The 8 Most Powerful Supercomputers In The World







The power of computers grows daily. The technology develops at an incredible speed, and sometimes we even fear the extent to which it will not transmit. Computers today can do amazing things, such as even simulating the human brain. These supercomputers are considered the most powerful computers in the world.

   1. Sunway TaihuLight



Currently ranked as the world's fastest supercomputer, Sunway TaihuLight supercomputer measures 125 petaFLOPS (theoretical peak) - five times faster than the supercomputer in second place. 
It is located in the National Supercomputer Center in Wuxi, it consists of 10.6 million cores and is used for climate research, modeling of ground systems and data analysis. In addition to being the fastest supercomputer in the world, Sunway TaihuLight is currently ranked as the fourth most efficient energy supercomputer because it requires significantly less megawatts per megaFLOPS.

   2. Piz Daint (2017)


At the end of 2016, the supercomputer Piz Daint in Lugano, Switzerland, received a huge upgrade to the hardware. This new power tripled its computing power and brought its theoretical cutting-edge performance to 19.6 petaFLOPS (their own measurements are currently displayed at 25.3) making it the fastest supercomputer outside Asia. Named after one mountain in the Swiss Alps, Piz Daint also creates advanced imaging and high-resolution shooting simulations. It will soon provide processing power to the Great Hadron Collider at CERN, helping to analyze vast amounts of data.

   3. Tianhe-2


Tianhe-2, also known as MILKYWAY-2, is a supercomputer developed by the Chinese National Defense University. It became the world's fastest supercomputer in June 2013 with a peak performance of 33.86 petaFLOPS (although the highest theoretical performances could be much higher), although in recent years it has fallen to third place. 16,000 computer nodes, composed of Intel Ivy Bridge and Xeon Phi processors, provide simulations of government security applications. It also serves as an open research platform for scientists in southern China. 

   4. Titan


Perhaps one of the most famous supercomputers in the western world, Titan at the National Laboratory of Oak Ridge in Tennessee was the fastest supercomputer on the planet, while Tianhe-2 (below) did not take it from the top spot in 2013. Titan is the first supercomputer to combine AMD Opteron processors and graphics processors with NVIDIA Tesla, bringing the total peak power to 27 petaFLOPS. This type of energy allows researchers to carry out the complex simulations needed in climate science, astrophysics, and molecular physics. 

   5. Sequoia


Sequoia is a supercomputer built to measure the risks of nuclear warfare by making calculated scientific achievements. It is owned by the Lawrence Livermore National Laboratory in California. With 98,304 nodes, it is ranked as the fifth most powerful supercomputer on the planet. It has a speed of 17.2 petaFLOPS. 

   6. Corey (NERSC)


The National Research Center for Energy Research, near Oakland, California, names the latest supercomputing creature "Corey" after Gerty Corey, the first American to win the Nobel Prize. The system is the Cray XC40, manufactured by the company responsible for major breakthroughs in supercomputer performance during the 1970s. Cori can theoretically achieve a processing speed of 29.1 petaFLOPS. This is achieved through the use of Haswell architecture Intel Xeon and Xeon Phi processors. 

   7. Oakforest-PACS


As a result of the collaboration between the University of Tokyo, the University of Tsukuba and Fujista Limiting, a supercomputer named Oakforest-PACS broke the 25 petaflops barrier thanks to the latest generation of Intel's Xeon Phi processors, which made it the fastest supercomputer in Japan. The system is comprised of 8,208 computing nodes, and is used to promote computer science research and to teach young researchers. 

   8. K computer



K Fujitu's computer was the first supercomputer ever to break the ten petaFLOPS barriers in November 2011. K in its name refers to the Japanese word "kei" or 10 quadrillion - reference to the number of FLOPS. To function at this level, K combines the power of 80,000 separate processors through specialized connectors designed to transmit high speed data. The water cooling system protects the individual processor cores from overheating.

Comments

Popular posts from this blog

DirectX 12 vs DirectX 11

Android N's "Freeform Windows"

The Chord Mojo turns good headphones into great ones