Naoya Teshima

Toward an international sparse linear algebra expert system by interconnecting the ITBL computational Grid with the Grid-TLSE platform

Complex optimization problems are of high interest for Process Systems Engineering. The selection of the relevant technique for the treatment of a given problem has already been studied for batch plant design issues. Classically, most works reported in the dedicated literature yet considered item sizes as continuous variables. In a view of realism, a similar approach is proposed in this paper, with discrete variables for representing equipment capacities, which leads to a combinatorial problem. For this purpose, a Genetic Algorithm was used, which is multiparametric by nature and a grid approach is perfectly relevant to this case study, since the GA code must be run several times, with different values of some input parameters, to guarantee its stochastic nature. This paper is devoted to the presentation of a grid-oriented GA methodology. Some significant results are highlighted and discussed.In the present paper, the methodology of interoperability between ITBL and Grid-TLSE is described. Grid-TLSE is an expert web site to provides user assistance in choosing the right solver for its problems and appropriate values for the control parameters of the selected solve. The time to solution of linear equation solver strongly depends on the type of problem, the selected algorithm, its implementation and the target computer architecture. Grid-TLSE uses the Diet middleware to distribute computing tasks over the Grid. Therefore, extending the variety of computer architecture by Grid middleware interoperability between Diet and ITBL has a beneficial impact to the expert system. To show the feasibility of the methodology, job transfering program as a special service of Diet was developed.

Network Computing Infrastructure to Share Tools and Data in GNEP

Network computing infrastructure for sharing tools and data was implemented to support international collaboration. In designing the system, we focused on three issues: accessibility, security, and usability. In the implementation, we integrated existing network and web technologies into the infrastructure by introducing the authentication gateway. For the first issue, SSL-VPN (Security Socket Layer – Virtual Private Network) technology was adopted to access computing resources beyond firewalls. For the second issue, PKI (Public Key Infrastructure)-based authentication mechanism was used for access control. Shared key based file encryption was also used to protect against information leakage. The introduction of the authentication gateway enables to strengthen the security. To provide high usability, WebDAV (Web-based Distributed Authoring and Versioning) was used to provide users with a function to manipulate distributed files through a windows-like GUI (Graphical User Interface). These functions were integrated into a Grid infrastructure called AEGIS (Atomic Energy Grid InfraStructure). Web applications were developed on the infrastructure for dynamic community creation and information sharing. In this paper, we discuss design issues of the system and report the implementation of a prototype applied to share information for the international project GNEP (Global Nuclear Energy Partnership).Copyright

Development of Three-Dimensional Virtual Plant Vibration Simulator on Grid Computing Environment ITBL-IS/AEGIS

Center for computational science and e-systems of Japan Atomic Energy Agency is carrying out R&D in the area of extra large-scale simulation technologies for solving nuclear plant structures in its entirety. Specifically, we focus on establishing a virtual plant vibration simulator on interconnected supercomputers intended for seismic response analysis of a whole nuclear plant. The simulation of the whole plant is a very difficult task because an extremely large dataset must be processed. To overcome this difficulty, we have proposed and implemented a necessary simulation framework and computing platform. The simulation framework based on the computing platform has been applied to a linear elastic analysis of the reactor pressure vessel and cooling systems of a nuclear research facility, the HTTR. The simulation framework opens a possibility of new simulation technologies for building a whole virtual nuclear plant in computers for virtual experiments.Copyright

Development of Simple Orchestration Application Framework and Its Application to Burning Plasma Simulation

We have developed the Simple Orchestration Application Framework (SOAF) to cooperatively control simulation codes on remote computers from a client PC. SOAF enables researchers to cooperatively execute various codes on grid infrastructure by only describing a configuration file including the information of execution codes and file flows among them. SOAF does not need substantial modification of the simulation codes. We have applied SOAF to the “Burning Plasma Integrated Code” which consists of various plasma simulation codes to solve the current diffusion, stability of plasma, current drive, and so on. In order to predict and interpret the behavior of fusion burning plasma, it is necessary to integrate simulation codes for complex plasma phenomena with wide temporal and spatial ranges. Since those codes exist on distributed heterogeneous computers installed in different sites such as universities and institutes, a grid computing technology is needed to cooperatively execute those codes. However, traditional grid technologies are difficult for non-computer scientists to use. By using SOAF, we successfully execute four plasma simulation codes included in the “Burning Plasma Integrated Code” according to the scenario described in the configuration file.

High Performance Computing for Analyzing PB-Scale Data in Nuclear Experiments and Simulations

By performance improvement of computers and expansion of experiment facilities, output data having became huge. In near future, the output data will become petabyte (PB)-scale. It will become increasingly important how huge data is analyzed efficiently and derive useful information. To analysis huge data efficiently, we are constructing large-scale data integrated analysis system which treats terabytes-petabytes data. In this system, two elemental technologies, i.e., heterogeneous processor and distributed parallel computing framework with fault-tolerance are implemented. The former and the latter are effective for computation dominant processes and data I/O dominant processes, respectively. First, we have applied acceleration by the heterogeneous processor to experimental data and estimated its performance. The processor accelerated experimental data processing substantially. Next, then we have constructed a prototype of distributed parallel computing system for simulation data and carried out processing test. We have found the notice points for application these elemental techniques.

Full-Scale 3D Vibration Simulator for an Entire Nuclear Power Plant on the Simple Orchestration Application Framework

So far, we have developed grid-enabled application for “Full-Scale 3D Vibration Simulator for an Entire Nuclear Power Plant” which is simulation platform to analyze seismic response of a whole digitalized nuclear power plant. In the 3D Vibration Simulator, components of a nuclear power plant are treated in hierarchical manner in which large components are grouped at primary level and small components such as pipes are grouped at secondary level and boundary condition data from the large components simulation are used as input data of small components simulation. In this work, to make the whole simulation more efficient than the previous sequential scenario in which after large components simulation is completed, small components simulation starts, we introduce pipelined data-transfer scenario in which boundary condition data are transferred each time step while all components simulation are run in parallel. In realization of the 3D Vibration Simulator in the introduced scenario, we confronted two challenges: first, clearance of job’s idle time to be wasted for only waiting data which takes from a few ten minutes to a few hours per each time step and second, immediate resubmission of abnormal ended jobs for a long time simulation under the introduced scenario. To address these challenges, we proposed two solutions: as first solution, we set policy by which jobs of small components are submitted after all necessary data per each time step arrive and executed only that time step, which process is repeated whenever next time step input data arrive and as second solution, we make an abnormal ended job automatically resubmitted. Since there were no pre-existing grid technologies to provide sufficient functionalities to enable these solutions to be possible from the previous grid-enabled application, we developed Simple Orchestration Application Framework (SOAF) and upgraded the previous grid-enabled application by implementing the SOAF. Using the upgraded grid-enable application, we performed seismic analysis of High Temperature Engineering Test Reactor at O-arai R&D center of Japan Atomic Energy Agency and confirmed that the simulation were performed in pipelined data-transfer scenario effectively using computing resources without idle time for about a week simulation period resubmitting abnormally ended jobs. In this paper, the details of all of this work will be described.

Interoperation between Atomic Energy Grid Infrastructure (AEGIS) and Other Grids

Coordination of global knowledge is needed to advance the computational and computer science needed for nuclear research. We have been conducting cooperative international research in various fields to construct a highly-secure worldwide network computing infrastructure, based on the Atomic Energy Grid Infrastructure (AEGIS). A promising way to achieve this is to establish interoperation using AEGIS with other grids. The operation of existing grid environments that allow the continuous development and execution of user applications is critical. To achieve the interoperability while maintaining operations, we have developed a system that converts messages among different grid middlewares without requiring modification of grid middlewares. To realize interoperability with two or more grid middlewares in the present study, we have defined the application programming interface (API) as a common interface to convert messages among the grid middlewares. We have applied our system to three interoperable environments. Through these experiments, we have confirmed that our system is applicable to the construction of interoperable environments among various grid middlewares.