Two years ago I accepted a challenge by Anwar Osseyran from SURFsara in Amsterdam to cooperate on a book about industrial HPC. Not from the classical industrial sense of a supplier, but from the perspective of HPC usage by industry. There are very few centers in the world that serve industry in this way and, as a consequence, little understanding of the science and engineering depth accomplished by the private sector.
Hosting one of of the most powerful supercomputer centers in the world, Moscow State University is deeply committed to all aspects of supercomputing technology development. As a reflection of this mission, MSU has been a CUDA Center of Excellence (CCOE) for the last four years, using and disseminating GPU technology within Russian science, education and industry.
Increasing investment in research in many western countries is still a matter that sparks debate and maybe even controversy. But increasing research investment in Africa by an African government is a whole new ballgame.
With the year 2014 behind us, all my fellow HPC users, practitioners and of course enthusiasts will have reflected upon the conclusion of the last Supercomputing conference, affectionately known to all as SC14. It’s theme was the popular hashtag - #HPCmatters – and to me that represented several important elements.
Why does your two-year old smartphone feel like a 1975 Ford Pinto? The answer, of course, is Moore’s Law. Thanks to transistor shrinkage, the semiconductor components inside the latest handheld devices are twice as powerful as the ones in your now outdated (2013!) relic. Moore’s Law, of course, does more than drive smartphones sales. It has made the entire computer industry an economic juggernaut for the last 50 years.
Walking around SC14 in New Orleans, one can’t help but notice the density claims. Figures range upwards from 20kW with a number of impressive sounding 100kW cabinets on display too. Density is important to the future of HPC in terms of reducing energy, cost and inefficiency in interconnect, not to mention ensuring that operators can install their growing HPC systems within their real estate constraints.
My father, Hans Meuer, was a huge proponent of all kinds of ranking. With great pleasure he would recite the list of names of the best chess players along with their own ”Linpack rating“, the so-called Elo numbers, and enjoy his opponent’s astonishment afterwards. He definitely could impress those who understood that the Elo numbers, unlike the TOP500 ranking, were updated monthly.
This year at the SC conference, the iconic Beowulf Bash celebrates the 20-year history of Beowulf clusters, the 1994 achievement that would transform the HPC industry, lowering the cost-per-flop barrier for anyone ambitious enough to tackle the parallelism challenge. Today the parallel is palpable, as HPC faces new architectural revolutions that carry software implications of their own.