arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.08403cs.AR
收藏

MENAGE:面向边缘应用的混合信号事件驱动神经形态加速器

MENAGE: Mixed-Signal Event-Driven Neuromorphic Accelerator for Edge Applications

Armin Abdollahi, Mehdi Kamal, Massoud Pedram

AI总结:

本文提出面向边缘应用的混合信号神经形态加速器MENAGE,通过引入虚拟神经元、基于内存的事件控制和ILP映射方法,在CIFAR10-DVS上实现了12.1 TOPS/W的高能效。

摘要:

本文提出了一种混合信号神经形态加速器架构,旨在加速基于事件的神经网络模型的推理。该加速器完全兼容CMOS工艺,利用模拟计算来模拟突触和神经元操作。C2C阶梯结构实现突触,而运算放大器(op-amps)用于实现神经元功能。为提升硬件资源利用率和能效,我们引入了虚拟神经元概念,即利用基于事件的神经形态系统固有的稀疏性,由单个神经元引擎模拟一组模型神经元。此外,我们提出一种基于内存的控制技术来管理各层事件,在提升性能的同时保持支持多种层类型的灵活性。我们还引入一种基于整数线性规划(ILP)的映射方法,用于将模型高效分配到所提加速器上。该加速器是一个通用神经形态平台,能够执行线性和卷积神经网络模型。使用两个专门设计的神经形态加速器和两个基于事件的数据集评估了所提架构的有效性。结果表明,在加速基于CIFAR10-DVS训练的模型时,所提架构实现了12.1 TOPS/W的能效。

英文摘要:

This paper presents a mixed-signal neuromorphic accelerator architecture designed for accelerating inference with event-based neural network models. This fully CMOS-compatible accelerator utilizes analog computing to emulate synapse and neuron operations. A C2C ladder structure implements synapses, while operational amplifiers (op-amps) are used to realize neuron functions. To enhance hardware resource utilization and power efficiency, we introduce the concept of a virtual neuron, where a single neuron engine emulates a set of model neurons, leveraging the sparsity inherent in event-based neuromorphic systems. Additionally, we propose a memory-based control technique to manage events in each layer, which improves performance while maintaining the flexibility to support various layer types. We also introduce an integer linear programming (ILP)-based mapping approach for efficiently allocating the model onto the proposed accelerator. The accelerator is a general-purpose neuromorphic platform capable of executing linear and convolutional neural models. The effectiveness of the proposed architecture is evaluated using two specially designed neuromorphic accelerators and two event-based datasets. The results show that the proposed architecture achieves 12.1 TOPS/W energy efficiency when accelerating a model trained on CIFAR10-DVS.

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。

↑