翼动芯生

行动起来，活在当下

累计撰写 16 篇文章
累计创建 10 个标签
累计收到 0 条评论

目录CONTENT

最新文章

2020-09-01
置顶导师简介潘彪的个人简介
- 2020-09-01
- 886
- 0
- 15
2024-12-19
衡山芯片衡山芯片规格数据
- 2024-12-19
- 101
- 0
- 0
2024-12-19
嵩山芯片嵩山芯片规格数据
- 2024-12-19
- 45
- 0
- 0
2024-12-16
A Mini Tutorial of Processing in Memory: From Principles, Devices to Prototypes 文章围绕存内计算（Processing in Memory, PIM）系统性地探讨了其基本原理、不同存储设备在PIM中的应用以及近年来的典型开发成果。随着大数据应用的快速增长，传统冯·诺依曼架构在处理数据传输时效率低下，导致能耗增加和性能瓶颈。为解决这一问题，PIM技术通过直接在存储器中执行计算，减
- 2024-12-16
- 40
- 0
- 0
2024-12-12
PipeCIM: 基于嵌套流水线和扩展RISC-V指令的高吞吐量内存计算微处理器 PipeCIM: A High-ThroughputComputing-In-Memory Microprocessor With Nested Pipeline and RISC-VExtended Instructions 引言背景与挑战卷积神经网络（CNN）在图像分类、语音识别等领域应用广
- 2024-12-12
- 43
- 0
- 0
2024-12-12
DS-CIM: 面向尖峰神经网络的40nm异步双脉冲驱动MRAM内存计算宏单元 DS-CIM: A 40nm Asynchronous Dual-SpikeDriven, MRAM Compute-In-MemoryMacro for Spiking Neural Network 引言研究背景物联网（IoT）设备的普及对边缘计算提出了低能耗、高吞吐量的需求。传统冯诺依曼架
- 2024-12-12
- 18
- 0
- 0
2024-12-12
Spin-Torque Memristors Based on Perpendicular MagneticTunnel Junctions for Neuromorphic Computing Spin-Torque Memristors Based on Perpendicular MagneticTunnel Junctions for Neuromorphic Computing(Advanced Science) 忆阻器作为神经形态计算的关键器件，传统器件通常依赖离子运动，存在寿命
- 2024-12-12
- 17
- 0
- 0
2024-12-02
RDCIM:基于RISC-V的数字存算一体处理器，具有高能效和低面积开销 RDCIM: RISC-V Supported Full-Digital Computing-in-Memory Processor With High Energy Efficiency and Low Area Overhead （TCAS-I）本文介绍一种支持 RISC-V 指令集的数字存算
- 2024-12-02
- 76
- 0
- 0
2024-12-02
基于40nm eFlash的IMC SoC的端到端内存计算系统：电路、工具链和系统协同设计框架 An End-to-End In-Memory Computing System Based on a 40-nm eFlash-Based IMC SoC: Circuits, Toolchains, and Systems Co-Design Framework（TCAD 2024）研究背景
- 2024-12-02
- 30
- 0
- 0
2024-11-29
A Survey of MRAM-Centric Computing: From Near Memory to In Memory
- 2024-11-29
- 54
- 0
- 1

1
2