1. ​Sunway TaihuLight - China (New entrant)

The brand new Sunway TaihuLight supercomputer is three times faster than the previous reigning champ, the Tianhe-2.

Sitting within the National Supercomputing Center in the city of Wuxi, the Chinese system will aid research and engineering work, ranging from climate modelling to advanced manufacturing.

Unlike the Intel-powered Tianhe-2, previously the fastest supercomputer in the world, the machine relies heavily on Chinese technology, utilising a new ShenWei processor and custom interconnect made in Wuxi.

The TaihuLight has 40,960 64-bit, RISC processors, each of which has 260 cores. Together these 1.45 GHz SW26010 processors have a peak performance equivalent to 125 petaflops (quadrillion floating point operations per second) — 93 petaflops in the Linpack benchmark. Each compute node has 32GB DDR3 memory, for 1.3 PB across the whole machine. The TaihuLight runs the Linux-based Sunway Raise OS and drew 15.4MW when benchmarked, less than the 17.8MW of the Tianhe-2.

​2. Tianhe-2 - China (Previously: No 1)

Capable of performing more than 33 quadrillion calculations per second at launch, the Tianhe-2 held onto the top spot for two years.

Deployed at the National Supercomputer Center in Guangzho, the Tianhe-2, is otherwise known as the Milky Way 2.

The supercomputer has 16,000 nodes, each with two Intel Xeon E5 Ivy Bridge processors and three Xeon Phi 31SP co-processors, for a combined total of 3,120,000 computing cores. This architecture allows it to carry out a massive number of operations in parallel, although reportedly makes it more difficult to write code for. Combined with 1PB (petabyte) of memory, the machine’s theoretical peak performance is 54 petaflops. Its draw is a whopping 17.8MW and it runs Kylin Linux and uses TH Express-2 interconnects.

3. Titan - US (Previously: No 2)

Another former frontrunner, Titan’s ability to handle more than 20 quadrillion calculations per second helps researchers at the US Oak Ridge National Laboratory probe climate change, alternate fuel sources and other global challenges.

The Cray XK7 machine relies on a mix of processors, utilising 560,640 cores, split between AMD Opteron 6274 processors, clocked at 2.2GHz, and NVIDIA K20x accelerators. Its peak performance is 27.1 petaflops and it has 710TB of memory. The Titan runs a Linux-based OS made by Cray and uses the Cray Gemini interconnects. It draws 8.2MW.

5. K computer - Japan (Previously: No 4)

Another longstanding member of the top 10, the K computer was capable of crunching more than eight quadrillion calculations per second at launch.

Based in Kobe’s RIKEN Advanced Institute for Computational Science, the K computer is helping tackle major global challenges, engaged in everything from disaster prevention to medical research.

The Fujitsu-designed machine packs in 705,024 SPARC64 VIIIfx processor cores, each rated at 2GHz, and 1.4PB of memory. Capable of a peak performance of 11.2 petaflops, it draws 12.7MW. The machine uses custom interconnects and runs a Linux-based OS.

6. Mira - US (Previously: No 5)

Able to crank through 10 quadrillion calculations per second, Mira helps US researchers model everything from the human body to jet engines.

Installed at the Argonne National Laboratory in Illinois, the IBM BlueGene supercomputer has a peak performance of 10.1 petaflops. The machine relies on 49,152 compute nodes, each with a 16-core PowerPC A2 processor clocked at 1.6GHz, and 16GB DDR3 memory, giving it a total of 786,432 processing cores and 786TB memory. It runs on a Linux-based OS, uses custom interconnects and draws 3.9MW.

7. Trinity - US (Previously: No 6)

By simulating nuclear explosions, the Trinity supercomputer will help the US test the effectiveness of its nuclear arsenal.

Based at Los Alamos National Laboratory, Trinity is a Cray XC40 with a peak performance of 11 petaflops. Despite having a slightly higher peak performance than Mira, Trinity is further down the TOP500 list, due to its slightly lower Linpack benchmark score. The machine relies on 16-core Xeon E5-2698v3 processors, clocked at 2.3GHz, for a total of 301,056 cores.

8. Piz Daint - Switzerland (Previously: No 7)

The prize for the fastest system in Europe goes to Piz Daint, based at the Swiss National Supercomputing Centre.

The research machine is one of the most energy efficient supercomputers, consuming just 2.3MW. Capable of 7.8 petaflops peak performance, the Cray XC30 machine relies on 5,272 compute nodes, each with an eight-core Xeon E5-2670 processor, clocked at 2.6GHz, and a NVIDIA Tesla K20X GPU accelerator. For memory, the machine has a total of 169TB DDR3 and 32TB GDDR5. The system uses Aries interconnects and runs on a Cray Linux OS.

Piz Daint was recently upgraded with a further 1,256 compute nodes, each with two 12-core Intel Xeon E5-2690 v3 CPUs.

9. Hazel Hen - Germany (Previously: No 8)

Another European contender is the Cray-built Hazel Hen, based in Germany.

Situated at the High Performance Computing Center Stuttgart, the machine is helping European researchers study topics ranging from minimizing CO2 emissions to modelling new materials for aerospace.

Hazel Hen is a Cray XC40-system, with a peak performance of 7.4 petaflops. Under the hood are 15,424 Intel Xeon CPU E5-2680 v3 processors, clocked at 2.5 GHz, for a total of 185,088 cores. The machine has about 1PB of memory, relies on Aries interconnects and draws 3.2MW.

10. Shaheen II - Saudi Arabia (Previously: No 9)

First entering the top 10 at seventh place in 2007, the Shaheen II is a Saudi Arabian computer focused on modelling atmospheric dynamics and other complex systems.

Based at King Abdullah University of Science and Technology in Thuwal, the Cray XC40 system relies on more than 12,000 Xeon E5-2698v3 processors, each packing 16 cores clocked at 2.3GHz, for a total of 196,608 cores. It’s capable of 7.2 petaflops peak performance and draws 2.8MW. The system runs a Cray Linux OS and uses Aries interconnects.