The kind of HPC and supercomputing that makes the news is the truly mind-blowing, modeling the galaxy, simulating climate change, that kind of stuff. But a little less glamorous are the more mainstream applications being done on high-end computer equipment in fields such as financial services and business intelligence. Throughout the history of HPC, there has been a trickle down effect as what was once HPC enters the mainstream HPC arena, broadening its user base.
In a recent Register article, Andrew Buss of Freeform Dynamics makes the case that there are lessons from the specialized HPC realm that can be applied to the more generalized enterprise IT arena.
A deficit in skills is one of the major limiting factors to better appropriation of HPC by the enterprise base according to Buss:
From our research, it is clear that the impact of HPC on mainstream IT is less to do with technology, and more to do with skills and operations management. Commodity hardware is widely regarded as suitable for HPC, with custom hardware reserved for the most demanding tasks. One of the reasons for this, apart from the direct cost advantage, is the pool of available skills. This has undoubtedly broadened the use of HPC, but the lack of high-end HPC skills has the potential to be a barrier to translating HPC experience into more general IT performance improvement.
To be accessible to a wider IT audience, platforms and software need to become more user friendly, or companies will have to develop the necessary skillsets in their employees. To that end, Buss argues that two of the most important areas are networking fabrics and storage systems. Other HPC-type skills that will be suitable for more generalized system implementation come from the fields of virtualization and power management.