Hierarchical Network Partitioning for Reconfigurable Large-Scale Neuromorphic Systems
2021 International Conference on Rebooting Computing (ICRC)(2021)
摘要
We present an efficient and scalable partitioning method for mapping large-scale neural network models to reconfigurable neuromorphic hardware. The partitioning framework is optimized for compute-balanced, memory -efficient parallel processing targeting low-latency execution and dense synaptic storage, with minimal routing across various compute cores. We demonstrate highly scalable and efficient ...
更多查看译文
关键词
Neuromorphics,Computational modeling,Neural networks,Memory management,Parallel processing,Routing,Hardware
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要