April 18, 2013
NEW YORK, April 18 — Cycle Computing, the leader in utility HPC software, today announced the release of DataManager, a new solution that schedules and manages the secure transfer and storage of data sets needed for large scale computations. DataManager seamlessly automates data archival and retrieval from lower cost cloud storage solutions, such as Amazon Glacier. This enables users to more quickly and cost-effectively conduct a wide range of compute and data intensive workloads in areas such as life sciences, financial services, manufacturing, academia and energy.
HPC workloads from molecular modeling to risk simulation require analysis of increasingly large volumes of data. Access to affordable compute has driven down the cost of generating this data, faster than the cost to store it. As a result, organizations want to reliably and securely leverage internal and cloud-based storage solutions to ensure their users have local access to the data needed to run these complex workloads.
"We introduced DataManager to meet the growing need for scientists to more efficiently manage large amounts of data to foster new discoveries in their fields," said Jason Stowe, CEO of Cycle Computing.
"Researchers now have the ability to control the transfer of large computation result, to and from various internal and cloud-based storage. With DataManager, intelligent scheduling and automation can keep data in the right place at the right time for reference and future research."
Cycle uses DataManager to automatically move data, using a variety of open source and 3rd party transfer protocols and appliances, to utility HPC environments like the recently announced utility HPC cluster for a Top 10 Pharma. This 10,600 server utility supercomputer was created in 2 hours, ran 39 years of computing on Amazon EC2 in 9 hours, for $4,372, using one Opscode Chef server to automate configuration management.
"DataManager does for automating data scheduling at scale what Opscode Chef does for configuration management in utility HPC clusters," added Mr. Stowe.
Key benefits of DataManager include:
· Data elasticity: Efficiently move data from endpoint to endpoint, such as a local file system to Glacier or a remote file system, based on the specific date and time it is needed.
· Data awareness and usage chargeback: Usage statistics enable accurate accounting and chargeback and user awareness of cost savings.
· Client-side security and encryption: Locally control encryption and key management for data in transit and at rest in Amazon Glacier.
· Lower latency and cost: Make cost-effective cloud archival more readily accessible to free up "hot" storage and avoid the need to buy additional on-premise devices.
DataManager is now available for general use after being successfully tested and used in beta by two leading pharmaceutical companies and two of the top five life insurance organizations.
About Cycle Computing
Cycle Computing is the leader in Utility HPC software. As a self-funded, profitable software company, Cycle makes award-winning products that accelerate breakthroughs at any scale. From 50 to 50,000+ cores against up to 100s of TBs of data, the world's brightest minds rely on Cycle software to tackle their most challenging computational problems in less time, for less cost than ever before possible. Cycle software provides the single pane of glass from which customers and partners easily orchestrate complex workloads and data across a right-sized set of internal and external HPC resources. Cycle helps clients maximize existing infrastructure and speed computations on servers, VMs, and on-demand in the cloud, like the 10,000-core cluster for Genentech, the 30,000+ core cluster for a Top 5 Pharma, and the 50,000-core cluster for Schrödinger covered in Wired, TheRegister, BusinessWeek, Bio-IT World, and Forbes. Since 2005, starting with three initial Fortune 100 clients, Cycle has grown to deploy proven implementations at Fortune 500s, SMBs and government and academic institutions including JP Morgan Chase, Purdue University, Pfizer and Lockheed Martin.
Source: Cycle Computing
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?