典型文献
Tetris:A Heuristic Static Memory Management Framework for Uniform Memory Multicore Neural Network Accelerators
文献摘要：
Uniform memory multicore neural network accelerators(UNNAs)furnish huge computing power to emerging neural network applications.Meanwhile,with neural network architectures going deeper and wider,the limited memory capacity has become a constraint to deploy models on UNNA platforms.Therefore how to efficiently manage memory space and how to reduce workload footprints are urgently significant.In this paper,we propose Tetris:a heuristic static memory management framework for UNNA platforms.Tetris reconstructs execution flows and synchronization relationships among cores to analyze each tensor's liveness interval.Then the memory management problem is converted to a sequence per-mutation problem.Tetris uses a genetic algorithm to explore the permutation space to optimize the memory management strategy and reduce memory footprints.We evaluate several typical neural networks and the experimental results demon-strate that Tetris outperforms the state-of-the-art memory allocation methods,and achieves an average memory reduction ratio of 91.9％and 87.9％for a quad-core and a 16-core Cambricon-X platform,respectively.
文献关键词：
中图分类号：
作者姓名：
Xiao-Bing Chen;Hao Qi;Shao-Hui Peng;Yi-Min Zhuang;Tian Zhi;Yun-Ji Chen
作者机构：
State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China;School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China;Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology,Shanghai 200031 China
文献出处：
引用格式：
[1]Xiao-Bing Chen;Hao Qi;Shao-Hui Peng;Yi-Min Zhuang;Tian Zhi;Yun-Ji Chen-.Tetris:A Heuristic Static Memory Management Framework for Uniform Memory Multicore Neural Network Accelerators)[J].计算机科学技术学报（英文版）,2022(06):1255-1270
A类：
Tetris,Multicore,Accelerators,UNNAs,UNNA,Cambricon
B类：
Heuristic,Static,Memory,Management,Framework,Uniform,Neural,Network,memory,multicore,neural,accelerators,furnish,huge,computing,power,emerging,applications,Meanwhile,architectures,going,deeper,wider,limited,capacity,has,become,constraint,deploy,models,platforms,Therefore,how,efficiently,space,reduce,workload,footprints,are,urgently,significant,In,this,paper,propose,heuristic,static,management,framework,reconstructs,execution,flows,synchronization,relationships,among,cores,analyze,each,tensor,liveness,interval,Then,problem,converted,sequence,uses,genetic,algorithm,explore,permutation,optimize,strategy,We,evaluate,several,typical,networks,experimental,results,demon,that,outperforms,state,art,allocation,methods,achieves,average,reduction,ratio,quad,respectively
AB值：
0.591047
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
