The early involvement of test and evaluation can significantly reduce the cost of modifying issues and errors found in the later stages of aircraft development and design process.This paper presents a methodology for ...The early involvement of test and evaluation can significantly reduce the cost of modifying issues and errors found in the later stages of aircraft development and design process.This paper presents a methodology for aircraft mission effectiveness evaluation and design space exploration based on Virtual Operational Test(VOT),incorporating Virtual Open Scenario(VOS)and User in Scenarios(UIS)concepts.By employing modeling and simulation technologies in the early stages of aircraft development and design,a virtual environment can be constructed,allowing aircraft users to participate more closely and conveniently in the design process.Virtual tests conducted by users within the mission context provide data on mission effectiveness and critical user feedback.This paper outlines the main components of the virtual operational test process and related conceptual methods,and discusses an open support system framework that supports VOT.The effectiveness and adaptability of the method are demonstrated through two case studies:a beyond-visual-range air combat scenario and a helicopter ground attack scenario.These case studies demonstrate the evaluation of aircraft mission effectiveness and the sensitivity analysis and optimization of design and operational parameters based on VOT.展开更多
With the increasing demand of computational power in artificial intelligence(AI)algorithms,dedicated accelerators have become a necessity.However,the complexity of hardware architectures,vast design search space,and c...With the increasing demand of computational power in artificial intelligence(AI)algorithms,dedicated accelerators have become a necessity.However,the complexity of hardware architectures,vast design search space,and complex tasks of accelerators have posed significant challenges.Tra-ditional search methods can become prohibitively slow if the search space continues to be expanded.A design space exploration(DSE)method is proposed based on transfer learning,which reduces the time for repeated training and uses multi-task models for different tasks on the same processor.The proposed method accurately predicts the latency and energy consumption associated with neural net-work accelerator design parameters,enabling faster identification of optimal outcomes compared with traditional methods.And compared with other DSE methods by using multilayer perceptron(MLP),the required training time is shorter.Comparative experiments with other methods demonstrate that the proposed method improves the efficiency of DSE without compromising the accuracy of the re-sults.展开更多
Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip （MPSoC）. Tasks of the applications need to be mapped on the MPSoC resources efficiently i...Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip （MPSoC）. Tasks of the applications need to be mapped on the MPSoC resources efficiently in order to satisity their performance constraints. Exploring all the possible mappings, i.e., tasks to resources combinations exhaustively may take days or weeks. Additionally, the exploration is performed at design-time, which cannot handle dynamism in applications and resources＇ status. A runtime mapping technique can cater for the dynamism but cannot guarantee for strict timing deadlines due to large computations involved at run-time. Thus, an approach performing feasible compute intensive exploration at design-time and using the explored results at run-time is required. This paper presents a solution in the same direction. Communicationaware design space exploration （CADSE） techniques have been proposed to explore different mapping options to be selected at run-time subject to desired performance and available MPSoC resources. Experiments show that the proposed techniques for exploration are faster over an exhaustive exploration and provides almost the same quality of results.展开更多
Supporting designers in making effective renovation decisions is urgently needed to address the ever-growing climate crisis.This requires developing tools that bring insight into the enormous set of design options at ...Supporting designers in making effective renovation decisions is urgently needed to address the ever-growing climate crisis.This requires developing tools that bring insight into the enormous set of design options at hand,where the efficacy of candidate renovation design options is evaluated using(potentially computationally expensive)simulations.Thus,a systematic,goal-driven design process is required that ensures“design space”diversity and coverage,while making careful and effective use of highly informative but time consuming performance simulations.To this end,we define twelve new concepts based on scenario(dis)similarity that give designers insight about pairs of scenarios,clusters of scenarios,and pairs of clusters,and apply these concepts in an iterative,goal-driven design process.We evaluate a software implementation of our design concept analyser using a real renovation case of a large residential building in Denmark.展开更多
Deep learning has gained superior accuracy on Euclidean structure data in neural networks.As a result,nonEuclidean structure data,such as graph data,has more sophisticated structural information,which can be applied i...Deep learning has gained superior accuracy on Euclidean structure data in neural networks.As a result,nonEuclidean structure data,such as graph data,has more sophisticated structural information,which can be applied in neural networks as well to address more complex and practical problems.However,actual graph data obeys a power-law distribution,so the adjacent matrix of a graph is random and sparse.Graph processing accelerator(GPA)is designed to handle the problems above.However,graph computing only processes 1-dimensional data.In graph neural networks(GNNs),graph data is multi-dimensional.Consequently,GNNs include the execution processes of both traditional graph processing and neural network,which have irregular memory access and regular computation,respectively.To obtain more information in graph data and require better model generalization ability,the layers of GNN are deeper,so the overhead of memory access and computation is considerable.At present,GNN accelerators are designed to deal with this issue.In this paper,we conduct a systematic survey regarding the design and implementation of GNN accelerators.Specifically,we review the challenges faced by GNN accelerators,and existing related works in detail to process them.Finally,we evaluate previous works and propose future directions in this booming field.展开更多
文摘The early involvement of test and evaluation can significantly reduce the cost of modifying issues and errors found in the later stages of aircraft development and design process.This paper presents a methodology for aircraft mission effectiveness evaluation and design space exploration based on Virtual Operational Test(VOT),incorporating Virtual Open Scenario(VOS)and User in Scenarios(UIS)concepts.By employing modeling and simulation technologies in the early stages of aircraft development and design,a virtual environment can be constructed,allowing aircraft users to participate more closely and conveniently in the design process.Virtual tests conducted by users within the mission context provide data on mission effectiveness and critical user feedback.This paper outlines the main components of the virtual operational test process and related conceptual methods,and discusses an open support system framework that supports VOT.The effectiveness and adaptability of the method are demonstrated through two case studies:a beyond-visual-range air combat scenario and a helicopter ground attack scenario.These case studies demonstrate the evaluation of aircraft mission effectiveness and the sensitivity analysis and optimization of design and operational parameters based on VOT.
基金the National Key R&D Program of China(No.2018AAA0103300)the National Natural Science Foundation of China(No.61925208,U20A20227,U22A2028)+1 种基金the Chinese Academy of Sciences Project for Young Scientists in Basic Research(No.YSBR-029)the Youth Innovation Promotion Association Chinese Academy of Sciences.
文摘With the increasing demand of computational power in artificial intelligence(AI)algorithms,dedicated accelerators have become a necessity.However,the complexity of hardware architectures,vast design search space,and complex tasks of accelerators have posed significant challenges.Tra-ditional search methods can become prohibitively slow if the search space continues to be expanded.A design space exploration(DSE)method is proposed based on transfer learning,which reduces the time for repeated training and uses multi-task models for different tasks on the same processor.The proposed method accurately predicts the latency and energy consumption associated with neural net-work accelerator design parameters,enabling faster identification of optimal outcomes compared with traditional methods.And compared with other DSE methods by using multilayer perceptron(MLP),the required training time is shorter.Comparative experiments with other methods demonstrate that the proposed method improves the efficiency of DSE without compromising the accuracy of the re-sults.
基金The authors would like to thank the reviewers for their feedback and suggestions. We also wish to mention that this work is partly supported by Singapore Ministry of Education Academic Research Fund Tier 1 （R-263-000-655-133） and National Natural Science Foundation of China （NSFC） （Grant No. 61173032）.
文摘Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip （MPSoC）. Tasks of the applications need to be mapped on the MPSoC resources efficiently in order to satisity their performance constraints. Exploring all the possible mappings, i.e., tasks to resources combinations exhaustively may take days or weeks. Additionally, the exploration is performed at design-time, which cannot handle dynamism in applications and resources＇ status. A runtime mapping technique can cater for the dynamism but cannot guarantee for strict timing deadlines due to large computations involved at run-time. Thus, an approach performing feasible compute intensive exploration at design-time and using the explored results at run-time is required. This paper presents a solution in the same direction. Communicationaware design space exploration （CADSE） techniques have been proposed to explore different mapping options to be selected at run-time subject to desired performance and available MPSoC resources. Experiments show that the proposed techniques for exploration are faster over an exhaustive exploration and provides almost the same quality of results.
基金supported by the European Union Horizon 2020 research project PROBONO under grant agreement no.101037075.
文摘Supporting designers in making effective renovation decisions is urgently needed to address the ever-growing climate crisis.This requires developing tools that bring insight into the enormous set of design options at hand,where the efficacy of candidate renovation design options is evaluated using(potentially computationally expensive)simulations.Thus,a systematic,goal-driven design process is required that ensures“design space”diversity and coverage,while making careful and effective use of highly informative but time consuming performance simulations.To this end,we define twelve new concepts based on scenario(dis)similarity that give designers insight about pairs of scenarios,clusters of scenarios,and pairs of clusters,and apply these concepts in an iterative,goal-driven design process.We evaluate a software implementation of our design concept analyser using a real renovation case of a large residential building in Denmark.
基金supported by the National Natural Science Foundation of China(Grant Nos.62032001 and 61972407).
文摘Deep learning has gained superior accuracy on Euclidean structure data in neural networks.As a result,nonEuclidean structure data,such as graph data,has more sophisticated structural information,which can be applied in neural networks as well to address more complex and practical problems.However,actual graph data obeys a power-law distribution,so the adjacent matrix of a graph is random and sparse.Graph processing accelerator(GPA)is designed to handle the problems above.However,graph computing only processes 1-dimensional data.In graph neural networks(GNNs),graph data is multi-dimensional.Consequently,GNNs include the execution processes of both traditional graph processing and neural network,which have irregular memory access and regular computation,respectively.To obtain more information in graph data and require better model generalization ability,the layers of GNN are deeper,so the overhead of memory access and computation is considerable.At present,GNN accelerators are designed to deal with this issue.In this paper,we conduct a systematic survey regarding the design and implementation of GNN accelerators.Specifically,we review the challenges faced by GNN accelerators,and existing related works in detail to process them.Finally,we evaluate previous works and propose future directions in this booming field.
