December 07, 2010
It's not too often that research-based HPC resources are made available to private firms, although in an age where cash-strapped publicly-funded universities must eek out alternative sources of revenue, public/private partnerships may be one way of financing expensive high-end computing systems. And what better way to make those resources available to outside entities than via the cloud, with the ease and convenience it promises.
If said public/private collaborations are going to be more common in the future, then consider Nanyang Technological University (NTU) one of the trendsetters. NTU announced plans to open up its high performance computing resources for commercial customers back in May, and according to an article at BizIT, the university is still on track to deliver on that goal. Not only does NTU want to make supercomputing resources available to private firms, it wants to make those resources available on-demand using a cloud computing infrastructure. In order to make that vision a reality, NTU is collaborating with IBM on solutions that will give corporate users access to HPC in a convenient cloud-based delivery platform.
Associate Dean of NTU's College of Engineering and the project lead,dSoh Yeng Chai, shared the significance of the project with BizIT:
"Cloud computing will enable the NTU faculty, research staff and students to access HPC resources easily and will accommodate different computing demands and workloads. This will place NTU at the forefront of HPC, and hopefully encourage large organisations and SMBs to leverage on HPC's cloud computing capacity."
The project is ramping up. Although it's not yet in the active marketing stage, Professor Soh predicts that private firms with a need for HPC-level resources will begin to show interest early next year. Currently, NTU and IBM are ironing out any technical issues so that the project may have a successful debut. Initial target areas will be interactive digital media (IDM) and business analytics, selected for their potential to benefit Singapore's developing technology sector.
The collaboration between the two partners got a jumpstart in November of 2009 when NTU became a charter member of the IBM Cloud Academy, a global initiative that allows members to innovate at the intersection of education and cloud computing. Involved parties are working toward the convergence of HPC and cloud computing with the aim of developing novel technologies and research methods.
Professor Soh examines the types of endeavors that will benefit from the new model:
"This initiative will enable the entire faculty of NTU to embark on HPC and cloud computing projects relevant to their departments. That will in turn support various industries such as engineering, mathematical sciences, medical/pharmaceutical, and finance-related research."
Nanyang Analytics is the name of the IBM-based machine that will be supporting these applications. With 28-teraflops of power, 2,400 compute cores together with 700 terabytes of storage capacity, this is one of the fastest supercomputers in Southeast Asia.
Full story at Business Times
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?