November 20, 2006
It's fall in beautiful Tampa, Florida and the Grid and high performance computing communities are again gathered to discuss the state-of-the-state in HPC-related technologies and solutions. The Open Grid Forum (OGF) community has deep roots in HPC and the Supercomputing conference and many of our members contribute their time and effort to help make this gathering a great and very productive event.
Having thoroughly enjoyed and been inspired by Ray Kurzweil's keynote and the OGF eScience, Board and Advisory Committee meetings during the week, I was finally able to break away and walk the show floor. It is always interesting to talk to the many innovators at this event -- comparing notes and catching up on the latest information.
One of the highlights for me at SC06 was the HPC interoperability demonstration at OGF member booths in the exhibit hall. This successful demonstration showed heterogeneous integration of HPC Grid solutions using OGF's Open Grid Services Architecture (OGSATM) HPC Profile specification. The OGSA HPC Profile leverages common Web Services specifications and existing OGF specifications (JSDL, BES). It enables interoperability between multiple HPC middleware platforms and allows application and middleware software providers to target multiple HPC systems via a single protocol.
The OGSA HPC Profile began as a set of observations from several leaders within the OGF community. Their perspective was that successful standardization efforts often address small, well-defined and modular subject areas while taking into account broader and sometimes longer term goals. By starting with simpler designs that can be enhanced over time, fast progress can be made and capabilities can then evolve in an incremental fashion. Bringing together this fast-track design approach with existing specifications already broadly adopted within the industry (WS-Basic Profile) and ones that were maturing rapidly (OGF JSDL and BES specifications) enabled the OGSA HPC Profile to gain traction quickly. From the germ of an idea, to the establishment of the OGSA HPC Working Group, to the demonstration at SC06, this was a team of people focused on delivery and supported by leaders within the broader Grid community.
OGF and partner organizations that participated in the demonstration included Altair Engineering, CROWN, EGEE, Fujitsu Labs of Europe, Genesis II, Globus Alliance, HP, Microsoft, OMII-UK, Platform Computing, Tokyo Institute of Technology, and University of Virginia. Demonstration usage scenarios include web applications where users execute applications through their web browser; rich client workbench applications running design simulations; and workflow engine applications chained together into a workflow of computing tasks. The demonstration showed how users can benefit by:
Interoperability is critical to harnessing the capabilities of distributed HPC clusters and grids to enable scientific discovery and business advantage for organizations of all sizes. More and more customers want to increase Grid adoption across silo'd Grid deployments with an eye towards utilizing grids across and between organizations. Industry standards are critical to these deployments as most will include software products from more than just a single vendor.
This demo highlights the value of OGF standards in deploying multi-site, multi-vendor grids for HPC customers and illustrates the progress being made by OGF and our members to produce specifications that enable interoperability and accelerate adoption.
I want to thank the OGF members and groups involved in this effort (JSDL-WG, OGSA-BES-WG, OGSA-HPCP-WG) along with the organizations who worked so hard to support their efforts. OGF intends to build on the momentum achieved with the OGSA HPC Profile in several ways. We will continue to mature and/or address limitations in the current specifications. We will also continue our interoperability testing with the various specifications that make up the HPC profile and its improvements. We will also look to identify profile opportunities that leverage the experience of the OGSA HPC Profile -- allowing OGF to deliver simple, yet effective specifications that the Grid community has determined to be of high value faster with a similar collaborative spirit and focus on results.
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.