arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.08070cs.ETcs.ARcs.LGcs.NE
收藏

一种新的以可调权重二元神经元为标准单元的ASIC设计流程

A Novel ASIC Design Flow using Weight-Tunable Binary Neurons as Standard Cells

Arizona State University(亚利桑那州立大学);Texas A&M University(得克萨斯农工大学)

Ankit Wagle, Gian Singh, Sunil Khatri, Sarma Vrudhula

摘要:

在本文中,我们描述了一个混合信号电路的二进制神经元(又名感知器,阈值逻辑门)的设计和自动嵌入ASIC中的细胞的方法。被称为FTL(闪存阈值逻辑)的二进制神经元使用浮置栅极或闪存晶体管,其阈值电压用作神经元的权重的代理。提出了用于将权重映射到闪存晶体管阈值电压的算法。阈值电压的确定是为了最大限度地提高单元的鲁棒性和速度。与传统的CMOS逻辑等效器件相比,单个FTL单元的性能、功耗和面积显着更小(79.4%),功耗更低(61.6%),运行速度更快(40.3%)。还包括的架构和算法编程的闪存设备的FTL。FTL单元被实现为标准单元,并且被设计为允许商业合成和P&R工具在ASIC的合成中自动使用它们。通过FTL单元的自动嵌入,在不牺牲性能的情况下大幅减少了面积和功耗,并在几个ASIC基准测试中得到了证明。本文还演示了如何FTL细胞可用于固定制造后的定时误差。

英文摘要:

In this paper, we describe a design of a mixed signal circuit for a binary neuron (a.k.a perceptron, threshold logic gate) and a methodology for automatically embedding such cells in ASICs. The binary neuron, referred to as an FTL (flash threshold logic) uses floating gate or flash transistors whose threshold voltages serve as a proxy for the weights of the neuron. Algorithms for mapping the weights to the flash transistor threshold voltages are presented. The threshold voltages are determined to maximize both the robustness of the cell and its speed. The performance, power, and area of a single FTL cell are shown to be significantly smaller (79.4%), consume less power (61.6%), and operate faster (40.3%) compared to conventional CMOS logic equivalents. Also included are the architecture and the algorithms to program the flash devices of an FTL. The FTL cells are implemented as standard cells, and are designed to allow commercial synthesis and P&R tools to automatically use them in synthesis of ASICs. Substantial reductions in area and power without sacrificing performance are demonstrated on several ASIC benchmarks by the automatic embedding of FTL cells. The paper also demonstrates how FTL cells can be used for fixing timing errors after fabrication.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑