One of the hot candidates certainly is IBM's Roadrunner at LANL in Los Alamos, USA. Currently, the number one position is held by BLueGene/L eServer at DOE/NNSA/LLNL, USA, with a best Linpack performance of 478.2 Teraflop/s.

How will Sun's consolidation system Ranger at TACC at the University of Austin, USA, be doing? Ranger missed the 30th list in Reno due to delivery problems with the AMD processor chips. Ranger has a peak performance of above 500 Teraflop/s. Can Ranger help Sun Microsystems catch up with the other HPC manufacturers again?

In the 30th list, more than 70% of the processors in all 500 systems were manufactured by Intel; this was the largest share of Intel chips in the TOP500 ever. Especially successful are Intel's dual-core Woodcrest and quad-core Clovertown processors.

In the 31st list, the TOP500 team will check whether AMD has been able to recover or not. The team will also have a look at how the Asian countries are doing. Will the rapid drop in Japan's share be stopped? Are China and India already new players in the TOP500? And last but not least, in which way IBM's BG series, representing the "power-efficient systems" class, will go?

In the first presentation at ISC'08, Intel Corporate Chief Technology Officer Justin Rattner will tell the conference audience about how Intel's Tera-scale research programme addresses fundamental issues to unleash the performance of multi/many-core microprocessors. This includes architecture research to ensure a high computational efficiency as well as research into programming models and tools to support parallel programming as well as a glimpse into future applications.

As we very soon will have hundreds of processor cores on a chip, massive parallelism will get mainstream and will mean dramatic changes to most software. In the second presentation, Professor Jack Dongarra of the University of Tennessee will explain what this means to especially mathematical software and what changes it has to go through.

MPI has been the prevailing programming interface for parallel computing. With the widespread use of multi/many-core computers, OpenMP will gain in importance. Professor Lutz Gross, the Director of High Performance Computing in the Earth Systems Science Computational Center (ESSCC) at the University of Queensland, Australia will speak about the issues involved in parallelization of finite element (FEM) solvers on multi-core Xeon clusters using a hybrid approach including MPI as well as OpenMP.

ISC'08 will also devote a session on European High End HPC activities with Prof. Dr. Achim Bachem from the Research Centre Juelich, Germany about the PRACE project; Prof. Dr. Dr. Thomas Lippert, from the Juelich Supercomputing Centre (JSC), Germany and Dr. Giovanni Trezza from Quadrics, Italy on PROSPECT, a European Alliance; and Claude Camozzi from Bull, France and Dr. Jean Gonnord from CEA, France about Talos in order to

strengthen European HPC through co-operative projects.

The submission deadline for Birds-of-Feather sessions and research posters is April 12, 2008.

More information is available at http://www.isc08.org