当前位置: X-MOL 学术arXiv.cs.ET › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
RANC: Reconfigurable Architecture for Neuromorphic Computing
arXiv - CS - Emerging Technologies Pub Date : 2020-11-01 , DOI: arxiv-2011.00624
Joshua Mack, Ruben Purdy, Kris Rockowitz, Michael Inouye, Edward Richter, Spencer Valancius, Nirmal Kumbhare, Md Sahil Hassan, Kaitlin Fair, John Mixter, Ali Akoglu

Neuromorphic architectures have been introduced as platforms for energy efficient spiking neural network execution. The massive parallelism offered by these architectures has also triggered interest from non-machine learning application domains. In order to lift the barriers to entry for hardware designers and application developers we present RANC: a Reconfigurable Architecture for Neuromorphic Computing, an open-source highly flexible ecosystem that enables rapid experimentation with neuromorphic architectures in both software via C++ simulation and hardware via FPGA emulation. We present the utility of the RANC ecosystem by showing its ability to recreate behavior of the IBM's TrueNorth and validate with direct comparison to IBM's Compass simulation environment and published literature. RANC allows optimizing architectures based on application insights as well as prototyping future neuromorphic architectures that can support new classes of applications entirely. We demonstrate the highly parameterized and configurable nature of RANC by studying the impact of architectural changes on improving application mapping efficiency with quantitative analysis based on Alveo U250 FPGA. We present post routing resource usage and throughput analysis across implementations of Synthetic Aperture Radar classification and Vector Matrix Multiplication applications, and demonstrate a neuromorphic architecture that scales to emulating 259K distinct neurons and 73.3M distinct synapses.

中文翻译:

RANC:神经形态计算的可重构架构

神经形态架构已被引入作为节能尖峰神经网络执行的平台。这些架构提供的大规模并行性也引发了非机器学习应用领域的兴趣。为了提高硬件设计人员和应用程序开发人员的准入门槛,我们推出了 RANC:神经拟态计算的可重构架构,这是一个开源的高度灵活的生态系统,可以通过 C++ 仿真在软件和通过 FPGA 仿真的硬件中对神经拟态架构进行快速实验. 我们展示了 RANC 生态系统的效用,展示了其重新创建 IBM TrueNorth 行为的能力,并通过与 IBM Compass 模拟环境和已发表文献的直接比较进行验证。RANC 允许基于应用程序洞察优化架构,以及对可以完全支持新应用程序类别的未来神经形态架构进行原型设计。我们通过基于 Alveo U250 FPGA 的定量分析研究架构变化对提高应用程序映射效率的影响,证明了 RANC 的高度参数化和可配置性。我们展示了合成孔径雷达分类和向量矩阵乘法应用程序的路由后资源使用情况和吞吐量分析,并展示了一种神经形态架构,可扩展到模拟 259K 不同神经元和 73.3M 不同突触。我们通过基于 Alveo U250 FPGA 的定量分析研究架构变化对提高应用程序映射效率的影响,证明了 RANC 的高度参数化和可配置性。我们展示了合成孔径雷达分类和向量矩阵乘法应用程序的路由后资源使用情况和吞吐量分析,并展示了一种神经形态架构,可扩展到模拟 259K 不同神经元和 73.3M 不同突触。我们通过基于 Alveo U250 FPGA 的定量分析研究架构变化对提高应用程序映射效率的影响,证明了 RANC 的高度参数化和可配置性。我们展示了合成孔径雷达分类和向量矩阵乘法应用程序的路由后资源使用情况和吞吐量分析,并展示了一种神经形态架构,可扩展到模拟 259K 不同神经元和 73.3M 不同突触。
更新日期:2020-11-03
down
wechat
bug