March 19, 2013
FREMONT, Calif., March 19 — AMAX, a leading innovator of high performance computing (HPC) solutions, today announced that it is showcasing the ClusterMax SuperG High Performance Cluster at the 2013 GPU Technology Conference in San Jose, Calif., March 18-21.
Powered by NVIDIA Tesla K20X accelerators based on the NVIDIA Kepler compute architecture, the ClusterMax SuperG has been optimized for double precision floating point performance within a tight power envelope. It provides unprecedented real-world compute performance and breakthrough power-efficiency for climate & weather modeling, CFD, CAE, computational physics, biochemistry simulations, and computational finance applications.
The ClusterMax SuperG targets universities, national research labs, government, and enterprise high-performance computing environments where massive computational power is required. To meet these demands, AMAX offers a complete turnkey GPU-powered cluster that has been pre-configured, tuned, ready to deploy onsite and configurable with up to 108 NVIDIA Tesla K20X GPU accelerators. It delivers over 142 teraflops of peak double precision performance and over 426 teraflops of peak single precision performance across 290,304 CUDA cores per standard 42U cabinet. In addition, at three times higher performance per watt than clusters based on previous GPU architectures, ClusterMax SuperG enables more computational jobs to be completed in far less time.
"With the high-performance, energy efficient Tesla K20X accelerators and AMAX's dynamic cluster and server solutions, we are providing our customers with breakthrough performance and compute efficiency for double precision focused applications," said James Huang, HPC Product Manager at AMAX. "With NVIDIA's advanced SMX, Dynamic Parallelism, and Hyper-Q technologies, the performance increases we've seen in weather modeling and satellite imaging applications have simply been astounding."
The ClusterMax SuperG K20X powered GPU Cluster is powered by:
"Tesla K20X GPUs accelerators deliver unmatched acceleration for a range of compute-intensive HPC applications," said Sumit Gupta, general manager of the Tesla accelerated computing business at NVIDIA. "AMAX's ClusterMax SuperG systems provide researchers with a powerful and flexible platform to drive new waves of innovation and discovery."
Designed and manufactured in an ISO9001/14001/TL9000 certified and UL approved facility, AMAX ClusterMax clusters are backed by the highest quality in manufacturing standards with triple QA checkpoints, component- and server-level testing, and complete rack-integration testing. With manufacturing, logistics & support services spanning the globe, AMAX ClusterMax clusters can be deployed and supported world-wide, complete with onsite installation.
AMAX is showcasing the Tesla K20X powered ClusterMax SuperG at the GPU Technology Conference 2013 (booth No. 402), held at the San Jose McEnery Convention Center in San Jose, Calif., March 18-21. AMAX provides a wide-range of GPU solutions optimized for the NVIDIA Tesla K20X GPU accelerators, including cluster, server, and workstation solutions, and are available immediately. A FREE GPU Test Drive cluster is available for qualified applicants to remotely access an AMAX engineered, in-house Tesla K20 cluster.
Founded in 1979, AMAX specializes in engineering and manufacturing advanced Cluster, Server and Storage Solutions. Headquartered in Fremont, California, AMAX globally operates ISO:9001/14001/ TL9000 certified and UL approved facilities throughout North America and China to service the US, Canadian, LTAM, APAC and EMEA regions. AMAX's expertise drives two key divisions that deliver customized computing solutions to a wide range of industries: AMAX's Appliance Manufacturing Division provides efficient and top-of-the-line manufacturing solutions and global logistics to OEM customers while AMAX's Enterprise & High Performance Computing Division provides innovative and scalable cluster, server, and storage products developed for HPC, Cloud, Virtualization and Big Data applications.
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?