Back to Table of contents

Primeur live 2011-06-21

Blog

Some insights in the TOP500 ...

Hardware

Petaflop/s: The why, the how and the what for? ...

Applications

Russia accelerates scientific innovation with GPU supercomputers ...

hpc-ch at ISC'11 to present HPC activities in Switzerland ...

TOP500

Tera 100 once again crowned as Europe's most powerful supercomputer ...

The Grid

RealityServer: A powerful platform for 3D visualization and rendering now accessible in the Cloud ...

You ask "What Cloud?" It's Enterprise IT! ...

Company news

NetApp bolsters management capabilities, provides common foundation for enterprise customers' private, public, and hybrid Clouds ...

Bull announces the creation of BUX, the Bull User group for eXtreme Computing ...

Bright Cluster Manager 5.2 shipping with support for CUDA 4, ScaleMP, SLURM, LSF and enhanced multi-cluster management ...

Experts from Russia and EU collaborate on HOPSA; a new project to boost the performance of supercomputers ...

Companies at ISC'11 exhibition show media the innovations they've got in store for user ...

Xyratex exhibiting at International Supercomputing Conference 2011 ...

Supermicro showcases portfolio of HPC optimized solutions at ISC'11 ...

Mellanox FDR InfiniBand selected to deliver PetaScale performance for Europe’s fastest supercomputer ...

NetApp E5400 meets extreme customer demands in high-performance environments ...

VMware introduces vFabric 5, an integrated application platform for virtual and Cloud environments ...

Some insights in the TOP500


21 Jun 2011 Hamburg - The special TOP500 session at ISC11 started with an opportunity to ask questions to Yui Oniaga, designer of the K computer and Tadashi Watanabe designer of the Earth Simulator. According to Oniaga, the K system does not have GPUs, because they really would not add to the performance of the system. The most important part is the direct network connection. Which currently is based on Infiniband. The individual speed of the nodes is not that important, as long as their connection is.

Their next system will have a performance of over 10 Petaflop/s. That is only a factor of 100 way from Exascale, says Oniaga. He is sure that without too much changers in the design, they will get there. Again, interconnect is key.

The K computer is SPARC based with a special brand of Unix. Will that not hinder porting of applications? Was another question. The designers do not think so. Actually most of the porting work goes into parallelisation. Adapting it to the processor and operating system is only minor work.

K computer is a huge system with over 500.000 nodes. About every 15 hours a node fails. So they are working on low level rerouting of nodes so that applications do not fail.

Jack Dongarra, responsible for Linpack software used as benchmark in the TOP500, commented that to tun the Linpack to brought them on top of the list, the K system needed 22 hours. According to Dongarra it as amazing that brand new large supercomputers of this kind run for that long, right after they have been installed. The Linpack group is working on a new version of the bench mark that allows to only execute part of the benchmark, so that the run would only take about 12 hours. Of course the short benchmark should never give higher figures than the complete benchmark. With this changes the Linpack would be "Exascale ready".

Ad Emmen

Back to Table of contents

Primeur live 2011-06-21

Blog

Some insights in the TOP500 ...

Hardware

Petaflop/s: The why, the how and the what for? ...

Applications

Russia accelerates scientific innovation with GPU supercomputers ...

hpc-ch at ISC'11 to present HPC activities in Switzerland ...

TOP500

Tera 100 once again crowned as Europe's most powerful supercomputer ...

The Grid

RealityServer: A powerful platform for 3D visualization and rendering now accessible in the Cloud ...

You ask "What Cloud?" It's Enterprise IT! ...

Company news

NetApp bolsters management capabilities, provides common foundation for enterprise customers' private, public, and hybrid Clouds ...

Bull announces the creation of BUX, the Bull User group for eXtreme Computing ...

Bright Cluster Manager 5.2 shipping with support for CUDA 4, ScaleMP, SLURM, LSF and enhanced multi-cluster management ...

Experts from Russia and EU collaborate on HOPSA; a new project to boost the performance of supercomputers ...

Companies at ISC'11 exhibition show media the innovations they've got in store for user ...

Xyratex exhibiting at International Supercomputing Conference 2011 ...

Supermicro showcases portfolio of HPC optimized solutions at ISC'11 ...

Mellanox FDR InfiniBand selected to deliver PetaScale performance for Europe’s fastest supercomputer ...

NetApp E5400 meets extreme customer demands in high-performance environments ...

VMware introduces vFabric 5, an integrated application platform for virtual and Cloud environments ...