PARAM

PARAM is a series of supercomputers designed and assembled by the Centre for Development of Advanced Computing (C-DAC) in Pune, India.[1][2] PARAM means "supreme" in the Sanskrit language, whilst also creating an acronym for "PARAllel Machine".[1] As of November 2020 the latest and fastest machine in the series is the PARAM Siddhi AI which ranks 63rd in world with an Rpeak of 5.267 petaflops.[3]

History

C-DAC was created in November 1987, originally as the Centre for Development of Advanced Computing Technology (C-DACT).[4] This was in response to issues purchasing supercomputers from foreign sources.[5] The Indian Government decided to try and develop indigenous computing technology.[6]

PARAM 8000

The PARAM 8000 was the first machine in the series and was built from scratch.[2] A prototype was benchmarked at the 1990 Zurich Super-computing Show: it demonstrated that India had the second most powerful, publicly-demonstrated , supercomputer in the world after the United States.[7]

A 64-node machine was delivered in August 1991.[2][1] Each node used Inmos T800/T805 transputers.[1] A 256-node machine had had a theoretical performance of 1GFLOPS, however in practice had a sustained performance of 100-200MFLOPS.[1][2] PARAM 8000 was a distributed memory MIMD architecture with a reconfigurable interconnection network.[8]

The PARAM 8000 was noted to be 28 times more powerful than the Cray X-MP that the government originally requested, for the same $10 million cost quoted for it. [9]

Exports

The computer was a success and was exported to Germany, UK and Russia.[10] Apart from taking over the home market, PARAM attracted 14 other buyers with its relatively low price tag of $350,000.[11]

The computer was also exported to the ICAD Moscow in 1991 under Russian collaboration.[12][13][14][15]

PARAM 8600

PARAM 8600 was an improvement over PARAM 8000. In 1992 C-DAC realised its machines were underpowered and wished to integrate the newly released Intel i860 processor.[16] Each node was created with one i860 and four Inmos T800 transputers.[8][2][1] The same PARAS programming environment was used for both the PARAM 8000 and 8600; this meant that programs were portable.[2][1] Each 8600 cluster was noted to be as powerful as 4 PARAM 8000 clusters.[1]

PARAM 9000

The PARAM 9000 was designed to be merge cluster processing and massively parallel processing computing workloads.[17] It was first demonstrated in 1994.[5] The design was changed to be modular so that newer processors could be easily accommodated.[8] Typically a system used 32–40 processors, however it could be scaled up to 200 CPUs using the clos network topology.[8] The PARAM 9000/SS was the SuperSPARC II processor variant,[18] the PARAM 9000/US used the UltraSPARC processor, and the PARAM 9000/AA used the DEC Alpha.[19]

PARAM 10000

The PARAM 10000 was unveiled in 1998 as part of C-DAC's second mission.[5] PARAM 10000 used several independent nodes, each based on the Sun Enterprise 250 server; 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.[20] A typical system would contain 160 CPUs and be capable of 100 GFLOPS[21] But, it was easily scalable to the TFLOP range. Exported to Russia and Singapore.[22]

PARAM Padma

PARAM Padma (Lotus in Sanskrit) was introduced in December 2002.[5] It had a peak speed of 1024 GFLOPS (about 1 TFLOPS). The machine used IBM POWER4 processors.[5] PARAM Padma was the first Indian machine ranked on a worldwide supercomputer list.[5]

PARAM Yuva

PARAM Yuva (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.[23] 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.[24] It uses PARAMNet-3 as its primary interconnect.

Param Yuva II

PARAM Yuva II was unveiled on 8 February 2013. It was created in three months at a cost of 160 million (US$2 million). It performs at a peak of 524 TFLOPS, about 10 times faster than the present facility, and will consume 35% less energy as compared to the existing facility. According to CDAC, the supercomputer can deliver sustained performance of 360.8 TFLOPS on the community standard LINPACK benchmark.[25][26] It is the first Indian supercomputer achieving more than 500 teraflops.[27][28][29]

PARAM ISHAN

Inaugurated at IIT Guwahati Campus on 19 September 2016.[30][31]

PARAM Brahma

It is a supercomputer offering a computational power of 850 TeraFlop with 1 PetaByte storage capacity. It is one of the supercomputers built in India under NSM, co-funded by Ministry of Electronics and Information Technology and Department of Science and Technology. Centre for Development of Advanced Computing (C-DAC) and Indian Institute of Science, Bengaluru, are steering this mission. 'PARAM Brahma' is supported by a first-of-its-kind cooling system called direct contact liquid available in India. This cooling system makes effective use of thermal conductivity of liquids, namely water, in maintaining the temperature of the system during operations.[32] As of 2020 it is available at IISER Pune.

PARAM Siddhi-AI

Siddhi-AI is a high performance computing-artificial intelligence (HPC-AI) and by far the fastest supercomputer developed in India with an Rpeak of 5.267 PFlops and 4.6 PFlops Rmax (Sustained). Artificial intelligence aids research in advanced materials, computational chemistry & astrophysics, health care system, flood forecasting and applications related to COVID-19 through faster simulations, medical imaging and. genome sequencing. In November 2020, PARAM Siddhi-AI ranked 63rd among most powerful supercomputers in the world. It is built on the NVIDIA DGX SuperPOD reference architecture networking along with C-DAC’s indigenously developed HPC-AI engine, software frameworks and cloud platform.[3]

Supercomputer summary

PARAM Timeline
Name Release Year CPUs Technology Speed
PARAM 8000 1991 64 Inmos T800 Transputers, Distributed Memory MIMD
PARAM 8600 256 Intel i860 5 GFLOPS
PARAM 9900/SS 32 to 200 SuperSPARC II, clos network
PARAM 9900/US 32 to 200 UltraSPARC, clos network
PARAM 9900/AA 32 to 200 DEC Alpha, clos network
PARAM 10000 1998 160 Sun Enterprise 250, 400Mhz UltraSPARC UltraSPARC II processor 6.4 GFLOPS
PARAM Padma 2003 1TB storage, 248 IBM Power4 – 1GHz, IBM AIX 5.1L, PARAMNet 1024 GFLOPS
PARAM Yuva 2008 4608 cores, Intel 73XX – 2.9 GHz, 25 to 200 TB, PARAMnet 3 38.1 to 54 TFLOPS
PARAM Yuva II 2013 524 TFLOPS
PARAM Kanchenjunga[33] 2016 15 TFLOPS
PARAM SHAVAK 2016 3.8 TFLOPS
PARAM ISHAN[34][31] 2016 300 Terabits capacity 250 TFLOPS
PARAM SHIVAY[35] 2019 833 TFLOPS
PARAM Brahma[36] 2019 1PB storage 0.85 PFLOPS
PARAM Siddhi-AI[3] 2020 Nvidia DGX SuperPOD based networking architecture, HPC-AI engine software frame works and cloud platform from C-DAC 5.267 PFLOPS (Peak)
4.6PFLOPS (Sustained)

PARAMNet

PARAMNet is a high speed high bandwidth low latency network developed for the PARAM series. The original PARAMNet used an 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 was a full-duplex network. It was first used in PARAM 10000.[9]

PARAMNet II, introduced with PARAM Padma, is capable of 2.5 Gbit/s while working full-duplex. It supports interfaces like Virtual Interface Architecture and Active messages. It uses 8 or 16 port SAN switches.[37]

PARAMNet-3, used in PARAM Yuva and PARAM Yuva-II, is next generation high performance networking component for building supercomputing systems. PARAMNet-3 consists of tightly integrated hardware and software components. The hardware components consist of Network Interface Cards (NIC) based on CDAC's fourth generation communication co-processor "GEMINI", and modular 48-port Packet Routing Switch "ANVAY". The software component "KSHIPRA" is a lightweight protocol stack designed to exploit capabilities of hardware and to provide industry standard interfaces to the applications. Other application areas identified for deployment of PARAMNet-3 are storage and database applications.[38]

Operators

PARAM supercomputers are used by both public and private[24] operators for various purposes. As of 2008, 52 PARAMs have been deployed. Of these, 8 are located in Russia, Singapore, Germany and Canada. PARAMs have also been sold to Tanzania, Armenia, Saudi Arabia, Singapore, Ghana, Myanmar, Nepal, Kazakhstan, Uzbekistan, and Vietnam.[39]

See also

References

  1. Patnaik, LM. "High Performance Computing in India and Far-East". United Nations Industrial Development Organisation. Retrieved 20 July 2020.
  2. Kahaner, D.K. (1996). "Parallel computing in India". IEEE Parallel & Distributed Technology: Systems & Applications. 4 (3): 7–11. doi:10.1109/88.532134. L.M. Patnaik developed a significant amount of the factual material for this report.
  3. "Indias AI supercomputer Param Siddhi 63rd among top 500 most powerful non-distributed computer systems in the world". Department of Science and Technology. Retrieved 8 December 2020.
  4. Delapierre, Michel; Zimmermann, Jean-Benoît (1989). "La nouvelle politique industrielle : le cas de l'informatique". Tiers-Monde. 30 (119): 559–576. doi:10.3406/tiers.1989.3862.
  5. Sinha, P. K.; Dixit, S. P.; Mohanram, N.; Purohit, S. C.; Arora, R. K.; Ramakrishnan, S. (2004). "Current state and future trends in high performance computing and communications (HPCC) research in India". Proceedings. 10th IEEE International Workshop on Future Trends of Distributed Computing Systems, 2004: 217–220. doi:10.1109/FTDCS.2004.1316619. ISBN 0-7695-2118-5. S2CID 47348115.
  6. Beary, Habib (25 April 1999). "India unveils huge supercomputer". BBC News. India began developing supercomputers in the late 1980s after being refused one by the US.
  7. "God, Man And Machine". PARAM SUKHADIA India. 1 July 1998. Retrieved 15 September 2011.
  8. Zelkowitz, Marvin V. (1997). Advances in Computers, Volume 44. p. 186. ISBN 9780080566764. Retrieved 15 September 2011.
  9. Rajaraman, V. (1999). Super Computers. Universities Press. p. 75. ISBN 9788173711497. Retrieved 15 September 2011.
  10. "Only protected usable knowledge can create wealth.". Thehindubusinessline.com. 26 February 2001. Retrieved 10 September 2016.
  11. "CRAY DEAL A CASUALTY OF ATOMIC WEAPON FEARS". The Washington Post.
  12. "C-DAC furthering ties with ICAD, Moscow: From PARAM 8000 to PARAM 10000". Center for Development of Advanced Computing (C-DAC). Retrieved 15 September 2011.
  13. "Supercomputer being developed at Pune, Bangalore will be ready in 6 months". Center for Development of Advanced Computing (C-DAC). Retrieved 15 September 2011. ...giving India her first indigenous supercomputer in 1991 (PARAM 8000)
  14. "Digital India Week".
  15. "The Little Known Story of How India's First Indigenous Supercomputer Amazed the World in 1991". The Better India. 13 January 2017.
  16. Bhatkar, V.P. (April 1994). "PARAM parallel supercomputer: architecture, programming environment, and applications". Proceedings of 8th International Parallel Processing Symposium: 388–389. doi:10.1109/IPPS.1994.288273. ISBN 0-8186-5602-6. S2CID 9917838.
  17. Mohan, RN. "A Microkernel Based Operating System for PARAM 9000" (PDF). Retrieved 24 July 2020.
  18. Van der Steen, Aad J.; Dongarra, Jack J (1995). Overview of recent supercomputers. National Computing Facilities Foundation (Netherlands).
  19. Harkar, A.; Shaligram, A.D.; Ghaisas, S.V.; Sundararajan, V. (December 1996). "Monte Carlo device simulation on PARAM". Proceedings of 3rd International Conference on High Performance Computing (HiPC): 33–35. doi:10.1109/HIPC.1996.565792. ISBN 0-8186-7557-8. S2CID 40870947.
  20. Abraham; Baets; Köppen (2006). Applied soft computing technologies: the challenge of complexity. Springer. p. 54. ISBN 9783540316626. Retrieved 15 September 2011.
  21. Ram, B. (December 2009). Computer Fundamentals, Architecture & Organisation. New Age International. pp. 1–20. ISBN 9788122420432. Retrieved 15 September 2011.
  22. "Rediff on the Net, Infotech: Exporting speed". Rediff.com. 28 September 1999. Retrieved 10 September 2016.
  23. "Top500: "PARAM Yuva" Cluster (Performance)". Retrieved 15 September 2011.
  24. "PARAM Yuva supercomputer now open to private sector". Indian Express. 26 February 2011. Retrieved 15 September 2011. With an enhanced storage capacity of 200 TB from 25 TB, a large number of users can use it for data processing and storage at the same time.
  25. "C-DAC launches India's fastest supercomputer; becomes first R&D institution in India to cross 500 teraflops milestone". Information Week. 9 February 2013. Archived from the original on 13 February 2013. Retrieved 9 February 2013.
  26. "C-DAC reaffirms India's position on supercomputing map with PARAM Yuva - II". CDAC. Retrieved 9 February 2013.
  27. "C-DAC unveils India's fastest supercomputer". The Times of India. Retrieved 9 February 2013.
  28. "India's fastest supercomputer 'Param Yuva II' unveiled". DNA India. 8 February 2013. Retrieved 9 February 2013.
  29. "C-DAC unveils India's fastest supercomputer Param Yuva II". The Economic Times. 9 February 2013. Retrieved 9 February 2013.
  30. "Technical Information". IIT Guwahati Website for PARAM ISHAN. Retrieved 16 January 2019.
  31. "PARAM-Ishan @ IIT Guwahati Official site". Retrieved 26 November 2018. Details of PARAM-Ishan a 250 tfps Hybrid HPCC at IIT Guwahati
  32. "PARAM Brahma will allow scientists to address complex scientific problems". 29 September 2019.
  33. "PARAM Kanchenjunga inaugurated at NIT Sikkim". Retrieved 26 November 2018.
  34. "PARAM-ISHAN launched at IIT". Retrieved 26 November 2018. Fastest and most powerful computer in north-eastern India launched in IIT Guwahati
  35. "PM Modi inaugurates supercomputer Param Shivay at IIT BHU". C-DAC.
  36. "PARAM Brahma will allow scientists to address complex scientific problems". 29 September 2019.
  37. Singh, Ashok Kumar (July 2007). Science And Technology For Civil Service. Tata McGraw-Hill Education. p. 216. ISBN 9780070655485. Retrieved 15 September 2011.
  38. "PARAMNet3". Retrieved 26 November 2018. PARAMNet-3, a high performance clusters interconnect developed indigenously by CDAC.
  39. "C-DAC Press Release: Faster PARAM to take on US supercomputer". Retrieved 15 September 2011.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.