September 11, 2013
BOSTON, Mass., Sept. 11 -- Terascala, the fast data company, today announced that the University of North Texas (UNT) has installed a Dell | Terascala HPC Storage Solution (DT-HSS 4.5). The Dell | Terascala solution is part of the university’s new cluster, Talon 2.0, a high-performance, campus-wide system that supports computational research.
The new HPC cluster is housed at UNT’s Central Data Center and replaces the original Talon cluster. Talon 2.0 is part of UNT's High Performance Computing Initiative, a project of Academic Computing and User Services (ACUS) – a division of the University IT (UIT). The cluster will support approximately 55 research groups and more than 350 faculty and student researchers in a variety of fields, with top utilization in chemistry, material sciences and physics.
UNT selected the Dell | Terascala storage appliance because they needed higher throughput and more storage capacity at an affordable price. Since the installation of the original Talon cluster in 2009, the number of researchers accessing the cluster has grown fivefold. The huge increase in processing loads resulted in I/O bottlenecks.
“To meet our rapidly growing storage needs, we were looking for a solution that would deliver the high I/O we require for the numerically intensive applications used by our researchers,” explained Scott Yockel, Ph.D., manager of HPC Services, UNT. “Talon 2.0 will enable researchers to do everything faster. Additionally, we’ll be able to do research we couldn’t even attempt before, such as conducting natural language processing on text from UNT’s 100TB and growing digital library.”
Terascala’s intelligent yet intuitive operating system, TeraOS, simplifies managing Lustre®-based storage, including failover of object and metadata server nodes. Yockel believes this capability will allow him to better manage the system because it lets him detect and fix problems before they become noticeable to the end user.
“TeraOS provides a view into the Lustre layer so UNT can see how the file system is being used, which is a tool they didn’t have before. The Terascala appliance also provides them with graphical representations of any failures in the system, along with alerts of potential problems,” explained Steve Butler, Terascala’s Chief Executive Officer. “Together, these capabilities will allow UNT to address minor problems before they snowball into major problems.”
Installation of the DT-HSS at UNT was quick and easy. TeraOS was up and running in less than a day. The 1.5 petabyte system utilizes 4TB disks and includes Lustre 2.1.5.
“We are pleased that UNT has selected Terascala to meet their HPC storage needs,” concluded Butler. “TeraOS optimizes workflows and simplifies the management, monitoring and tuning of high-performance storage. Our graphical view of the system, our analytics, and other performance features will enable UNT to provide their researchers with the high throughput storage they need to solve bigger problems faster.”
Terascala provides the operating system and analytics that transform block storage and controllers from Dell, EMC, and NetApp into an easy-to-manage storage appliance that delivers multiple gigabytes per second of throughput for HPC workloads. Terascala-powered storage appliances can reduce run times to hours instead of days or weeks, delivering unmatched value both in terms of initial investment and long-term operating costs.
Terascala is the fast data company. Terascala storage appliances dramatically accelerate the time to insight for organizations that rely on simulation, analysis, and modeling tools to bring new products and innovation to market. Exclusively available through strategic partners Dell, EMC, and NetApp, Terascala storage appliances provide on-demand throughput at multiple gigabytes per second while leveraging industry-leading storage platforms for long-term data protection. Learn more at http://www.terascala.com/.
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?