Here's the good news: government funding in both science & research and HPC will continue. There’ll be an evolution of HPC into more commercial environments, and from a technology perspective, there will be more focus and interest around HPC virtualisation and uptake of co-processors and accelerator technologies.
For example, IDC expects the overall HPC technical server market to grow at a healthy 7.4 per cent yearly rate with revenues, reaching $14.7 billion by 2018. Much of those sales will be driven by national science and research projects and direct bolstering of HPC infrastructure, which governments around the world seem increasingly keen to support.
In the UK, for example, Whitehall funding is traditionally granted to enable people to acquire technology rather than to develop it; the UK has been a follower rather than a leader relative to other countries. However, the government has shifted its view recently and begun to invest in research and development, adding to the intellectual capacity of the nation and creating new high value employment opportunities.
And the state does say it really does want to make Britain ‘the best place to do science and research’. In 2011, it injected £145 million into HPC, £270 million for quantum computing in December 2013, £73 million for big data in February 2014 - and made changes to the national curriculum in September 2014 to introduce software coding at a much younger age. In the past month alone, the Government has launched a £42 million Alan Turing Institute to research big data, committed £113 to expand the excellent work done at the Hartree Centre and announced funding for a £200 million science institute for the North of England concentrating on Materials Science.
Now, the bad news. Sadly, the UK’s efforts don’t quite yet match the funding efforts of other countries such as the US and China - even France and Germany. While certainly a notable change of stance and I can see this funding continuing, we do still have some challenges to overcome to really unelash HPC's potential for our economy.
Keeping Up With The Supercomputer Joneses
Whether an organisation is purchasing HPC power for science & research or for commercially driven motives, it’s essential to keep adopting the latest technological solutions to meet those bigger challenges I mentioned. The push toward Exascale is always quite exciting - the industry utopia for power and performance - but sadly, it isn’t going any faster today than it did 12 months ago because it depends on having millions upon millions of compute cores – the cost and heat output is prohibitive.
Co-processors have been consistently talked about over the past few years, not least by OCF. From my own perspective, for the UK, co-processors and accelerator technology, such as GPUs and Intel’s Phi, are still being tested, with people trying to find out how they can best use them. The reality is, they really aren’t being as well utilised as you might expect.
That said, it is proven that they do make applications run faster so sooner or later there will be more of an uptake of accelerator technology. Another technology worthy of a mention is HPC virtualisation. Virtualisation does have a negative impact on server performance, but it has a positive impact on manageability. Virtualisation technology now has far fewer overheads, so in the next 12-18 months people will be seriously considering a virtualisation layer on their HPC infrastructure because it simplifies the management.
Don't know about you, but I’ve never thought the future is not a rail track, fixed and straight; we follow a big wide road where we need to adapt, disrupt and be nimble. Organisations in the public and private sectors need to keep adopting the latest technological solutions to beat their challenges more efficiently and cost effectively. Vendors and integrators need to ensure they can deliver and support these new solutions. In the last few years, we have evolved our own HPC expertise to reflect the demand from customers – now offering HPC, HPC on demand, big data storage and management, plus predictive analytics solutions.
It’s the way of the HPC market: excting, promising, but with a lot of ups and downs. Nonetheless, the future is bright for both the technology and UK Plcs if we continue to try and get things right.
The author is Managing Director of high performance computing, Big Data and analytics integrator OCF, which has installed supercomputers at many UK centres including at Oxford and The Hartree Centre
(c) 2015 24n.biz