Recently, China claimed to be leader in Supercomputing by introducing Tianhe-1A, a supercomputer which has peak performance of 2.566 PFLOPS, powered by 14,336 Intel Xeon CPUs and 7,168 Nvidia Tesla M2050 GPUs with a new interconnect fabric of Chinese origin, situated at National Supercomputing Center, Tianjin, China. How can it's neighbor country can be far behind?
On Monday, 2-May 2011, Indian Space Research Organisation has announced that they 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).
Named as 'SAGA-220', this supercomputer is indigenous design built by the Satish Dhawan Supercomputing Facility located at Vikram Sarabhai Space Centre (VSSC), costed about Rs 14 crore ($ 3.1 Million), built with an aim to solve complex aerospace problems.
'SAGA-220' uses 400 NVIDIA Tesla 2070 GPUs and 400 Intel Quad Core Xeon CPUs supplied by WIPRO with a high speed interconnect uses only 150 KW of power.
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.
As its built on commercially available hardware, open source software components, the present GPU system offers significant advantage over the conventional CPU based system in terms of cost, power and space requirement.
But the thing is US built supercomputer with similar capabilities long back in 2005.
Via: [DC]
On Monday, 2-May 2011, Indian Space Research Organisation has announced that they 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).
Named as 'SAGA-220', this supercomputer is indigenous design built by the Satish Dhawan Supercomputing Facility located at Vikram Sarabhai Space Centre (VSSC), costed about Rs 14 crore ($ 3.1 Million), built with an aim to solve complex aerospace problems.
'SAGA-220' uses 400 NVIDIA Tesla 2070 GPUs and 400 Intel Quad Core Xeon CPUs supplied by WIPRO with a high speed interconnect uses only 150 KW of power.
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.
As its built on commercially available hardware, open source software components, the present GPU system offers significant advantage over the conventional CPU based system in terms of cost, power and space requirement.
But the thing is US built supercomputer with similar capabilities long back in 2005.
Via: [DC]
No comments:
Post a Comment