New compute-in-memory macro boosts edge AI inference efficiency

Researchers have developed E-ReCON, a novel compute-in-memory (CIM) macro designed for efficient AI inference on edge devices. This macro utilizes a compact ReRAM bitcell capable of performing multiplication for both conventional neural networks and spiking neural networks. The design incorporates an interleaved adder tree to reduce transistor count and power consumption, achieving high energy efficiency and low latency. AI

影响 This new compute-in-memory macro could enable more powerful and energy-efficient AI processing directly on edge devices.

排序理由 The cluster contains a research paper detailing a new hardware macro for AI inference. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• AlexNet
• CNN
• E-ReCON
• LeNet-5
• ReRAM
• ResNet-18
• VGG-16
• VGG-8

• 论文
• 基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →