As a large amount of data is increasingly generated from edge devices,such as smart homes,mobile phones,and wearable devices,it becomes crucial for many applications to deploy machine learning modes across edge device...As a large amount of data is increasingly generated from edge devices,such as smart homes,mobile phones,and wearable devices,it becomes crucial for many applications to deploy machine learning modes across edge devices.The execution speed of the deployed model is a key element to ensure service quality.Considering a highly heterogeneous edge deployment scenario,deep learning compiling is a novel approach that aims to solve this problem.It defines models using certain DSLs and generates efficient code implementations on different hardware devices.However,there are still two aspects that are not yet thoroughly investigated yet.The first is the optimization of memory-intensive operations,and the second problem is the heterogeneity of the deployment target.To that end,in this work,we propose a system solution that optimizes memory-intensive operation,optimizes the subgraph distribution,and enables the compiling and deployment of DNN models on multiple targets.The evaluation results show the performance of our proposed system.展开更多
Mobile cloud computing（MCC） combines mobile Internet and cloud computing to improve the performance of mobile applications. However, MCC faces the problem of energy efficiency because of randomly varying channels. A...Mobile cloud computing（MCC） combines mobile Internet and cloud computing to improve the performance of mobile applications. However, MCC faces the problem of energy efficiency because of randomly varying channels. A scheduling algorithm is proposed by introducing the Lyapunov optimization, which can dynamically choose users to transmit data based on queue backlog and channel statistics. The Lyapunov analysis shows that the proposed scheduling algorithm can make a tradeoff between queue backlog and energy consumption in the channel-aware mobile cloud computing system. The simulation results verify the effectiveness of the proposed algorithm.展开更多
基金supported by the National Natural Science Foundation of China(U21A20519)。
文摘As a large amount of data is increasingly generated from edge devices,such as smart homes,mobile phones,and wearable devices,it becomes crucial for many applications to deploy machine learning modes across edge devices.The execution speed of the deployed model is a key element to ensure service quality.Considering a highly heterogeneous edge deployment scenario,deep learning compiling is a novel approach that aims to solve this problem.It defines models using certain DSLs and generates efficient code implementations on different hardware devices.However,there are still two aspects that are not yet thoroughly investigated yet.The first is the optimization of memory-intensive operations,and the second problem is the heterogeneity of the deployment target.To that end,in this work,we propose a system solution that optimizes memory-intensive operation,optimizes the subgraph distribution,and enables the compiling and deployment of DNN models on multiple targets.The evaluation results show the performance of our proposed system.
基金supported by the National Natural Science Foundation of China(61173017)the National High Technology Research and Development Program(863 Program)(2014AA01A701)
文摘Mobile cloud computing（MCC） combines mobile Internet and cloud computing to improve the performance of mobile applications. However, MCC faces the problem of energy efficiency because of randomly varying channels. A scheduling algorithm is proposed by introducing the Lyapunov optimization, which can dynamically choose users to transmit data based on queue backlog and channel statistics. The Lyapunov analysis shows that the proposed scheduling algorithm can make a tradeoff between queue backlog and energy consumption in the channel-aware mobile cloud computing system. The simulation results verify the effectiveness of the proposed algorithm.
