March 05, 2013
This is an open invitation to members of our HPC, CAE, life sciences, and big data communities to join us for this third round of the UberCloud Experiment, where we will jointly apply the cloud computing services model to compute and data-intensive workloads on remote cluster computing resources.
To all industry end users, HPC experts, compute resource and software providers: The UberCloud HPC Experiment is making HPC available as a service, for everybody, on demand, at your fingertips, by exploring the end-to-end process of using remote computing resources as a service, and learning how to resolve the many roadblocks.
The HPC Experiment started in July last year with 160 organizations and 25 teams, helping industry end-users to explore access and use of remote computing resources available from HPC centers and from the cloud. Detailed results have been published in the final report and are available upon registration. Then, the second, much improved round of the experiment started last December, with more than 350 organizations and 35 teams as of today and will conclude at the end of March. Now, for round 3 starting April 1, we invite industry end-users, software providers, HPC experts, and resource providers from HPC centers and from the cloud, to join the experiment and collaboratively explore the end-to-end process of remote HPC as a Service, hands on, in 22 well-defined guided steps.
Why Are We Performing this Experiment?
In the US alone, there are over 360,000 small and medium-size manufacturers, many of them using workstations for their daily design and development work, with the need however for more computing, from time to time. Buying an expensive HPC cluster is usually not an option, and renting computing power from HPC centers or cloud service providers still comes with severe roadblocks, such as the complexity of HPC itself, intellectual property and sensitive data, lengthy and expensive data transfers, conservative software licenses, performance bottlenecks from virtualized resources, user-specific system requirements, and missing standards and lack of interoperability among different clouds. Last but not least the currently exploding numbers of different service offerings in the cloud make it difficult for engineering end-users to locate the best-suited solutions or services for their applications' requirements.
On the other hand, by successively removing these roadblocks, the benefits of using remote computing resources are extremely attractive, for example: no lengthy procurement and acquisition cycles; shifting some budget from CAPEX to OPEX; gaining business flexibility i.e., getting additional resources on demand, from your workstation, when you need them, at your fingertips; and scaling resource usage automatically up and down according to your actual needs.
The Benefits of Participating in the Experiment
The UberCloud HPC Experiment has been designed to drastically reduce many of the barriers mentioned above. By participating in this experiment and moving their engineering or big data application onto a remote computing resource, end-users can expect several real benefits, such as:
On the other hand, the list of benefits for service providers (software, resources and expertise) to participate in this experiment is similarly rich. To name a few benefits for service providers: getting immediate constructive feedback from the experiment end-users on how to fine-tune your services; gaining deeper and practical insight into a new market and service-oriented business model; risk-free no failure experimenting allowing you to improve your services during the experiment, on the fly; getting in touch with potential customers; and gaining public attention by becoming part of widely published success stories. Last but not least, all service providers are encouraged to make use of the interactive UberCloud Exhibit to present their services to the wider HPC, CAE, life sciences, and big data communities, in an interactive experience.
Teams of Round 1 and Round 2
A sampling of team names from round 1 of the experiment reflects the wide spectrum of applications: anchor bolt, resonance, radiofrequency, supersonic, liquid gas, wing flow, ship hull, cement flow, sprinkler, space capsule, car acoustics, dosimetry, weathermen, wind turbines, combustion, blood flow, chinaCFD, gas bubbles, side impact, and colombiaBio. Round 2 teams were equally varied with names such as stent simulation, medical devices, photorealistic rendering, ventilation benchmark, roof air inlet, heterogeneous human body, two-phase flow, weather and climate, Hadoop for telecoms, combustion in IC engines, biological diversity, remote viz, acoustic field, electromagnetics, noise vibration, hybrid rocket motor, drifting snow, smoke flow, heat exchanger, gas turbine, bicycle flow, genomic data analysis.
Now We Are Inviting You to Join Round 3
Round 3 will be running from April until the end of June. We are expecting about 400 organizations to form 50 new teams built around industry end-users' applications running on remote computing resources. In addition to our current focus areas of HPC, CAE, and the life sciences we now also invite big data end users and software, services, and consulting providers to join this experiment, for the reasons that have been outlined in this article. The experiment will be conducted more formally, with more automation, and will be even more user-friendly. The 22-step end-to-end process will be better guided, and the Basecamp 'team rooms' for collaboration will be even more comfortable. We will also provide three levels of support: front line (within each team), 2nd level (UberCloud mentors), 3rd level (software & hardware providers), and finally further grow the interactive UberCloud Exhibit services directory.
And Finally, Why Would You Want to Join the Experiment?
In summary, there are many good reasons for joining this experiment for the next three months. Among them: HPC is complex – it is easier to tackle this complexity within our community; the barriers of entry into HPC as a Service through an experiment are low; learning by doing – experimenting without risk – no failure; becoming an active part of this growing community; exploring the end-to-end process of accessing remote computing resources; and learning how this fits into your research or business direction in the near future.
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?