Extreme Computing
10 reasons to choose Bull Extreme Computing solutions
Products & solutions
bullx clusters
Operating Systems
Cluster management
bullx servers
GPU solutions
mobull
Green Extreme Computing
Partners
Industry Solutions
Research and education
Manufacturing industry
Oil and gas
Resource center
References
Brochures
Press
Competence centre

bullx systems

Enhanced nodes

Designed without compromise for unlimited innovation
Bull’s Extreme Computing solutions are built using a large choice of bullx systems, based on latest generation Intel® Xeon® processors. Specifically designed with Extreme Computing in mind, they can serve all applications.

bullx blade system
bullx rack-mounted system

bullx blade system

The bullx blade system was designed with the following principles in mind:

  • Optimization and simplification of the compute node for HPC use
  • Integration of several compute nodes and first-level interconnect
  • Flexible structure for communication and I/O networks, for the closest fit with customer requirements

The resulting bullx blade system leverages the latest technological advances such as:

  • New-generation Intel® Xeon® 5500 series processors (code-named Nehalem-EP ), with Intel® QPI technology
  • InfiniBand network connection through an integrated 36-ports QDR switch
  • Flexible storage: choice between local HDD , or local SSD , or diskless blades
  • Availability of GPU -accelerated blades

Thanks to these innovations, the bullx blade system delivers:

  • Improved performance (enhanced compute node efficiency, reduced latency, higher communication and I/O throughput)
  • Reduced cost of ownership (fewer components, better fit of communication network, reduced installation time, improved upgradeability, power efficiency)
  • Enhanced reliability (less cabling)

Compute node


Compute node

bullx blade chassis: high density, uncompromised performance and optimized power consumption

The bullx blade chassis can host up to 18 compute blades in 7U. It also contains the first-level interconnect, a management unit and all components necessary to power and cool the blades, interconnect and management unit. It is the ideal foundation to build a medium to large-scale HPC cluster, with bullx compute blades combined with R423 E2 service nodes.

The bullx blade chassis provides a peak performance of up to 1.69 Tflops and offers a fully non-blocking InfiniBand QDR interconnect.

An ultracapacitor (option) protects the chassis from power outages up to 250ms. In areas with good quality power supplies, the ultracapacitor means a UPS is not needed – saving up to 15% on power consumption.

The chassis is equipped with high-efficiency (+90%) power supply units, and power consumption is further optimized by the smart fan control in each chassis.

More information on bullx chassis

   
bullx B500

bullx B500 compute blade

  • 2 high-frequency Intel® Xeon® 5500 series processors (up to 2.93 GHz)
  • Large memory capacity (up to 96GB memory per blade with 8GB DDR3 DIMMs)
  • 1 SATA HDD or 1 SSD drive or diskless

More information on bullx B500

   
bullx B505

bullx B505 accelerator blade

  • Double-width blade
  • 2 Intel® Xeon® 55xx processors
  • 2 NVIDIA Tesla M1060 GPUs
  • Memory: up to 48GB per blade with 8GB DDR3 DIMMs
  • 2 ConnectX adapters providing single QDR IB channel

More information on bullx B505

bullx rack-mounted system Page top

Compute node

Compute nodes : ultra dense servers for cost-effective capacity computing
The bullx (formerly NovaScale) R422 E2 2-socket servers are designed for high-level performance: high memory capacity, high-end connectivity, optimal internal storage capacity.
With 2 servers in 1U (i.e. up to 16 cores and 188 Gflops), the R422 E2 has the same density as blades, and the flexibility of 1U commodity servers.
And for the most demanding SMP applications and memory-hungry codes, the 4-socket NovaScale R480 E1 server is the right choice.

More information on R422 E2
More information on R480 E1

   
Enhanced nodes
Vizualisation node

Enhanced nodes designed for cluster management and visualization
The bullx (formerly NovaScale) R423 E2 service node has advanced connectivity features, extended storage options and redundancy features to guarantee reliable cluster management services.
The bullx R425 E2 visualization node is equipped to support the latest graphics and accelerator cards.

More information on R423 E2
More information on R425 E2


 
NEWS
 

HPCwire award

bullx named as the world's best HPC server product or technology and ranked among the top 5 new products to watch


 

NEED INFORMATION?
  Contact us.
NEWS

bullx recognized worlwide: HPCwire award for "Best HPC server product"

HPCwire award

 
SUCCESS

The University of Münster acquires a bullx supercomputer

Bull installs GENCI’s new supercomputer – Europe’s largest hybrid system

Rendering for Planet 51 animation film executed on a Bull cluster

 
NEWSLETTER

Read the Bull Extreme Computing Newsletter —  June edition Fortune

 
LEARN MORE

Download the special edition of La Recherche dedicated to HPC applications and technologies (June 2009)

Download the White paper co-authored by Bull and Microsoft: A Hybrid OS Cluster Solution - Dual-Boot and Virtualization with Windows HPC Server 2008 and Linux

 

 

Contact  |  Site map  |  Legal  |  Privacy