A computer having a very high computing speed several thousand times faster than that of conventional ones is called as a supercomputer.

The term supercomputing was first used by the New York World newspaper in 1929 to refer to large custom-built tabulators that IBM had made for Columbia University. Super Computers introduced in the 1960s, were designed primarily by Seymour Cray at Control Data Corporation and led the market into the 1970s.

The supercomputer will usually have more than one central processing unit (CPU), which allows the computer to do faster circuit switching and accomplish more tasks at once. (Because of this, a supercomputer will also have an enormous amount of storage so that it can access many tasks at a time.) It will also have the capability to do vector arithmetic, which means that it can calculate multiple lists of operations instead of just one at a time.

How does it work?

There are two major parts to a supercomputer, and they are the central processing unit, also known as the CPU, and the memory. The role of the CPU is to carry out instructions and the memory is where the instructions and data are stored. Those engineers who design supercomputers use high-performance circuits and architectures to make CPU’s that are 10 to 20 times faster than the top of the line CPU’s used for other commercial computers.

Uses of Super Computers

Supercomputers are used for many different things in today’s society.

• Supercomputers are used to help predict the weather. Meteorologists use them to do research on climate and global warming.
• Scientist uses them for molecular modelling, which gives them the opportunity to compute the structures and properties of biological compounds.
• Supercomputers are also used for simulations, for example, the effect of wind and turbulence on an aeroplane; and the simulation of the effect of a nuclear weapon if it were to be detonated.
• The military also uses supercomputers for many different reasons. Supercomputers are used to test new vehicles being engineered, to see how they will function in combat. They also use them to give soldiers a simulation of how it will be in the new vehicle, and how he/she needs to react in certain situations
• Supercomputers are also used for military pilots who go into a simulator to see how to react during a combat situation.
• Some other areas such as molecular biophysics, quantum chemistry and reaction dynamics etc. are using high-speed numeral computing.
• They are also being used in biological macromolecules, simulation of the detonation of nuclear weapons, research into nuclear fusion etc.

Supercomputer using Artificial Intelligence, Machine Learning, Healthcare Analytics based Research, Covid-19 (SAMHAR)

• It was announced by Centre for Development of Advanced Computing (C-DAC) under the aegis of the National Supercomputing Mission (NSM), a Ministry of Electronics & Information Technology (MeitY) and Department of Science & Technology (DST) initiative, in association with NVIDIA & OpenACC.
• The hackathon is open to Researchers, Academicians, MSMEs, Startups and Industries with an objective to bring out Innovative and Implementable Ideas for Prediction, Forecasting and Building Healthcare Models that could revolutionize the way we interpret science of pandemic outbreaks using AI technology on Supercomputers.

Some examples of some supercomputers are Roadrunner built by IBM and Param Padam developed by C-DAC of India.

Supercomputers in India

Indian attempts are aimed at developing supercomputers based on fronted technology but they are attempted to speeding up computers using slower processors.

Scientists at the advanced Numerical Research and Analysis Group (ANURAG) of the Defence Research and Development organization have developed the high-speed, user-friendly PACE (Processor for Aerodynamic Computation and Evaluations) system.

This DRDO's PACE project was primarily intended for fluid dynamics studies which required high computational speeds. Later on PACE plus supercomputer developed by the DRDO which was launched in 1995-96. After PACE supercomputers, scientists at the Center for Development of Advanced Computing developed the new model of PARAM supercomputer, capable of making 1,00,000 million calculations per second.

Supercomputer Education and Research Centre (SERC) was established in 1990 to provide state-of-the-art computing facility to the faculty and students of the Indian Institute of science. Apart from functioning as a central computing facility of IISc, the SERC is engaged in education and research programs in areas relating to supercomputer development and application.

Param Padma

India has written a fresh chapter in its history of super-computing by developing a one teraflop high-performance scalable computing cluster.  Hosed in the Terascale Supercomputing Facility at the Centre for Development of Advanced Computing (C-DAC’s), Knowledge Park in Banglore, this next generation of the now well-known Param series has been nicknamed Param Padma. The Padma in Indian mythology stands for 10 to the power of 12. One teraflop or 1000 Gigaflops stands for one trillion floating-point operations per second. The Param Padma stands at 500,000 motps and boasts of 250 processors.  What is of real pride is that two crucial technologies that control the teraflop machine have been indigenously developed.  One is the interconnect switch –PARAMENT II (which allows passing and sharing of calculations at 2.5 Gbps in full-duplex over fibre) and two, the entire suite of systems software tools, including management, debugging, compiling and engineering solutions.

As per Green500 List announced at the Supercomputing Conference (SC 2013) in Denver, Colorado, in the US, India’s PARAM Yuva II supercomputer built by the Centre for Development of Advanced Computing (C-DAC), has been ranked no.1 in India, 9^th in the Asia Pacific Region and 44th in the world among the most power-efficient computer systems.

Other supercomputers in India

• The Chennai-based Institute of Mathematical Sciences' cluster-computer ``Kabru''
• The world's fastest computer remains the Lawrence Livermore National Laboratory's ``BlueGene/L'' made by IBM, which clocked 136.8 TFLOP/s. In this light India has still a long way to go.
• The Bhabha Atomic Research Centre (BARC) has developed a very high-speed ANUPAM-XENON/128 supercomputer, achieving another significant milestone in the field of supercomputers. The computing speed of this 128 processor ANUPAM supercomputer is 202 Giga Floating Point Operations Per Second (GFLOPS)

Fastest supercomputer in India

According to the latest 56th TOP500 in November 2020, India’s newest and fastest supercomputer, PARAM-Siddhi AI, has been ranked 63rd in the Top500 list of most powerful supercomputers in the world. The supercomputer was established in 2020, under the National Supercomputer Mission (NSM) and is going to be installed in the Centre for Development of Advanced Computing’s (C-DAC) unit. 

PARAM-Siddhi is the second Indian supercomputer to be entered in the top 100 on the Top500 list. Pratyush, a supercomputer used for weather forecasting at the Indian Institute of Tropical Meteorology, ranked 78th on the November edition of the list. 

Pratyush and Mihir are the supercomputers established at the Indian Institute of Tropical Meteorology (IITM), Pune and the National Center for Medium-Range Weather Forecast (NCMRWF) respectively. 

Significance of Pratyush and MIHIR:

Pratyush and Mihir are used in the fields of weather forecasting and climate monitoring in India. It helps the country to make better forecasts in terms of Monsoon, fishing, air quality, extreme events like Tsunami, cyclones, earthquakes, lightning and other natural calamities such as floods, droughts etc.

With these supercomputers on our side, India became the fourth country in the world to have a High-Performance Computing facility dedicated to weather and climate research after Japan, the United States and the United Kingdom.

National Mission on Quantum Technologies & Applications (NM-QTA)

The government of India in its Budget 2020 announced the largest ever science mission- National Mission on Quantum Technologies & Applications. This was done in the backdrop of rapidly developing Quantum Technologies, with the potential to change the entire paradigm of computation, communication and encryption. Google, recently built a quantum computer, Sycamore which took 200 seconds to perform a calculation that the world's fastest supercomputer, Summit, would have taken 10,000 years.

The mission will be implemented by the Department of Science & Technology (DST), Ministry of Science and Technology, with a proposed budget outlay of 8000 crores. The areas of focus will be in fundamental science, human and infrastructural resource generation, innovation and start ups to address issues concerning national priorities. 

The mission will not only support advanced and interdisciplinary research projects in quantum technology through the government's support but will also provide a push to next-generation transformative technologies, subsequently putting India on the world's Quantum-map.

National Supercomputing Mission

India’s position can be expected to improve as the cabinet has approved the National Supercomputing Mission with an outlay of Rs.4,500 crore over a period of seven years, launched in 2015. The mission aims to set up a grid connecting 70 supercomputers located in research and development institutions, universities and the 1 million core cloud using the National Knowledge Network. It will come up with the association of the Department of Science and Technology (DST) and the Department of Information and Technology (DIT).

The mission also aims to catalyze the government’s Digital India vision by making available huge data storage space and linking systems. However, there are challenges before the plan is undertaken at a full-scale level. First would be building both software and hardware infrastructure for such a large-scale project and making applications for these supercomputers. More importantly, having manpower for running these supercomputers would also be a challenge as it would require training them.

Achievements:

• The first supercomputer assembled indigenously, called Param Shivay, was installed in IIT (Banaras Hindu University).
• Similar systems Param Shakti and Param Brahma were installed at IIT-Kharagpur and IISER, Pune. They are equipped with applications from domains like Weather and Climate, Computational Fluid Dynamics, Bioinformatics, and Material science. 
• India has also developed an indigenous server (Rudra), which can meet the High-Performance Computing (HPC) requirements of all governments and PSUs. This is the first time that a server system was made in India, along with the full software stack developed by C-DAC.

Current Fastest Super Computer

According to the latest 56th TOP500 in November 2020, Fugaku, a supercomputer built by Fujitsu ranks as the fastest supercomputer with 442 petaflops High-Performance Linpack (HPL) benchmark -  a key benchmark for high-performance computing, on that same TOP500 list.

Summit, which ranked second-fastest is an IBM-built supercomputer now running at the Department of Energy’s (DOE) Oak Ridge National Laboratory (ORNL). It has a performance of 148.6 petaflops on High-Performance Linpack (HPL). Summit has 4,608 nodes, each one equipped with two IBM Power9 CPUs, and six NVIDIA Tesla V100 GPUs. The nodes are linked together with a Mellanox dual-rail EDR InfiniBand network.

Sierra, a new system at the DOE’s Lawrence Livermore National Laboratory took the number three spot, delivering 94.64 petaflops on HPL. Built by IBM, Sierra’s architecture is quite similar to that of Summit, with each of its 4,320 nodes powered by two Power9 CPUs plus four NVIDIA Tesla V100 GPUs and using the same Mellanox EDR InfiniBand as the system interconnect.

Sunway TaihuLight, a system developed by China’s National Research Center of Parallel Computer Engineering & Technology (NRCPC) and installed at the National Supercomputing Center in Wuxi, drops to number fourth. Its HPL mark of 93 petaflops has remained unchanged since it came online in June 2016.

Generally, supercomputers eat up a lot of power and produce much heat that requires sophisticated cooling facilities to ensure proper functioning. This renders the Total Cost of Ownership (TCO) of an operating supercomputer to increase. In a bid to draw attention towards the development of energy-efficient supercomputers, Green500 ranks computer systems in the world according to compute performance per watt, thus providing a world ranking based on energy efficiency.

Some other notable supercomputers

Selene was named the world’s fifth-fastest supercomputer in the world on November’s closely watched list of TOP500 supercomputers. Built with new NVIDIA A100 GPUs, Selene achieved 63.4 petaflops on HPL.

Built with new NVIDIA A100 GPUs, Selene achieved 63.4 petaflops on HPL, a key benchmark for high-performance computing, on that same TOP500 list.

Tianhe-2A, also known as Milky Way-2A, is developed by China’s National University of Defense Technology (NUDT) and is installed at the National Supercomputer Center in Guangzhou, China. It received a major upgrade that replaced its five-year-old Xeon Phi accelerators with custom-built Matrix-2000 coprocessors. The new hardware increased the system’s HPL performance from 33.9 petaflops to 61.4 petaflops, while bumping up its power consumption by less than four per cent. 

• SAGA-220 built by ISRO is capable of performing at 220000 GFLops (220 TFlops). It uses about 400 NVIDIA Tesla 2070 GPUs and 400 Intel Quad-Core Xeon CPUs
• EKA is a supercomputer built by the Computational Research Laboratories with technical assistance and hardware provided by Hewlett-Packard. It is capable of performing at 132800 GFLops (132 TFlops).
• Also, the Indian Institute of Tropical Meteorology (Pune) has got a 70.2 TFlops machine (Prithvi) which is being used for climate research and operational forecasting.
• Titan is a supercomputer developed by Cray Inc. at the Oak Ridge National Laboratory for use in a variety of science projects. Titan is an upgrade of Jaguar, a previous supercomputer at Oak Ridge, to use GPUs in addition to CPUs. The computer was expected to perform 20 petaFLOPS, or 20 quadrillion calculations per second, however real performance statistics have been published as 17.59 petaFLOPS. On November 12, 2012, the TOP500 organisation that ranks the worlds' supercomputers by its LINPACK performance announced that Titan was ranked first, displacing IBM Sequoia.
• IBM Sequoia is a petascale Blue Gene/Q supercomputer constructed by IBM for the National Nuclear Security Administration as part of the Advanced Simulation and Computing Program (ASC). It was delivered to the Lawrence Livermore National Laboratory (LLNL) in 2011 and was fully deployed in June 2012. Sequoia will be used to carry out simulations to help extend the life of ageing nuclear weapons, avoiding the need for real-world underground tests. Sequoia will be used primarily for nuclear weapons simulation, replacing the current Blue Gene/L and ASC Purple supercomputers at Lawrence Livermore National Laboratory. Sequoia will also be available for scientific purposes such as astronomy, energy, the study of the human genome, and climate change