In recent years,human-cyber-physical systems(HCPSs)have become increasingly complex due to the widespread adoption of environmental sensing and behavioral adaption.Apart from the tight coupling between application log...In recent years,human-cyber-physical systems(HCPSs)have become increasingly complex due to the widespread adoption of environmental sensing and behavioral adaption.Apart from the tight coupling between application logic and sensing-adaptation modules,such applications are mainly constrained by erroneous sensing and abnormal adaptation issues,often resulting in misjudgment of scenarios or adaptation behaviors that deviate from intended goals.Reliability in constructing and maintaining such application systems faces significant challenges,especially as human-cyber-physical scenarios exhibit dynamic uncertainties and evolving requirements,further exacerbating the development difficulty.To address these challenges,we design and implement SEPAL,a consistency-driven programming framework and runtime support for HCPSs with reliable environmental sensing and dynamic adaptation.SEPAL simplifies the design of environmental sensing and behavioral adaption in HCPSs through a unified programming framework,and transparently manages the reliability of sensing and the unbiasedness of adaptation through its two built-in consistency-based services.SEPAL also provides a flexible browser-based management interface and a customizable interface design language for ease of usage.Case studies and evaluations demonstrate SEPAL’s facilitation of reliable support for various HCPSs,as well as the effectiveness and efficiency of environmental sensing and behavioral adaption capabilities.展开更多
Peta-scale high-perfomlance computing systems are increasingly built with heterogeneous CPU and GPU nodes to achieve higher power efficiency and computation throughput. While providing unprecedented capabilities to co...Peta-scale high-perfomlance computing systems are increasingly built with heterogeneous CPU and GPU nodes to achieve higher power efficiency and computation throughput. While providing unprecedented capabilities to conduct computational experiments of historic significance, these systems are presently difficult to program. The users, who are domain experts rather than computer experts, prefer to use programming models closer to their domains （e.g., physics and biology） rather than MPI and OpenME This has led the development of domain-specific programming that provides domain-specific programming interfaces but abstracts away some performance-critical architecture details. Based on experience in designing large-scale computing systems, a hybrid programming framework for scientific computing on heterogeneous architectures is proposed in this work. Its design philosophy is to provide a collaborative mechanism for domain experts and computer experts so that both domain-specific knowledge and performance-critical architecture details can be adequately exploited. Two real-world scientific applications have been evaluated on TH-IA, a peta-scale CPU-GPU heterogeneous system that is currently the 5th fastest supercomputer in the world. The experimental results show that the proposed framework is well suited for developing large-scale scientific computing applications on peta-scale heterogeneous CPU/GPU systems.展开更多
基金supported by the National Key Research and Development Program of China under Grant No.2022YFB4501801the National Natural Science Foundation of China under Grant Nos.62302209 and 62472210+1 种基金the Leading-Edge Technology Program of Jiangsu Natural Science Foundation under Grant No.BK20202001support from the Collaborative Innovation Center of Novel Software Technology and Industrialization,Jiangsu,China.
文摘In recent years,human-cyber-physical systems(HCPSs)have become increasingly complex due to the widespread adoption of environmental sensing and behavioral adaption.Apart from the tight coupling between application logic and sensing-adaptation modules,such applications are mainly constrained by erroneous sensing and abnormal adaptation issues,often resulting in misjudgment of scenarios or adaptation behaviors that deviate from intended goals.Reliability in constructing and maintaining such application systems faces significant challenges,especially as human-cyber-physical scenarios exhibit dynamic uncertainties and evolving requirements,further exacerbating the development difficulty.To address these challenges,we design and implement SEPAL,a consistency-driven programming framework and runtime support for HCPSs with reliable environmental sensing and dynamic adaptation.SEPAL simplifies the design of environmental sensing and behavioral adaption in HCPSs through a unified programming framework,and transparently manages the reliability of sensing and the unbiasedness of adaptation through its two built-in consistency-based services.SEPAL also provides a flexible browser-based management interface and a customizable interface design language for ease of usage.Case studies and evaluations demonstrate SEPAL’s facilitation of reliable support for various HCPSs,as well as the effectiveness and efficiency of environmental sensing and behavioral adaption capabilities.
基金Project(61170049) supported by the National Natural Science Foundation of ChinaProject(2012AA010903) supported by the National High Technology Research and Development Program of China
文摘Peta-scale high-perfomlance computing systems are increasingly built with heterogeneous CPU and GPU nodes to achieve higher power efficiency and computation throughput. While providing unprecedented capabilities to conduct computational experiments of historic significance, these systems are presently difficult to program. The users, who are domain experts rather than computer experts, prefer to use programming models closer to their domains （e.g., physics and biology） rather than MPI and OpenME This has led the development of domain-specific programming that provides domain-specific programming interfaces but abstracts away some performance-critical architecture details. Based on experience in designing large-scale computing systems, a hybrid programming framework for scientific computing on heterogeneous architectures is proposed in this work. Its design philosophy is to provide a collaborative mechanism for domain experts and computer experts so that both domain-specific knowledge and performance-critical architecture details can be adequately exploited. Two real-world scientific applications have been evaluated on TH-IA, a peta-scale CPU-GPU heterogeneous system that is currently the 5th fastest supercomputer in the world. The experimental results show that the proposed framework is well suited for developing large-scale scientific computing applications on peta-scale heterogeneous CPU/GPU systems.
