Article Preview
TopIntroduction
Engineers and scientists today have two powerful options for applying additional computing and computer simulations to their product design, development, and research, in addition to their desktop workstations: high performance computing (HPC) servers, and HPC Clouds. The benefits of using these tools are huge: enormous cost savings; reduction in product failures early during design, development, and production; developing optimized processes; achieving higher quality products to keep existing and to gain new customers; and shortening time to market. All this leads to increased competitiveness and innovation.
However, less than 5% of manufacturers are using HPC servers or HPC clouds for computer simulations (Council of Competitiveness, 2010). The vast majority (in fact about 95%) perform virtual prototyping or large-scale data modelling still just on their desktop computers. But, 57% of these companies said that they have application problems that they can't solve because their desktops are too slow for the problems they want to solve or because geometry or physics are too complex and need more memory than is available from their desktop.
The first option of acquiring additional compute power is buying an HPC server which is many times faster than what engineers currently have available on their desk. However, for many organizations, especially small and medium size enterprises (SMEs) and small academic departments, buying a large HPC server is often not a viable alternative. In addition to the high cost of expertise, equipment, maintenance, software, and training, there are often long and painful internal procurement and approval processes, and additional skills and manpower are needed to operate and maintain such a system.
The second option for SMEs to experience the benefits from HPC is recently offered by cloud computing. HPC in the Cloud allows engineers and scientists to continue using their own desktop system for daily design and development work, and to submit the larger, more complex, more time-consuming jobs to the cloud. Additional benefits are on-demand access to ‘infinite’ resources, pay per use, reduced capital expenditure, greater business agility, higher-quality results, lower risk, lower product failure rate, and dynamically scaling resources up and down as needed.
In the following, we are presenting an overview of the status and trend of HPC in the Cloud for the manufacturing and scientific markets. We provide the status and trend of HPC in the Cloud for the software, hardware, and consulting service provider market. We include an outlook on how the UberCloud Experiment can accelerate the process of go-to-market and customer acceptance. Finally, we highlight the underlying Linux container technology, with a special focus on Docker containers, which reduces or even completely removes most of the current cloud computing roadblocks.