The most popular hardware used for parallel depth migration is the PC-Cluster but its application is limited due to large space occupation and high power consumption. In this paper, we introduce a new hardware archite...The most popular hardware used for parallel depth migration is the PC-Cluster but its application is limited due to large space occupation and high power consumption. In this paper, we introduce a new hardware architecture, based on which the finite difference （FD） wavefield-continuation depth migration can be conducted using the Graphics Processing Unit （GPU） as a CPU coprocessor. We demonstrate the program module and three key optimization steps for implementing FD depth migration： memory, thread structure, and instruction optimizations and consider evaluation methods for the amount of optimization. 2D and 3D models are used to test depth migration on the GPU. The tested results show that the depth migration computational efficiency greatly increased using the general-purpose GPU, increasing by at least 25 times compared to the AMD 2.5 GHz CPU.展开更多
This paper puts forward sharing teaching resources based on cloud computing solutions, through the use of architecture means virtualization technology based on KVM on the server side, the infrastructure layer manage t...This paper puts forward sharing teaching resources based on cloud computing solutions, through the use of architecture means virtualization technology based on KVM on the server side, the infrastructure layer manage the underlying physical hardware equipment. In the realization of the infrastructure layer using Libvirt virtualization management suite that provides a common API development Web, through the RDP protocol, and finally access to the remote virtual desktop browser by the graphical user interface （GUI） and traditional Web B/S architecture, to simulate and access to low-level resources and sharing of teaching resources, teaching resources can be achieved education informatization in the process of teaching.展开更多
The three-dimensional discontinuous deformation analysis(3D-DDA) is a promising numerical method for both static and dynamic analyses of rock systems. Lacking mature software, its popularity is far behind its ability....The three-dimensional discontinuous deformation analysis(3D-DDA) is a promising numerical method for both static and dynamic analyses of rock systems. Lacking mature software, its popularity is far behind its ability. To address this problem, this paper presents a new software architecture from a software engineering viewpoint. Based on 3D-DDA characteristics, the implementation of the proposed architecture has the following merits. Firstly, the software architecture separates data, computing, visualization, and signal control into individual modules. Secondly, data storage and parallel access are fully considered for different conditions. Thirdly, an open computing framework is provided which supports most numerical computing methods; common tools for equation solving and parallel computing are provided for further development. Fourthly, efficient visualization functions are provided by integrating a variety of visualization algorithms. A user-friendly graphical user interface is designed to improve the user experience. Finally, through a set of examples, the software is verified against both analytical solutions and the original code by Dr. Shi Gen Hua.展开更多
基金supported by the National Natural Science Foundation of China (Nos. 41104083 and 40804024) Fundamental Research Funds for the Central Universities (No, 2011YYL022)
文摘The most popular hardware used for parallel depth migration is the PC-Cluster but its application is limited due to large space occupation and high power consumption. In this paper, we introduce a new hardware architecture, based on which the finite difference （FD） wavefield-continuation depth migration can be conducted using the Graphics Processing Unit （GPU） as a CPU coprocessor. We demonstrate the program module and three key optimization steps for implementing FD depth migration： memory, thread structure, and instruction optimizations and consider evaluation methods for the amount of optimization. 2D and 3D models are used to test depth migration on the GPU. The tested results show that the depth migration computational efficiency greatly increased using the general-purpose GPU, increasing by at least 25 times compared to the AMD 2.5 GHz CPU.
文摘This paper puts forward sharing teaching resources based on cloud computing solutions, through the use of architecture means virtualization technology based on KVM on the server side, the infrastructure layer manage the underlying physical hardware equipment. In the realization of the infrastructure layer using Libvirt virtualization management suite that provides a common API development Web, through the RDP protocol, and finally access to the remote virtual desktop browser by the graphical user interface （GUI） and traditional Web B/S architecture, to simulate and access to low-level resources and sharing of teaching resources, teaching resources can be achieved education informatization in the process of teaching.
基金supported by the National Natural Science Foundation of China(Grant No.61471338)the Knowledge Innovation Program of the Chinese Academy of Sciences,Youth Innovation Promotion Association CAS,President Fund of UCASCRSRI Open Research Program(Grant No.CKWV2015217/KY)
文摘The three-dimensional discontinuous deformation analysis(3D-DDA) is a promising numerical method for both static and dynamic analyses of rock systems. Lacking mature software, its popularity is far behind its ability. To address this problem, this paper presents a new software architecture from a software engineering viewpoint. Based on 3D-DDA characteristics, the implementation of the proposed architecture has the following merits. Firstly, the software architecture separates data, computing, visualization, and signal control into individual modules. Secondly, data storage and parallel access are fully considered for different conditions. Thirdly, an open computing framework is provided which supports most numerical computing methods; common tools for equation solving and parallel computing are provided for further development. Fourthly, efficient visualization functions are provided by integrating a variety of visualization algorithms. A user-friendly graphical user interface is designed to improve the user experience. Finally, through a set of examples, the software is verified against both analytical solutions and the original code by Dr. Shi Gen Hua.
