Quadrics - Case Studies

Case Studies

Tera-10 at CEA/DAM

Tera10 is a multi-rail system of 544 NovaScale 6160 Computing Nodes for a total of 8704 Itanium Montecito Processors interconnected with QsNet^II, and the first Quadrics system using paralle fiber links.
System Performance:

60 Teraflops of Computing Power

27 Terabytes of Core Memory

1 Petabytes of disc space with a throughput of 100GB/s

Image courtesy of CEA

Thunder at LLNL

Quadrics has collaborated with Lawrence Livermore National Laboratory over the past 4 years to integrate Quadrics technologies in over six large scale commodity based clusters to ensure that the demanding production performance, scalability and stability requirements of the Laboratory are satisfied. The latest Quadrics based system at LLNL , called Thunder delivers world-record performance for a commodity Linux cluster.

Thunder at LLNL -Image Courtesy of Top500 List

Gonzales at ETHZ

Gonzales is a 160 dual-processor high performance cluster system deployed at the Swiss Federal Institute of Technology Zurich (ETH), one of the top research centers in the world. The system incorporates the Quadrics QsNet^II fast interconnect together with a number of unique features provided by DALCO based around SuSE Linux and the Quadrics Resource Management System.

Image courtesy of Dalco AG

ASCI Q at LANL

The ASCI-Q system at Los Alamos National Laboratory was in the 22nd top500 list the most powerful supercomputing system in the US. It is based on the HP™ AlphaServer™ SC. It deploys 2 rails of Quadrics QsNet and spans over 2000 nodes.
The Q-machine can be described as a cluster of Shared Memory Multiprocessors (SMP), which is expected to deliver a peak performance in excess of 30 Teraflops with approximately 12,000 processors. Multiple independent QsNet network rails will interconnect the SMPs through their I/O ports (PCI or PCI-X).

ASCIQ at LANL- Image courtesy of Top500 List

Mpp2 at PNNL

Quadrics worked very closely with HP and HP sub-contractors in architecting a Linux/Supercomputing solution. Quadrics interconnect (QsNet) and software-stack (QsRMS) have been ported to Linux and are now being deployed in production environments at both US National Laboratories and Industrial organization where performance and reliability both play demanding roles in guaranteeing time-to-solution.

Mpp2 at PNNL - Image courtesy of Top500 List

MCR at LLNL

In order to meet the exacting requirements of this program, Quadrics developed a custom version of its QsNet switch and expanded the number of nodes in the fat tree topology for a given number of switch stages to produce a more cost effective network.This allowed the proven supercomputer class technology of QsNet to be combined with commodity processing elements.

MCR at LLNL -Image Courtesy of Top500 List

Le Mieux at PSC

The Terascale Computing System at the Pittsburgh Supercomputing Center (PSC), entered the top500 some 2 years ago as the most powerful Supercomputer in academia with an RMAX of 4463 GigaFlops. It was the first system to deploy the federated QsNet network and comprises 2 rails of Quadrics QsNet. The system is based on the HP' AlphaServer SC product and combines Intel processing nodes using Linux to create a customized heterogeneous QsNet configuration for high performance graphics and storage.

Image courtesy of PCS

> Legal