Supercomputing in India has a history going back to the 1980s. [1] The Government of India created an indigenous development programme as they had difficulty purchasing foreign supercomputers. [1] As of June 2023 [update] , the AIRAWAT supercomputer is the fastest supercomputer in India, having been ranked 75th fastest in the world in the TOP500 supercomputer list. [2] AIRAWAT has been installed at the Centre for Development of Advanced Computing (C-DAC) in Pune. [3]
India had faced difficulties in the 1980s when trying to purchase supercomputers for academic and weather forecasting purposes. [1] In 1986 the National Aerospace Laboratories (NAL) started the Flosolver project to develop a computer for computational fluid dynamics and aerospace engineering. [4] [5] The Flosolver MK1, described as a parallel processing system, started operations in December 1986. [4] [6] [5]
In 1987 the Indian Government had requested to purchase a Cray X-MP supercomputer; this request was denied by the United States government as the machine could have a dual use in weapons development. [7] After this problem, in the same year, the Government of India decided to promote an indigenous supercomputer development programme. [8] [9] [10] Multiple projects were commissioned from different groups including the Centre for Development of Advanced Computing (C-DAC), the Centre for Development of Telematics (C-DOT), the National Aerospace Laboratories (NAL), the Bhabha Atomic Research Centre (BARC), and the Advanced Numerical Research and Analysis Group (ANURAG). [9] [10] C-DOT created "CHIPPS": the C-DOT High-Performance Parallel Processing System. NAL had started to develop the Flosolver in 1986. [4] [11] BARC created the Anupam series of supercomputers. ANURAG created the PACE series of supercomputers. [10]
The Centre for Development of Advanced Computing (C-DAC) was created at some point between November 1987 and August 1988. [8] [10] [9] C-DAC was given an initial 3 year budget of Rs375 million to create a 1000MFLOPS (1GFLOPS) supercomputer by 1991. [10] C-DAC unveiled the PARAM 8000 supercomputer in 1991. [1] This was followed by the PARAM 8600 in 1992/1993. [10] [9] These machines demonstrated Indian technological prowess to the world and led to export success. [10] [9] Param 8000 was replicated and installed at ICAD Moscow in 1991 with Russian collaboration.
The PARAM 8000 was considered a success for C-DAC in delivering a gigaFLOPS range parallel computer. [10] From 1992 C-DAC undertook its "Second Mission" to deliver a 100 GFLOPS range computer by 1997/1998. [1] The plan was to allow the computer to scale to 1 teraFLOPS. [10] [12] In 1993 the PARAM 9000 series of supercomputers was released, which had a peak computing power of 5 GFLOPS. [1] In 1998 the PARAM 10000 was released; this had a sustained performance of 38 GFLOPS on the LINPACK benchmark. [1]
The C-DAC's third mission was to develop a teraFLOPS range computer. [1] The PARAM Padma was delivered in December 2002. [1] This was the first Indian supercomputer to feature on a list of the world's fastest supercomputers, in June 2003. [1]
By the early 2000s it was noted that only ANURAG, BARC, C-DAC and NAL were continuing development of their supercomputers. [6] NAL's Flosolver had 4 subsequent machines built in its series. [6] At the same time ANURAG continued to develop PACE, primarily based on SPARC processors. [6]
The Indian Government has proposed to commit US$2.5 billion to supercomputing research during the 12th Five-Year Plan period (2012–2017). The project will be handled by Indian Institute of Science (IISc), Bangalore. [13] Additionally, it was later revealed that India plans to develop a supercomputer with processing power in the exaflops range. [14] It will be developed by C-DAC within the subsequent five years of approval. [15]
Supercomputing overview | |
---|---|
Formed | 2015 |
Parent department | C-DAC |
Website | https://nsmindia.in/ |
In 2015 the Ministry of Electronics and Information Technology announced a "National Supercomputing Mission" (NSM) to install 73 indigenous supercomputers throughout the country by 2022. [16] [17] [18] [19] This is a seven-year program worth $730 million (Rs. 4,500 crore).[ citation needed ] Whilst previously computer were assembled in India, the NSM aims to produce the components within the country. [20] The NSM is being implemented by C-DAC and the Indian Institute of Science. [19]
The aim is to create a cluster of geographically distributed high-performance computing centers linked over a high-speed network, connecting various academic and research institutions across India. [17] This has been dubbed the "National Knowledge Network" (NKN). [20] The mission involves both capacity and capability machines and includes standing up three petascale supercomputers. [21] [22]
The first phase involved deployment of supercomputers which have 60% Indian components. [19] The second phase machines are intended to have an Indian designed processor, [19] with a completion date of April 2021. [20] The third and final phase intends to deploy fully indigenous supercomputers, [19] with an aimed speed of 45 petaFLOPS within the NKN. [20]
By October 2020, the first assembled in India supercomputer had been installed. [20] The NSM hopes to have the manufacturing capability for indigenous production by December 2020. [20]
As of November 2023 [update] there are 4 systems based in India on the TOP500 supercomputer list. [23]
Rank | Site | Name | Rmax (TFlop/s) | Rpeak (PFlop/s) |
---|---|---|---|---|
75 | Centre for Development of Advanced Computing | AIRAWAT - PSAI [24] [25] | 8.5 | 13.17 |
163 | Centre for Development of Advanced Computing | PARAM Siddhi-AI | 4.62.0 | 5.27 |
201 | Indian Institute of Tropical Meteorology | Pratyush (Cray XC40) [26] [27] | 3.76 | 4.01 |
354 | National Centre for Medium Range Weather Forecasting | Mihir (Cray XC40) | 2.57 | 2.81 |
List | Number of systems in TOP500 | System Share (%) | Total Rmax (Gflops) | Total Rpeak (Gflops) | Cores |
---|---|---|---|---|---|
2020 June | 2 | 0.4 | 6,334,340 | 6,814,886 | 202,824 |
2019 November | 2 | 0.4 | 6,334,340 | 6,814,886 | 202,824 |
2019 June | 3 | 0.6 | 7,457,490 | 8,228,006 | 241,224 |
2018 November | 4 | 0.8 | 8,358,996 | 9,472,166 | 272,328 |
2018 June | 5 | 1 | 9,078,216 | 10,262,899 | 310,344 |
2017 November | 4 | 0.8 | 2,794,753 | 3,759,153 | 107,544 |
2017 June | 4 | 0.8 | 2,703,926 | 3,935,693 | 103,116 |
2016 November | 5 | 1 | 3,092,368 | 4,456,051 | 133,172 |
2016 June | 9 | 1.8 | 4,406,352 | 5,901,043 | 204,052 |
2015 November | 11 | 2.2 | 4,933,698 | 6,662,387 | 236,692 |
2015 June | 11 | 2.2 | 4,597,998 | 5,887,007 | 226,652 |
2014 November | 9 | 1.8 | 3,137,692 | 3,912,187 | 184,124 |
2014 June | 9 | 1.8 | 2,898,745 | 3,521,915 | 169,324 |
2013 November | 12 | 2.4 | 3,040,297 | 3,812,719 | 188,252 |
2013 June | 11 | 2.2 | 2,690,461 | 3,517,536 | 173,580 |
2012 November | 9 | 1.8 | 1,291,739 | 1,890,914 | 90,548 |
2012 June | 5 | 1 | 787,652 | 1,242,746 | 56,460 |
2011 November | 2 | 0.4 | 187,910 | 242,995 | 18,128 |
2011 June | 2 | 0.4 | 187,910 | 242,995 | 18,128 |
2010 November | 4 | 0.8 | 257,243 | 333,005 | 25,808 |
2010 June | 5 | 1 | 283,380 | 384,593 | 30,104 |
2009 November | 3 | 0.6 | 199,257 | 279,702 | 23,416 |
2009 June | 6 | 1.2 | 247,285 | 333,519 | 33,456 |
2008 November | 8 | 1.6 | 259,394 | 368,501 | 37,488 |
2008 June | 6 | 1.2 | 189,854 | 275,617 | 32,432 |
2007 November | 9 | 1.8 | 194,524 | 303,651 | 34,932 |
2007 June | 8 | 1.6 | 45,697 | 86,642 | 10,336 |
2006 November | 10 | 2 | 34,162 | 61,520 | 10,908 |
2006 June | 11 | 2.2 | 36,839 | 66,776 | 11,638 |
2005 November | 4 | 0.8 | 11,379 | 21,691 | 3,354 |
2005 June | 8 | 1.6 | 13,995 | 24,726 | 4,212 |
2004 November | 7 | 1.4 | 6,945 | 11,873 | 2,126 |
2004 June | 6 | 1.2 | 5,652 | 9,557 | 1,750 |
2003 November | 3 | 0.6 | 2,099 | 5,098 | 1,106 |
2003 June | 2 | 0.4 | 1,158 | 3,747 | 822 |
A supercomputer is a type of computer with a high level of performance as compared to a general-purpose computer. The performance of a supercomputer is commonly measured in floating-point operations per second (FLOPS) instead of million instructions per second (MIPS). Since 2017, supercomputers have existed, which can perform over 1017 FLOPS (a hundred quadrillion FLOPS, 100 petaFLOPS or 100 PFLOPS). For comparison, a desktop computer has performance in the range of hundreds of gigaFLOPS (1011) to tens of teraFLOPS (1013). Since November 2017, all of the world's fastest 500 supercomputers run on Linux-based operating systems. Additional research is being conducted in the United States, the European Union, Taiwan, Japan, and China to build faster, more powerful and technologically superior exascale supercomputers.
Blue Gene was an IBM project aimed at designing supercomputers that can reach operating speeds in the petaFLOPS (PFLOPS) range, with low power consumption.
PARAM is a series of Indian supercomputers designed and assembled by the Centre for Development of Advanced Computing (C-DAC) in Pune. PARAM means "supreme" in the Sanskrit language, whilst also creating an acronym for "PARAllel Machine". As of November 2022 the fastest machine in the series is the PARAM Siddhi AI which ranks 163rd in world, with an Rpeak of 5.267 petaflops.
NEC SX describes a series of vector supercomputers designed, manufactured, and marketed by NEC. This computer series is notable for providing the first computer to exceed 1 gigaflop, as well as the fastest supercomputer in the world between 1992–1993, and 2002–2004. The current model, as of 2018, is the SX-Aurora TSUBASA.
The Centre for Development of Advanced Computing (C-DAC) is an Indian autonomous scientific society, operating under the Ministry of Electronics and Information Technology.
Vijay Pandurang Bhatkar is an Indian computer scientist, IT leader and educationalist. He is best known as the architect of India's national initiative in supercomputing where he led the development of Param supercomputers. He is a Padma Shri, Padma Bhushan, and Maharashtra Bhushan awardee. Indian computer magazine Dataquest placed him among the pioneers of India's IT industry. He was the founder and executive director of Centre for Development of Advanced Computing (C-DAC) and is currently working on developing exascale supercomputing for India.
The TOP500 project ranks and details the 500 most powerful non-distributed computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The first of these updates always coincides with the International Supercomputing Conference in June, and the second is presented at the ACM/IEEE Supercomputing Conference in November. The project aims to provide a reliable basis for tracking and detecting trends in high-performance computing and bases rankings on HPL benchmarks, a portable implementation of the high-performance LINPACK benchmark written in Fortran for distributed-memory computers.
EKA, is a supercomputer built by the Computational Research Laboratories, a company founded by Dr. Narendra Karmarkar, for scaling up a supercomputer architecture he designed at the Tata Institute of Fundamental Research with a group of his students and project assistants over a period of 6 years.
In computing, performance per watt is a measure of the energy efficiency of a particular computer architecture or computer hardware. Literally, it measures the rate of computation that can be delivered by a computer for every watt of power consumed. This rate is typically measured by performance on the LINPACK benchmark when trying to compare between computing systems: an example using this is the Green500 list of supercomputers. Performance per watt has been suggested to be a more sustainable measure of computing than Moore's Law.
Sugon, officially Dawning Information Industry Company Limited, is a supercomputer manufacturer based in the People's Republic of China. The company is a spin-off from research done at the Chinese Academy of Sciences (CAS), and still has close links to it.
Jaguar or OLCF-2 was a petascale supercomputer built by Cray at Oak Ridge National Laboratory (ORNL) in Oak Ridge, Tennessee. The massively parallel Jaguar had a peak performance of just over 1,750 teraFLOPS. It had 224,256 x86-based AMD Opteron processor cores, and operated with a version of Linux called the Cray Linux Environment. Jaguar was a Cray XT5 system, a development from the Cray XT4 supercomputer.
Exascale computing refers to computing systems capable of calculating at least "1018 IEEE 754 Double Precision (64-bit) operations (multiplications and/or additions) per second (exaFLOPS)"; it is a measure of supercomputer performance.
The K computer – named for the Japanese word/numeral "kei" (京), meaning 10 quadrillion (1016) – was a supercomputer manufactured by Fujitsu, installed at the Riken Advanced Institute for Computational Science campus in Kobe, Hyōgo Prefecture, Japan. The K computer was based on a distributed memory architecture with over 80,000 compute nodes. It was used for a variety of applications, including climate research, disaster prevention and medical research. The K computer's operating system was based on the Linux kernel, with additional drivers designed to make use of the computer's hardware.
Japan operates a number of centers for supercomputing which hold world records in speed, with the K computer being the world's fastest from June 2011 to June 2012, and Fugaku holding the lead from June 2020 until June 2022.
The history of supercomputing goes back to the 1960s when a series of computers at Control Data Corporation (CDC) were designed by Seymour Cray to use innovative designs and parallelism to achieve superior computational peak performance. The CDC 6600, released in 1964, is generally considered the first supercomputer. However, some earlier computers were considered supercomputers for their day such as the 1954 IBM NORC in the 1950s, and in the early 1960s, the UNIVAC LARC (1960), the IBM 7030 Stretch (1962), and the Manchester Atlas (1962), all of which were of comparable power.
Several centers for supercomputing exist across Europe, and distributed access to them is coordinated by European initiatives to facilitate high-performance computing. One such initiative, the HPC Europa project, fits within the Distributed European Infrastructure for Supercomputing Applications (DEISA), which was formed in 2002 as a consortium of eleven supercomputing centers from seven European countries. Operating within the CORDIS framework, HPC Europa aims to provide access to supercomputers across Europe.
The high performance supercomputing program started in mid-to-late 1980s in Pakistan. Supercomputing is a recent area of Computer science in which Pakistan has made progress, driven in part by the growth of the information technology age in the country. Developing on the ingenious supercomputer program started in 1980s when the deployment of the Cray supercomputers was initially denied.
The Cray XC40 is a massively parallel multiprocessor supercomputer manufactured by Cray. It consists of Intel Haswell Xeon processors, with optional Nvidia Tesla or Intel Xeon Phi accelerators, connected together by Cray's proprietary "Aries" interconnect, stored in air-cooled or liquid-cooled cabinets. The XC series supercomputers are available with the Cray DataWarp applications I/O accelerator technology.
Anupam is a series of supercomputers designed and developed by Bhabha Atomic Research Centre (BARC) for their internal usages. It is mainly used for molecular dynamical simulations, reactor physics, theoretical physics, computational chemistry, computational fluid dynamics, and finite element analysis.
The Sunway TaihuLight is a Chinese supercomputer which, as of November 2023, is ranked 11th in the TOP500 list, with a LINPACK benchmark rating of 93 petaflops. The name is translated as divine power, the light of Taihu Lake. This is nearly three times as fast as the previous Tianhe-2, which ran at 34 petaflops. As of June 2017, it is ranked as the 16th most energy-efficient supercomputer in the Green500, with an efficiency of 6.1 GFlops/watt. It was designed by the National Research Center of Parallel Computer Engineering & Technology (NRCPC) and is located at the National Supercomputing Center in Wuxi in the city of Wuxi, in Jiangsu province, China.
India began developing supercomputers in the late 1980s after being refused one by the US.
L.M. Patnaik developed a significant amount of the factual material for this report.