Indian government is accelerating the process of supercomputing in the country with 70 supercomputers soon to forecast weather and use them for defence applications, in a major step to modernize its capabilities of prediction of natural disasters and defence emergencies in the future.
To be equipped with an operational speed ranging from from 0.5 to 20 petaflops, these supercomputers will speed up to 50 petaflops. One Petaflop is 10^15 floating point operations per second.
The entire budget for the project is initially set at Rs.4,500 crore and it will be jointly set up by the Department of Science and Technology (DST) and Department of Information and Technology (DIT).
The supercomputers, currently confiend to PARAM supercomputers Delhi, will be set up in different parts of the country including Visakhapatnam, where crucial defence establishments are set up, according to Ashutosh Sharma, secretary of DST.
To be operation from 2022, these super computers will bring the entire weather and defence systems under one centralised framework and access will be given to researchers from government institutions in computer science, defence simulation, bio-research, material sciences and earth science, said the DST.
The government may also Indian private sector research organisations to make use of the supercomputers depending on their participation in national defence-oriented networks.
The entire super computers network will also employ huge number of researchers and technical staff, increasing the demand for computer scientists and specific field-based researchers in the future.
Eversince 1960, supercomputers came into vogue with Seymour Cray at Control Data Corporation (CDC), Cray Research and subsequently by other companies but bearing his name or monogram.
In the 1970s supercomputers used only a few processors, which accelerated in the 1990s to thousands of processors in supercomputers made by the US and Japan.
Fujitsu’s Numerical Wind Tunnel supercomputer used 166 vector processors in 1994 with a peak speed of 1.7 gigaFLOPS (GFLOPS) per processor, while Hitachi’s supercomputer SR2201 reached a peak of 600 GFLOPS in 1996 by using 2048 processors using a fast three-dimensional crossbar network.
The US-based Intel Paragon with 1000 to 4000 Intel i860 processors was ranked the fastest in the world in 1993. By the turn of the 20th century, massive parallel supercomputers with tens of thousands of “off-the-shelf” processors became the norm.
Currently, China’s Tianhe-2 supercomputer is the fastest in the world at 33.86 petaFLOPS (PFLOPS), or 33.86 quadrillion floating point operations per second.