IT infrastructure and computing capacity are critical to the efficiency of HPC computer centres in Research, Education or Industry. This has been recognized by the 'Commissariat à l'Energie Atomique' (CEA) has been using Platform LSF for a long time to manage the workload of compute jobs running on two of the largest European computers designed and delivered by Bull.

"CEA has been using Platform LSF software in its computing centre for a number of years and we decided to keep it as a batch management system when we replaced its computers in 2005 and 2006. Our motivations to renew our confidence in this product are multiple. It was of course intended to leverage and capitalize on past invested experience with this operation for running clusters", stated Hervé Lozach, Head of Scientific Computing and Networking Service, CEA. "The software maturity, its compatibility with a variety of architectures, are also strong points of Platform LSF. In our case, it also fits with the Quadrics/RMS resource manager for TERA as well as the SLURM CCRT batch management needs."

"Platform LSF is the perfect complement to Bull's NovaScale HPC Solutions", stated Christoph Reichert, Vice President HPC Sales, EMEA, Platform Computing. "With the speed and reliability LSF provides, Bull customers can look forward to implementing a faster, more efficient HPC solution in a timely manner without incurring prohibitive financial costs."

While significantly reducing TCO, Bull NovaScale Clusters also offer optimal flexibility and modularity, to match customers' exact requirements. They are available in a wide range of configuration sizes, and offer a broad choice of options for processors, interconnects, and operating environments. The BAS (Bull Advanced Server) software suite for HPC environments is built on top of standard Red Hat Enterprise Linux 4 or 5. This integrated and comprehensive package, designed by Bull, includes the best of Open Source and industry-standard software, together with specific features developed by Bull for high-performance computing clusters. BAS includes comprehensive management tools to allow an entire cluster, including the platform and interconnect network, to be as easily monitored and managed as a single system.

"We have a great history working with Platform Computing and have achieved significant successes together", stated Benoît Hallez, Director of Bull's HPC Business Unit. "This agreement will strengthen our collaboration, and will benefit our customers in their continuous quest for optimizing their cluster resources usage."