June 22, 2009
New Grid Director 4700 switch provides choice of 324 or 648 ports for extreme scalability and lowest latency in the industry; combines with Unified Fabric Manager software to optimize performance
HAMBURG, Germany, June 22 -- Voltaire Ltd., a leading provider of scale-out datacenter fabrics, today announced the general availability of the Grid Director 4700, a 40 Gb/s InfiniBand director switch which offers the lowest latency in the industry. Combined with Voltaire's Unified Fabric Manager (UFM) software, also released today, the solution provides blazing performance, scalability and ease-of-use for large, high-performance scale-out datacenters.
"Voltaire continues to lead the InfiniBand switching market with the availability of the highest performing 40 Gb/s solution with the lowest latency and extreme scalability," said Asaf Somekh, vice president of marketing at Voltaire. "Moreover, our focus on delivering extra application performance and ease of management through advanced software development provides unique benefits to our customers helping them to better manage scale-out and meet their business objectives."
Part of Voltaire's 4th generation switch family, the Voltaire Grid Director 4700 features 324 ports of 40 Gb/s InfiniBand connectivity, with the option to double capacity to 648 ports using double-density fabric boards. The double-density fabric boards are the basis for the HyperScale architecture, a unique stackable architecture for building larger configurations into the hundreds and thousands of nodes, with lower latency and greater simplicity than alternative solutions.
Using Grid Director 4700 switches with HyperScale architecture, a customer can build a 1,296 node supercomputer with a fabric that delivers 20 percent lower latency than alternative solutions while consuming 50 percent fewer switch ports, 40 percent fewer cables and 33 percent less power and rack-space.
The 19U high Grid Director 4700 has less than 300 nanosecond port-to-port latency to accelerate performance of applications running on server and storage scale-out fabrics. The switch runs a smart distributed software architecture that delivers the best signal quality, enhanced performance optimization, and better resiliency, which are all key challenges in large-scale deployments. Moreover, its low 6.5-watts-per-port power consumption makes the switch a greener choice for energy-efficient datacenters.
UFM software is the industry's first comprehensive management software to optimize performance of large server and storage scale-out fabrics. Unlike other management software platforms that are device-oriented and involve tedious manual processes, UFM software provides IT managers with a logical view of their infrastructure. This bridges the traditional gap between servers, applications and fabric elements, creating a more effective and business-oriented way to manage and scale out high-performance fabrics.
The High Performance Computing Center Stuttgart (HLRS) was able to cut application latency in half upon installing UFM software on a 700-node multi-tenant cluster. They also were able to increase the volume of critical jobs by 2X through addressing inefficiencies that were previously undetectable and slashed the time needed for routine maintenance tasks from days down to minutes. More information about the UFM installation at HLRS is available at http://www.hlrs.de/systems/platforms/nec-nehalem-cluster/ and www.voltaire.com/HLRS.
"It is clear that the increasingly dynamic nature of workloads in nearly every compute domain demands a more sophisticated management solution than conventional frameworks that are more often than not geared toward topology and asset management," said Jeff Boles, senior analyst at The Taneja Group. "Whether the specific use case is workload management on HPC clusters, a backplane for hosted cloud compute, or a management layer for the virtualized enterprise, the next generation of dynamic, flexible infrastructure is completely dependent upon on a cornerstone of intelligent insight and sophisticated orchestration that can only be supplied by tools like Voltaire's Unified Fabric Manager software."
The Grid Director 4700 switch and UFM software are available today and can be ordered through OEM partners and resellers.
More information about the Grid Director 4700 is available at www.voltaire.com/GridDirector4700 and instructions on how to register for a free 30-day trial of Unified Fabric Manager software at is available at www.voltaire.com/UFM.
Demonstration at ISC'09
Voltaire will host the worldwide unveiling of the Grid Director 4700 40 Gb/s InfiniBand switch and the recently announced Voltaire Vantage 8500 10 Gigabit Ethernet switch at a special event at ISC '09 in Hamburg, Germany, on Tuesday, June 23, 2009, at 7:15 p.m. in booth #540.
Voltaire (NASDAQ: VOLT) is a leading provider of scale-out computing fabrics for datacenters, high performance computing and cloud environments. Voltaire's family of server and storage fabric switches and advanced management software improve performance of mission-critical applications, increase efficiency and reduce costs through infrastructure consolidation and lower power consumption. Used by more than 30 percent of the Fortune 100 and other premier organizations across many industries, including many of the TOP500 supercomputers, Voltaire products are included in server and blade offerings from Bull, HP, IBM, NEC, Rackable, SGI and Sun and provide the internal server-to-storage connectivity for the HP-Oracle Database Machine. Founded in 1997, Voltaire is headquartered in Ra'anana, Israel, and Billerica, Mass. More information is available at www.voltaire.com or by calling 1-800-865-8247.
Source: Voltaire Ltd.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?