Next-Generation Massively Parallel Computers | Massively Parallel Computer for Particle-based Simulations
نویسندگان
چکیده
Subleader Junichiro Makino Associate Professor, School of Science, University of Tokyo Izumi Hachisu Associate Professor, College of Arts and Sciences, University of Tokyo Makoto Taiji Associate Professor, Institute for Statistical Mathematics Yoko Funato Research Associate, College of Arts and Sciences, University of Tokyo Toshiyuki Fukushige Research Associate, College of Arts and Sciences, University of Tokyo Koji Takahashi JSPS research fellow, School of Science, University of Tokyo
منابع مشابه
Gyrokinetic Simulations of Plasma Turbulence on Massively Parallel Computers
With the rapid development of massively parallel computers, the particle-in-cell (PIC) approach to plasma microturbulence in toroidal geometry has become an increasingly important tool. Global, self-consistent simulations with up to 100 millions particles yield valuable insights in the dynamics of the turbulence. The inclusion of the fast-moving electrons in the dynamics represents a major chal...
متن کاملVortex particle simulations of aircraft wake instabilities on massively parallel architectures
We present the Direct Numerical Simulations of high Reynolds numbers vortical flows employing vortex methods. The simulations involve a highly efficient implementation on massively parallel computers, enabling unprecedented simulations using billions of particles. Present results of this work include the investigation of the implementation performance up to 16k IBM BG/L nodes and the study of m...
متن کاملÜ 33 57
TISTESüflOi'i ST^.TEMEITT^A Ä„„,..r~~~A -f.-i-r rjuWc release; Distribution Unlimited Two years ago, researchers at Sandia National Laboratories showed that a massively parallel computer with 1024 processors could solve scientific problems more than 1000 times faster than a single processor. Since then, interest in massively parallel processing has increased dramatically. This review paper disc...
متن کامل12 A Critical Analysis of MultigridMethods on Massively
The hierarchical nature of multigrid algorithms leaves domain parallel strategies with a deeciency of parallelism as the computation moves to coarser and coarser grids. To introduce more parallelism several strategies have been designed to project the original problem space into non-interfering subspaces, allowing all grids to relax concurrently. Our objective is to understand the potential eec...
متن کاملDesign of scalable optical interconnection networks for massively parallel computers
The increased amount of data handled by current information systems, coupled with the ever growing need for more processing functionality and system throughput is putting stringent demands on communication bandwidths and processing speeds. While the progress in designing high-speed processing elements has progressed significantly, the progress on designing high-performance interconnection netwo...
متن کامل