To discover, explore, and understand the end-to-end process of accessing and using HPC Clouds – such is the aim of the UberCloud HPC Experiment. With more than 800 organizations from 66 countries now participating, the operation demonstrates the viability of this alternative to traditional and costly on-premises high performance computing.

Prof. Dr. Wolfgang Gentzsch, Chairman, ISC Cloud, & Co-Founder, The UberCloud

As is well-known to this audience, the benefits for small and medium size enterprises (SMEs) of using high performance computing within their design and development processes can be huge: better quality products, high Return on Investment (ROI), reduced product failure early in design, shorten time to market… Potentially, this leads to increased competitiveness and innovation.

Why then are many engineers and scientists running simulations just on their workstations, although many are often dissatisfied with the performance? The main reason is that the alternatives are still coming with a lot of challenges for engineers and scientists.

Alternative one, buying an HPC server, comes with high Total Cost of Ownership (TCO) as has been regularly demonstrated by IDC: in addition to server cost, expenses for staffing, training, software, downtime, and maintenance easily sum up to ten times the server cost over three years. There are also long and painful internal procurement and approval processes. And for many, ROI is not clear, although it is expected to be huge according to countless recent studies.

The second alternative for SMEs to experience the benefits from HPC without having to buy and operate their own HPC system is recently offered by cloud computing. HPC in the Cloud (or HPC as a Service) allows engineers and scientists to continue using their own desktop system for daily design and development, and to submit (burst) the larger, more complex, time-consuming jobs into the Cloud. Benefits of the HPC Cloud solution (in addition to HPC in general) are among others on-demand access to virtually infinite resources, pay per use, reduced capital expenditure (CAPEX), greater business agility, not to mention dynamic resources scaling.

However, HPC as a Service (in the Cloud) comes with challenges of its own. It is a new business and working paradigm, for the manager as well as for the engineer. Security, privacy, and trust in service providers can be an issue. Conservative software licensing is only slowly including the pay-per-use service model. Internet bandwidth is often not able to accommodate heavy data transfer needs. Unpredictable costs of cloud computing can be a major problem in securing a budget for a given project. And finally, there is often a lack of easy, intuitive self-service access and use of remote resources.

Now, here comes the UberCloud HPC Experiment which provides a platform for engineers and researchers to discover, explore and understand the end-to-end process of accessing and using HPC as a Service, and to identify and resolve the roadblocks. Guided through a 22-step process, end-users, software providers, resource providers and HPC experts are collaborating in teams, jointly solving the end-user’s application in the Cloud.

Since July 2012, the UberCloud HPC Experiment has attracted 800+ organizations from 66 countries, allowing to build 122 teams so far, in CFD, FEM, Life Sciences and Big Data. Recently, the UberCloud University and a Virtual Exhibition have been added, and an Intel sponsored Compendium with 25 case studies has been published.

SMEs who are aiming to develop better products faster are invited to join the free UberCloud HPC Experiment.