.

关键词:

在内存计算中的计算.混合精度精度混合精度精度精度对象检测检测对象检测对象检测阶段变化记忆的阶段变化记忆

更多相关视频

Gradient Echo Quantum Memory in Warm Atomic Vapor

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

相关概念视频

Understanding Memory

Understanding Memory

Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...