Bangalore ahead of other cities in supercomp race

 Bangalore, India’s IT capital, is doing well not only in IT services, but also in the kind of computing systems it has.

In the latest ranking of Top 500 supercomputers in India, undertaken by the Indian Institute of Science (IISc), Bangalore tops the list. While the City has seven systems, the closest competitor is Pune with six. Surprisingly Mumbai has just one, Delhi and Hyderabad have two each and Kolkata three. Most other cities have one.

The list reflects the number of supercomputers in a single city, based on which ranking is done. The institutions that have supercomputers in Bangalore are highly specialised – The Fourth Paradigm Institute, IISc, Aeronautical Development Agency, NAL, TIFR and JNCASR. IISc alone has three systems, one of which is in the Supercomputer Education and Research Centre (SERC).

Prof Sadagoppan of the International Institute of Information Technology had told this correspondent in an interview that Bangalore was topping the list because of its high number of science institutions, highly specialised departments and centres, and a large number of scientific personnel in just one city, which has given it the status of being the science capital.

 The combined supercomputing capacity of the country is 3.02 Peta Flops according to the list. The performance criteria taken up for ranking is 12 Terra Flops and the average performance of the entire supercomputing capacity is 100.79 TFlops. Hewlett-Packard is the most popular system among the various institutions.

Scientists say that the supercomputers come into use from enabling a safe flight (because your personal safety while flying depends on how a supercomputer has designed the aircraft) to deciding when you need to take a holiday (like in Uttarakhand, by analysing weather statistics to show whether the conditions are ideal or not).

These computers with a massive number of processors running into thousands enable you to make millions of calculations at great speed. You can sift through vast amounts of data in very less time and make rapid observations in the field of science. The supercomputers first came into use in the 1960s when launched by Seymour Cray at Control Data Corporation (CDC), Cray Research.

 In the 1970s, supercomputers used few processors, but by the 1990s, machines with thousands of processors made their appearance and, by the end of the 20th century, massively parallel supercomputers with tens of thousands “off-the-shelf” processors surfaced.

Such computers, says Prof Sadagoppan, play a vital role in computational science and computational intensive tasks in fields like quantum mechanics, weather forecasting, climate research, oil and gas exploration and molecular modeling. The IBM Blue Gene/P computer, for instance, has been used to simulate a number of artificial neurons equivalent to approximately one percent of a human cerebral cortex, containing 1.6 billion neurons with approximately 9 trillion connections.

It is impossible to track and map all the neurons – and here is where supercomputers come in – they enable us to create a form of the neuron cluster in human brains. Neuron analysis, one among many other tasks, helps in understanding the source of brain-related ailments.