Viet Tran - Academia.edu (original) (raw)
Papers by Viet Tran
... The network performance is one of the most critical point from the view of high performance c... more ... The network performance is one of the most critical point from the view of high performance computing: while the network throughput of virtual machines is still comparable with the physical hardware, the long latencies caused by virtualization can degrade performance of ...
Computer Methods in Biomechanics and Biomedical Engineering, 2007
GCCP 2009 BOOK OF ABSTRACTS, 2009
... balancing. We choose DIANE for our applications because it is in RESPECT program of EGEE and ... more ... balancing. We choose DIANE for our applications because it is in RESPECT program of EGEE and has a long development history. DIANE is a lightweight job execution control framework for parallel scientific applications. DIANE ...
ups.savba.sk
... Proxy has a short lifetime (typically 12 hours) to reduce security risks. For long-running jo... more ... Proxy has a short lifetime (typically 12 hours) to reduce security risks. For long-running jobs, in order to avoid the proxy expiration, there is a renewal mechanism to keep the proxy valid for aslong as needed. The MyProxy server is the component that provides this functionality. ...
GCCP 2009 BOOK OF ABSTRACTS, 2009
... This approach can work efficiently also for small workflows (smaller numbers oflong-time task... more ... This approach can work efficiently also for small workflows (smaller numbers oflong-time tasks). If jobs are submitted to heavy-loaded grid infrastrutures, they may have to wait for long times (hours, days) in queues before executions. ...
Computer Methods in Biomechanics and Biomedical Engineering, 2007
ups.savba.sk
Page 1. A Practical Component Framework for Development of Scientific Grid Applications V. ipkov... more Page 1. A Practical Component Framework for Development of Scientific Grid Applications V. ipková, R. Forgác, J. Astalo, VD Tran, and M. Dobrucký Ústav Informatiky, Slovenská Akadémia Vied 845 07 Bratislava, Dúbravská cesta 9 Abstract. ...
In this paper, we present workflow management tool for Earth science applications in EGEE. The wo... more In this paper, we present workflow management tool for Earth science applications in EGEE. The workflow management tool was originally developed within K-wf Grid project for GT4 middleware and has many advanced features like semi-automatic workflow composition, user-friendly GUI for managing workflows, knowledge management. In EGEE, we are porting the workflow management tool to gLite middleware for Earth science applications
Proceedings 8th Euromicro Workshop on Parallel and Distributed Processing, 1999
In this paper, bye present a new powerful method for parallel program representation called Data ... more In this paper, bye present a new powerful method for parallel program representation called Data Driven Graph (DDG). DDG takes all advantages of classical Directed Acyclic graph (DAC) and adds much more. Simple definition, flexibility and ability to represent loops and dynamically created tasks. With DDG, scheduling becomes an efficient tool for increasing performance of parallel systems. DDG is not
Parallel Computing - Fundamentals and Applications - Proceedings of the International Conference ParCo99, 2000
In this paper we present architecture and current state of implementation of a collaborative comp... more In this paper we present architecture and current state of implementation of a collaborative computation environment based on Grid infrastructure, used as a mean of support for large scientific virtual organizations. The environment consists primarily of a collaboration-supporting user interface, workflow system capable of submission of jobs to the Grid and a Grid-based data management suite. The whole system is
Parallel Computing, 2003
... Moreover, for critical situations, eg when an advancing flood is simulated in order to predic... more ... Moreover, for critical situations, eg when an advancing flood is simulated in order to predict which areas will be threatened so that necessary prevention measures can be implemented in time, long computation times are unacceptable. ... This straight fiver is 50 Km long. ...
2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2010
ABSTRACT The use of data mining techniques in environmental applications of IT, and specifically ... more ABSTRACT The use of data mining techniques in environmental applications of IT, and specifically in hydro-meteorological predictions, is not a new topic. In this paper however we present the novel use of data mining in the ADMIRE Project and its scenarios. In Orava scenario we try to predict the change of water level and water temperature in the OravaRiver below the Orava reservoir, and how they react to discharge from the reservoir. In second scenario - Radar, we are predicting rainfall in short term. The last scenario - SVP, is modeling situation of melting snow and caused inflow into reservoir.
Lecture Notes in Computer Science, 2004
This paper focuses on parallelization process of DaveF, a new two-dimensional depth-averaged flow... more This paper focuses on parallelization process of DaveF, a new two-dimensional depth-averaged flow and sediment transport model that allows breach development and the resulting flood wave to be simulated simultaneously. Problems encountered during ...
Parallel Computing - Fundamentals and Applications - Proceedings of the International Conference ParCo99, 2000
Parallel Computing - Advances and Current Issues - Proceedings of the International Conference ParCo2001, 2002
... The network performance is one of the most critical point from the view of high performance c... more ... The network performance is one of the most critical point from the view of high performance computing: while the network throughput of virtual machines is still comparable with the physical hardware, the long latencies caused by virtualization can degrade performance of ...
Computer Methods in Biomechanics and Biomedical Engineering, 2007
GCCP 2009 BOOK OF ABSTRACTS, 2009
... balancing. We choose DIANE for our applications because it is in RESPECT program of EGEE and ... more ... balancing. We choose DIANE for our applications because it is in RESPECT program of EGEE and has a long development history. DIANE is a lightweight job execution control framework for parallel scientific applications. DIANE ...
ups.savba.sk
... Proxy has a short lifetime (typically 12 hours) to reduce security risks. For long-running jo... more ... Proxy has a short lifetime (typically 12 hours) to reduce security risks. For long-running jobs, in order to avoid the proxy expiration, there is a renewal mechanism to keep the proxy valid for aslong as needed. The MyProxy server is the component that provides this functionality. ...
GCCP 2009 BOOK OF ABSTRACTS, 2009
... This approach can work efficiently also for small workflows (smaller numbers oflong-time task... more ... This approach can work efficiently also for small workflows (smaller numbers oflong-time tasks). If jobs are submitted to heavy-loaded grid infrastrutures, they may have to wait for long times (hours, days) in queues before executions. ...
Computer Methods in Biomechanics and Biomedical Engineering, 2007
ups.savba.sk
Page 1. A Practical Component Framework for Development of Scientific Grid Applications V. ipkov... more Page 1. A Practical Component Framework for Development of Scientific Grid Applications V. ipková, R. Forgác, J. Astalo, VD Tran, and M. Dobrucký Ústav Informatiky, Slovenská Akadémia Vied 845 07 Bratislava, Dúbravská cesta 9 Abstract. ...
In this paper, we present workflow management tool for Earth science applications in EGEE. The wo... more In this paper, we present workflow management tool for Earth science applications in EGEE. The workflow management tool was originally developed within K-wf Grid project for GT4 middleware and has many advanced features like semi-automatic workflow composition, user-friendly GUI for managing workflows, knowledge management. In EGEE, we are porting the workflow management tool to gLite middleware for Earth science applications
Proceedings 8th Euromicro Workshop on Parallel and Distributed Processing, 1999
In this paper, bye present a new powerful method for parallel program representation called Data ... more In this paper, bye present a new powerful method for parallel program representation called Data Driven Graph (DDG). DDG takes all advantages of classical Directed Acyclic graph (DAC) and adds much more. Simple definition, flexibility and ability to represent loops and dynamically created tasks. With DDG, scheduling becomes an efficient tool for increasing performance of parallel systems. DDG is not
Parallel Computing - Fundamentals and Applications - Proceedings of the International Conference ParCo99, 2000
In this paper we present architecture and current state of implementation of a collaborative comp... more In this paper we present architecture and current state of implementation of a collaborative computation environment based on Grid infrastructure, used as a mean of support for large scientific virtual organizations. The environment consists primarily of a collaboration-supporting user interface, workflow system capable of submission of jobs to the Grid and a Grid-based data management suite. The whole system is
Parallel Computing, 2003
... Moreover, for critical situations, eg when an advancing flood is simulated in order to predic... more ... Moreover, for critical situations, eg when an advancing flood is simulated in order to predict which areas will be threatened so that necessary prevention measures can be implemented in time, long computation times are unacceptable. ... This straight fiver is 50 Km long. ...
2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2010
ABSTRACT The use of data mining techniques in environmental applications of IT, and specifically ... more ABSTRACT The use of data mining techniques in environmental applications of IT, and specifically in hydro-meteorological predictions, is not a new topic. In this paper however we present the novel use of data mining in the ADMIRE Project and its scenarios. In Orava scenario we try to predict the change of water level and water temperature in the OravaRiver below the Orava reservoir, and how they react to discharge from the reservoir. In second scenario - Radar, we are predicting rainfall in short term. The last scenario - SVP, is modeling situation of melting snow and caused inflow into reservoir.
Lecture Notes in Computer Science, 2004
This paper focuses on parallelization process of DaveF, a new two-dimensional depth-averaged flow... more This paper focuses on parallelization process of DaveF, a new two-dimensional depth-averaged flow and sediment transport model that allows breach development and the resulting flood wave to be simulated simultaneously. Problems encountered during ...
Parallel Computing - Fundamentals and Applications - Proceedings of the International Conference ParCo99, 2000
Parallel Computing - Advances and Current Issues - Proceedings of the International Conference ParCo2001, 2002