What's new

PARAM Supercomputer

IND151

BANNED
Joined
Oct 25, 2010
Messages
10,170
Reaction score
3
Country
India
Location
India
PARAM_Yuva.jpg








PARAM is a series of supercomputers designed and assembled by the Centre for Development of Advanced Computing (C-DAC) in Pune, India. The latest machine in the series is the PARAM Yuva.

Param means supreme in Sanskrit.[1]

After being denied Cray supercomputers[2] as a result of a technology embargo, India started a program to develop an indigenous supercomputer in collaboration with Russia.[3][4] Supercomputers were considered a double edged weapon capable of assisting in the development of nuclear weapons.[5] For the purpose of achieving self sufficiency in the field, the Centre for Development of Advanced Computing (C-DAC) was formed by the Department of Electronics in 1988. Vijay Bhatkar was hired as the Director of C-DAC.[2] The project was given an initial run of 3 years and an initial funding of 300,000,000 . Because the same amount of money and time was usually expended to secure the purchase of a supercomputer from the US.[2] In 1990, a prototype was produced and was benchmarked at the 1990 Zurich Supercomputering Show. It surpassed most other systems, placing second after US.[2]

The final result of the effort was the PARAM 8000. which was installed in 1991.[1] It is considered India's first supercomputer.

[edit]PARAM Series

[edit]PARAM 8000

Unveiled in 1991, PARAM 8000 used Inmos 8000 transputers. Transputers was a fairly new and innovative microprocessor architecture designed for parallel processing at the time. It was a distributed memory MIMD architecture with a reconfigurable interconnection network.[6] It had 64 CPUs.

[edit]PARAM 8600
PARAM 8600 was an improvement over PARAM 8000. It was a 256 CPU computer. For every four Inmos 8000, it employed an Intel i860 coprocessor.[6] The result was over 5 GFLOPS at peak for vector processing. Several of these models were exported.

[edit]PARAM 9900/SS
PARAM 9900/SS was designed to be a MPP system. It used the SuperSPARC II processor. The design was changed to be modular so that newer processors could be easily accommodated. Typically, it used 32-40 processors. But, it could be scaled up to 200 CPUs using the clos network topology.[6] PARAM 9900/US was the UltraSPARC variant and PARAM 9900/AA was the DEC Alpha variant.

[edit]PARAM 10000
In 1998, the PARAM 10000 was unveiled. PARAM 10000 used several independent nodes, each based on the Sun Enterprise 250 server and each such server contained two 400Mhz UltraSPARC II processors. The base configuration had three compute nodes and a server node. The peak speed of this base system was 6.4 GFLOPS.[7] A typical system would contain 160 CPUs and be capable of 100 GFLOPS[8] But, it was easily scalable to the TFLOP range.

[edit]PARAM Padma
PARAM Padma (Padma means Lotus in Sanskrit) was introduced in April 2003.[4] It had a peak speed of 1024 GFLOPS (about 1 TFLOP) and a peak storage of 1 TB. It used 248 IBM Power4 CPUs of 1 GHz each. The operating system was IBM AIX 1.5L.. It used PARAMnet II as its primary interconnect.[8] It was the first Indian supercomputer to the break the 1 TFLOP barrier.[9]



PARAM Yuva

PARAM Yuva (Yuva means Youth in Sanskrit) was unveiled in November 2008. It has a maximum sustainable speed (Rmax) of 38.1 TFLOPS and a peak speed (Rpeak) of 54 TFLOPS.[10] There are 4608 cores in it, based on Intel 73XX of 2.9 GHz each. It has a storage capacity of 25 TB up to 200 TB.[11] It uses PARAMnet 3 as its primary interconnect.[9]

PARAMnet

PARAMnet is a high speed high bandwidth low latency network developed for the PARAM series. The original PARAMnet used a 8 port cascadable non-blocking switch developed by C-DAC. Each port provided 400 Mb/s in both directions (thus 2x400 Mbit/s) as it is was a full-duplex network. It was first used in PARAM 10000.[1]

PARAMnet II, introduced with PARAM Padma, is capable of 2.5 Gb/s while working full-duplex . It supports interfaces like Virtual Interface Architecture and Active Messages. It uses 8 or 16 port SAN switches. The grid computing network GARUDA is also based on it.[12]

[edit]Operators

PARAM supercomputers are used by both public and private[11] operators for various purposes. As 2008, 52 PARAMs have been deployed, of these 8 are located in Russia, Singapore, Germany and Canada.[9] PARAMs have also been sold to Tanzania, Armenia, Saudi Arabia, Singapore, Ghana, Myanmar, Nepal, Kazakhstan, Uzbekistan, and Vietnam.[13]

[edit]Future Developments

In July 2009, it was announced that C-DAC was developing a new high-speed PARAM. It is expected to be unveiled by 2012. It will be attempting to break the 1 PetaFLOP barrier.

PARAM - Wikipedia, the free encyclopedia
 
If you think PARAM's fast, have a look at this-
EKA (supercomputer) - Wikipedia, the free encyclopedia
Designed in India, with a top speed of 178 TeraFlops, it was the fourth fastest supercomputer in the world and fastest in Asia, at the time of it's unveiling...........:azn:

SAGA-220 - Wikipedia, the free encyclopedia
This one is even more awesome. Built by ISRO to assist in Space launches it is currently the fastest Supercomputer in the nation with a peak output of 220 TeraFlops!!!:woot:
 
^^ i know about them

BTW latest PARAM will be attempting to break the 1 PetaFLOP barrier. (more than SAGA 220 and EKA )

In July 2009, it was announced that C-DAC was developing a new high-speed PARAM. It is expected to be unveiled by 2012. It will be attempting to break the 1 PetaFLOP barrier.
 
Nothing agains a Fujitsu K-Computer
You are right, nothing rivals K computer, witha speed of 10.51 Teraflops!!...........................except IBM Sequoia with a speed of 16 Teraflops!!!!:woot::woot:
 
^^ our PARAM 8000 supercomputer was placed 2nd in Zurich Supercomputering Show.

i hope we do something like this again
 

Country Latest Posts

Back
Top Bottom