Kenji Takeda | University of Southampton (original) (raw)

Uploads

Papers by Kenji Takeda

Research paper thumbnail of An Evaluation of Commodity Supercomputers for CFD Applications

Research paper thumbnail of An Evaluation of Cost Effective Parallel Computers for CFD

An evaluation of the current status of two novel clusters, running Linux and NT, has been made to... more An evaluation of the current status of two novel clusters, running Linux and NT, has been made to assess their performance for parallel CFD calculations. The core algorithm of the code is the conjugate gradient method used to solve the pressure equation. For good performance, a low latency and high bandwidth is required and the results indicate that, without substantial investment in this area, neither system is competitive on parallel performance when compared to more traditional distributed memory machines. At present, they are very suitable for development platforms and, for particular applications that are not too sensitive to latency and bandwidth, they offer a very cost effective computing resource.

Research paper thumbnail of Commodity High Performance Computing at Commodity Prices

The entry price of supercomputing has traditionally been very high. As processing elements, opera... more The entry price of supercomputing has traditionally been very high. As processing elements, operating systems, and switch technology become cheap commodity parts, building a powerful supercomputer at a fraction of the price of a proprietary system becomes realistic. We have recently purchased, in support of both our local and national collaborations, a dedicated computational cluster of eight DEC Alpha workstations.

Research paper thumbnail of HPC On Dec Alphas And Windows NT

High-Performance Computing, 1999

Research paper thumbnail of Software Portability and Maintenance

High-Performance Computing, 1999

SOFTWARE PORTABILITY AND MAINTENANCE Kenji Takeda, Ivan Wolton and Denis Nicole Southampton HPCI ... more SOFTWARE PORTABILITY AND MAINTENANCE Kenji Takeda, Ivan Wolton and Denis Nicole Southampton HPCI Centre, Department of Electronics and Computer Science, University of Southampton, Southampton SO 17 1BJ ABSTRACT Topics related to ... fr/cgi-bin/molli/wilma. ...

Research paper thumbnail of Parallel Computing on Windows NT Clusters

Research paper thumbnail of Unsteady aerodynamics of race car cockpit flow

Research paper thumbnail of Proof-of-concept engineering workflow demonstrator

Research paper thumbnail of Microsoft institute for high performance computing

Research paper thumbnail of Service-oriented architectures for flight simulation: opportunities and challenges

Research paper thumbnail of Microsoft ESP: changing the game?

Research paper thumbnail of Scientific Computation and Data Management Using Microsoft Windows Azure

Research paper thumbnail of Prediction of ship motions for a Wigley hull using SPH

Research paper thumbnail of Research Data Management in the Cloud

Research paper thumbnail of Science in the cloud: lessons from three years of research projects on microsoft azure

Research paper thumbnail of Software+ services for engineers

Research paper thumbnail of Computational analysis of the effect of bogie inclination angle on landing gear noise

Research paper thumbnail of EP2DC-an EPrints module for linking publications and data

Research paper thumbnail of A framework for user driven data management

Research paper thumbnail of An Evaluation of Cost Effective Parallel Computers for CFD

ABSTRACT An evaluation of the current status of two novel clusters, running Linux and NT, has bee... more ABSTRACT An evaluation of the current status of two novel clusters, running Linux and NT, has been made to assess their performance for parallel CFD calculations. The core algorithm of the code is the conjugate gradient method used to solve the pressure equation. For good performance, a low latency and high bandwidth is required and the results indicate that, without substantial investment in this area, neither system is competitive on parallel performance when compared to more traditional distributed memory machines. At present, they are very suitable for development platforms and, for particular applications that are not too sensitive to latency and bandwidth, they offer a very cost effective computing resource.

Research paper thumbnail of An Evaluation of Commodity Supercomputers for CFD Applications

Research paper thumbnail of An Evaluation of Cost Effective Parallel Computers for CFD

An evaluation of the current status of two novel clusters, running Linux and NT, has been made to... more An evaluation of the current status of two novel clusters, running Linux and NT, has been made to assess their performance for parallel CFD calculations. The core algorithm of the code is the conjugate gradient method used to solve the pressure equation. For good performance, a low latency and high bandwidth is required and the results indicate that, without substantial investment in this area, neither system is competitive on parallel performance when compared to more traditional distributed memory machines. At present, they are very suitable for development platforms and, for particular applications that are not too sensitive to latency and bandwidth, they offer a very cost effective computing resource.

Research paper thumbnail of Commodity High Performance Computing at Commodity Prices

The entry price of supercomputing has traditionally been very high. As processing elements, opera... more The entry price of supercomputing has traditionally been very high. As processing elements, operating systems, and switch technology become cheap commodity parts, building a powerful supercomputer at a fraction of the price of a proprietary system becomes realistic. We have recently purchased, in support of both our local and national collaborations, a dedicated computational cluster of eight DEC Alpha workstations.

Research paper thumbnail of HPC On Dec Alphas And Windows NT

High-Performance Computing, 1999

Research paper thumbnail of Software Portability and Maintenance

High-Performance Computing, 1999

SOFTWARE PORTABILITY AND MAINTENANCE Kenji Takeda, Ivan Wolton and Denis Nicole Southampton HPCI ... more SOFTWARE PORTABILITY AND MAINTENANCE Kenji Takeda, Ivan Wolton and Denis Nicole Southampton HPCI Centre, Department of Electronics and Computer Science, University of Southampton, Southampton SO 17 1BJ ABSTRACT Topics related to ... fr/cgi-bin/molli/wilma. ...

Research paper thumbnail of Parallel Computing on Windows NT Clusters

Research paper thumbnail of Unsteady aerodynamics of race car cockpit flow

Research paper thumbnail of Proof-of-concept engineering workflow demonstrator

Research paper thumbnail of Microsoft institute for high performance computing

Research paper thumbnail of Service-oriented architectures for flight simulation: opportunities and challenges

Research paper thumbnail of Microsoft ESP: changing the game?

Research paper thumbnail of Scientific Computation and Data Management Using Microsoft Windows Azure

Research paper thumbnail of Prediction of ship motions for a Wigley hull using SPH

Research paper thumbnail of Research Data Management in the Cloud

Research paper thumbnail of Science in the cloud: lessons from three years of research projects on microsoft azure

Research paper thumbnail of Software+ services for engineers

Research paper thumbnail of Computational analysis of the effect of bogie inclination angle on landing gear noise

Research paper thumbnail of EP2DC-an EPrints module for linking publications and data

Research paper thumbnail of A framework for user driven data management

Research paper thumbnail of An Evaluation of Cost Effective Parallel Computers for CFD

ABSTRACT An evaluation of the current status of two novel clusters, running Linux and NT, has bee... more ABSTRACT An evaluation of the current status of two novel clusters, running Linux and NT, has been made to assess their performance for parallel CFD calculations. The core algorithm of the code is the conjugate gradient method used to solve the pressure equation. For good performance, a low latency and high bandwidth is required and the results indicate that, without substantial investment in this area, neither system is competitive on parallel performance when compared to more traditional distributed memory machines. At present, they are very suitable for development platforms and, for particular applications that are not too sensitive to latency and bandwidth, they offer a very cost effective computing resource.

Log In