Opinion - Editorials   

Supercomputing breakthrough

For an indigenously built supercomputer to make it to the fourth spot in the world ranking of high performance computing (HPC) systems is a real breakthrough. For this, the band of researchers at the Tata Group’s Pune-based Computational Research Laboratory (CRL), who achieved this just 18 months after their facility was established, deserve the highest praise. While the Tata system has been built around off-the-shelf technologies, the top three spots have gone to entirely bought out proprietary supercomputing systems, such as the IBM’s BlueGene. A comparison of the private effort with the record of the Centre for the Development of Advanced Computing (CDAC), a public-funded supercomputing research facility, is unavoidable. Although CDAC made the first Indian teraflop supercomputer, PARAM Padma, in 2003, its successor is yet to achieve the kind of breakthrough in performance the Tata system has scored. The reasons for this include the ability of an innovative private enterprise to quickly mobilise resources to exploit the latest off-the-shelf processors and platforms to put together a world class HPC system.

This is not to say that access to latest technologies alone suffices to make a mark. If it was that simple, the Tata system could not have outperformed the systems of more advanced countries, which have also used the same processors and computational platforms and the same standard computer architecture. It is to the great credit of the Tata Group that it could bring together people from diverse fields — mathematics, physics, optoelectronics, cryogenics, computer engineering, and software — for this project. This could happen because of the reputation of Narendra Karmarkar (of the Karmarkar algorithm fame) who was instrumental in the creation of the CRL and the Tatas re-entering the HPC field. However, because of his quitting the Tata venture early this year, his revolutionary idea of using projective geometry for interconnection among nodes remains to be exploited. The Tata system still uses the traditional architecture in which performance tends to saturate as the number of nodes becomes large. The innovation the Tata researchers have made is in terms of software optimisation, routing technology, and cooling techniques to achieve higher speeds. The big challenge for the CRL team is to see how to bring Dr. Karmarkar’s revolutionary ideas to fruition, but in the absence of his combined mathematical, physical, and computational skill at the helm. While the Tatas would naturally wish to go commercial with this development, they would do well to maintain the investment in R&D towards the more ambitious goal. The government could also step in to underwrite part of the cost of purchasing the present Tata system for government establishments and stem the tendency to buy outright, at high cost, proprietary Cray-like supercomputers, which the Tata system outperforms.

Printer friendly page  
Send this article to Friends by E-Mail

Stories in this Section

Supercomputing breakthrough
U.S. slowdown’s global impact
The need for cautious optimists
Space launches and the cost factor
Robots, progress, and the human cost
The new web TV station
A horse in the house
Corrections and clarifications
Pakistan crisis
BJP’s southern debut
Nandigram challenge

Copyright © 2007, The Hindu. Republication or redissemination of the contents of this screen are expressly prohibited without the written consent of The Hindu