Business

Nine most powerful supercomputers in the world

The processing speed of supercomputers is measured in FLOPS and is so large in area that can occupy a space upto 500 square metres.

Every day we spend most of our time working on computers — whether we are watching a film, transferring data or designing graphics, and all this is easily processed by our computer’s processor which has a maximum of 12 cores in it.

But there are various big tasks in the world which can’t be processed by the computers which we use on a daily basis, for that we need high level of performance as compared to a general-purpose computer.

Supercomputers are used for processing high level task such as weather forecasting, scientific researches, operating nuclear weapons etc. The processing speed of these machines is measured in FLOPS (Floating point operations per second) and is so large in area that can occupy a space upto 500 square metres.

Summit

Summit, is the fastest supercomputer in the world, developed by IBM for use at Oak Ridge National Laboratory –an American multiprogram science and technology national laboratory. It is the first supercomputer to reach exascale speed, achieving 1.88 exaflops during a genomic analysis and is expected to reach 3.3 exaflops using mixed precision calculations. The supercomputer is installed with  POWER9, Tesla V100 processors making it capable of 200 petaflops.

Sunway TaihuLight

Sunway TaihuLight is Chinese supercomputer with a LINPACK benchmark rating of 93 petaflops. The Supercomputer is used for oil prospecting, life sciences, weather forecast, industrial design and pharmaceutical research in China. The system runs on its own operating system, Sunway RaiseOS 2.0.5, which is based on Linux and costs (US$273 million)

Sierra

Sierra is a supercomputer built for the Lawrence Livermore National Laboratory for use by the National Nuclear Security Administration in the United States as the second Advanced Technology System. It is primarily used for predictive applications in stockpile stewardship, helping to assure the safety, reliability, and effectiveness of the nation’s nuclear weapons. The Sierra system uses IBM POWER9 CPUs in conjunction with Nvidia Tesla V100 GPUs. The nodes in Sierra are Witherspoon S922LC OpenPOWER servers with two GPUs per CPU and four GPUs per node.

Tianhe-2

Tianhe-2 is a 33.86-petaflop supercomputer located in National Supercomputer Center in Guangzhou, China. It was developed by a team of 1,300 scientists and engineers and build on completely domestic technology including the Sunway manycore microprocessor. The super machine costs US$390 million and  is deployed for simulation, analysis, and government security applications.

Piz Daint

Piz Daint is a supercomputer in the Swiss National Supercomputing Centre, named after the mountain Piz Daint in the Swiss Alps, the computing performance of the super machine is 25 petaflops

Titan

Titan is a supercomputer built by Cray at Oak Ridge National Laboratory for use in scientific research and has a computing performance of 17.59 petaFLOPS (LINPACK), 27 petaFLOPS theoretical peak.

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). Sequoia is also more energy efficient, as it consumes 7.9 MW. Record-breaking science applications have been run on Sequoia, the first machine  to cross 10 petaflops of sustained performance.

Trinity

Trinity is a supercomputer at Los Alamos National Laboratory in New Mexico, United States. It was built as the first Advanced Technology System for the National Nuclear Security Administration. It is equipped with Intel “Knights Landing” Xeon Phi processors.

Cray XC40

Cray XC40 is a massively parallel multiprocessor supercomputer manufactured by Cray and equipped with Intel Haswell Xeon processors, with optional Nvidia Teslaor Intel Xeon Phi accelerators. The Supercomputer has a peak system performance of 500 petaflops  and 1 petaflops in a single cabinet.

RELATED ITEMS:
Show More