Thursday, May 5, 2011

India's fastest supercomputer by ISRO

Hi guys.. Indians are done it again. Though Indian is having several problems such as Corruption,black money etc,It wont affact the growth of a India.And ISRO has been proving it from years together.Hats off to ISRO.


Indian Space Research Organisation has built a supercomputer, which is to be India's fastest in terms of theoretical peak performance of 220 TeraFLOPS (220 Trillion Floating Point Operations per second).



The supercomputer "SAGA-220", built by the Satish Dhawan Supercomputing Facility located at Vikram Sarabhai Space Centre (VSSC), Thiruvananthapuram at a cost of about Rs 14 crore was inaugurated by K Radhakrishnan, Chairman ISRO at Vikram Sarabhai Space Centre (VSSC), Thiruvananthapuram.

The new Graphic Processing Unit (GPU) based supercomputer, "SAGA-220" (Supercomputer for Aerospace with GPU Architecture-220 TeraFLOPS) is being used by space scientists for solving complex aerospace problems.

"SAGA-220" is fully designed and built by Vikram Sarabhai Space Centre using commercially available hardware, open source software components and in house developments. The system uses 400 NVIDIA Tesla 2070 GPUs and 400 Intel Quad Core Xeon CPUs supplied by WIPRO with a high speed interconnect. With each GPU and CPU providing a performance of 500 GigaFLOPS and 50 GigaFLOPS respectively, the theoretical peak performance of the system amounts to 220 TeraFLOPS, the statement said.




ISRO’s existing supercomputer is only 70 teraflops, whereas this supercomputer can be ramped much higher than 220 teraflops. According to ISRO, the present GPU system offers significant advantage over the conventional CPU-based system in terms of cost, power and space requirements. The total cost of this supercomputer is about Rs 14 crore.


The present GPU system offers significant advantage over the conventional CPU based system in terms of cost, power and space requirements, it said. The system is environmentally green and consumes a power of only 150 KW. This system can also be easily scaled to many PetaFLOPS (1000 TeraFLOPS).

No comments:

Post a Comment