June 02, 2010
Brings system integration and parallel programming services together in an attempt to ease barriers in global HPC adoption
HAMBURG, and NEW DELHI, India, June 2 -- HPC Links Pvt. Ltd. announced today that it is partnering with Supermicro and NVIDIA and using Intel's manycore technology to offer a new HPC cluster platform named SuperLinks. The SuperLinks platform is available in a wide range of peak performance, starting with 1TF boxes, to a 30-60 TF rack extending upto 3-6 PF high end HPC clusters for HPC Links' customers worldwide.
SuperLinks is a hybrid, multicore cluster supercomputing platform with CPU/GPU combination, superior power efficiency and management, balanced memory, IO and network bandwidth optimized for our customers' most demanding HPC applications. These solutions are built using leading industry standard hardware components such as Supermicro's Sueprblade that incorporates Intel Gulftown and NVIDIA Fermi processors. Both Linux and Windows HPC Server software environments are supported on SuperLinks.
SuperLinks brings additional value to the customers in the form of HPC Links' parallel application programming, research, development, scaling and optimization services, including cross platform application migration. HPC Links' unique, multidisciplinary parallel programming skill pool strives to find a solution for HPC users' pressing application performance needs.
Founder and CEO of HPC Links, Dr. Ashwini K Nanda said, "Major HPC infrastructure vendors today provide integrated systems and datacenter services. But the buck stops there. Broader adoption of HPC demands that users have easier access to parallel programming skills and application availability. HPC Links promises to go the extra mile for our customers in porting and optimizing their applications on the SuperLinks platform."
"The HPC Links team members certainly have the experience of large systems, and combining with Supermicro the best in the class server platforms. With a superior level of understanding customers' needs, HPC Links brings together the complexities of both hardware and software integration process to fulfill the needs." said Dev Tyagi, General Manager of Supermicro UK, "HPC users appreciate the technical strength of the SuperLinks platform combined with HPC Links' versatile parallel application programming services."
"The world has truly woken up to the outstanding performance improvements which hybrid HPC can bring to the most challenging parallel applications," said Daniel Saison, NVIDIA sales director Middle East, Africa and India. "With their SuperLinks platform HPC Links is making the compute power of NVIDIA's Fermi architecture even more attractive and accessible to a wide range of HPC users."
About HPC Links
HPC Links provides leading edge services, systems and solutions in the areas of multicore, cloud and high performance computing to its worldwide customers. The new venture has been formed by industry veterans who in the past played key roles in the development of several top supercomputers around the world -- the LANL Roadrunner machine in the US, first to cross the petaflop barrier, the Barcelona Marenostrum machine, fastest in Europe 2004-06, and the CRL Eka machine, Asia's fastest 2007-08, India's fastest 2007-10. HPC Links is based out of both India and the US. HPC Links' unique, interdisciplinary skill pool covers all areas of computer science and major HPC application domains and continuously strives to make parallel programming easier for their scientific, engineering and business customers. For further info, visit www.hpclinks.com and send your queries to email@example.com.
Source: HPC Links Pvt. 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?