> EXTREME COMPUTING > bullx systems >

Hybrid systems and services that fully leverage the performance of accelerators
Although the emergence of multi-core CPUs has allowed manufacturers to keep pace with the steadily growing demand for more computing power, energy consumption, space, and cooling have become major inhibitors to computing systems expansion. Hence the success of accelerators such as GPUs (Graphics Processing Units) offering breakthrough performance plus outstanding space and energy efficiency. Derived from technologies initially developed for game machines, GPUs are highly parallel processors designed to seamlessly boost High Performance Computing applications without impacting power or cooling infrastructures.

Implementing GPU computing is getting easier every month as new tools become available, but it is still not trivial. To help you innovate with GPUs with maximum payoff, Bull offers complete GPU-based solutions:

  • Bull hardware leveraging the latest technologies,
  • an integrated software environment,
  • expertise and services to implement your solution.

bullx B505 blades: integrated GPUs to eliminate bottlenecks

bullx B505

Developed by the Bull R&D teams, the bullx B505 ultra-dense, double-width blades combine two Intel® Xeon® processors and two new-generation NVIDIA® Tesla GPUs. They can be associated with B500 compute blades within the same bullx chassis.

The integration of the GPUs inside the blades maximizes performance. The bullx B505 blades are the only blades on the market designed to provide maxi­mum bandwidth between each GPU and its host CPU, thanks to two chipsets and a double interconnect on each blade:

  • dedicated PCI-e 16x connection for each GPU,
  • two InfiniBand QDR ports connected to the first-level switch within the bullx chassis, so that each GPU has access to full QDR bandwidth.

Bull expertise and services for maximum performance acceleration

Depending on the type of application and its degree of optimization, GPUs can accelerate processing by a factor of 1 to 100! Expertise is therefore essential to get the most out of GPUs. Bull has a long experience of systems associating GPUs and CPUs, and places this distinctive expertise at the service of Extreme Computing customers. Bull engineers have had hands-on experience of porting and optimizing applications for GPU computing through many cooperative projects with customers, such as a cluster with 46,080 GPU cores, designed by Bull for GENCI. Bull experts deliver end-to-end services, from system design to advanced user training, through application optimization for GPUs.

A long experience of accelerators

In the last few years, Bull has designed for its customers accelerator-based systems of all sizes, from test systems with a few GPUs – purchased by several universities for example – to very large hybrid systems such as those developed for GENCI and Petrobras. Bull helps its customers optimize their GPU utilization, with very varied codes such as BIGDFT (nano-sciences), SPECFEM3D (seismic), NAMD (biochemistry), but also for oil and gas research with the porting of RTM (Reverse Time Migration) codes to GPU.

Seamless integration in the Extreme Computing environment

The bullx supercomputer suite integrates all the tools needed to operate a hybrid system comprising Intel® Xeon®-based servers and NVIDIA® Tesla™ GPUs. The task management environment supports the allocation of applications to the relevant computing resource. An application can naturally use both computing resources so as to fully capitalize on the rich potential offered by this type of system.

bullx blade system
GPU computing solutions: technical specifications flyer

The best of accelerator technologies to boost your High Performance Computing system

download
bullx blade system
Revolutionizing High Performance Computing: Bull servers for GPU accelerated HPC

This brochure published by NVIDIA outlines the advantages of GPUs and describes some real-life implementations with GPUs.

download
Retour haut de page
Print page.Send page.Share on Facebook.Share on Linkedin.Share on Viadeo.Share on Technorati.Share on Digg.Share on Delicious.Bookmark this page on Google.Share on Windows Live.Share on Twitter.
Contact

19/03/2012
Bull, CEA, F4E and JAEA inaugurate the Helios supercomputer in Rokkasho (Japan), dedicated to the Nuclear Fusion program

The supercomputer, delivering over 1.5 Petaflops, will provide the computer modeling and simulation capabilities needed for the 'Broader Approach' program, linked to the ITER initiative.
Read more >>

15/02/2012
CURIE speeds up European research

Capable of up to two million billion operations a second (or 2 Petaflop/s) GENCI's CURIE supercomputer - designed by Bull - opens up unprecedented new possibilities for academic and industrial research in Europe
Read more >>

Tera 100 receives "TOP supercomputing achievement" award from the international HPC community
More info
The readers of HPCwire voted Tera 100 as the "TOP supercomputing achievement" of the year >>

November 2011
Special Edition of La Recherche - Supercomputers: at the frontiers of Extreme Computing

New horizons / Major Challenges / The future: exascale computing
Read more >>

Contact