Social Innovation

The 10 most powerful supercomputers

Chris Parker
Head of Digital Media, World Economic Forum

For the first time, a supercomputer based in the Middle East has appeared in the top 10 of TOP500’s most powerful supercomputers list, published earlier this month.

According to the creators of the list, the rate of growth in global computing power is slowing down. Relatively few supercomputers have been switched on in the last few years, in comparison with a decade ago. There is a higher number of older supercomputers in the list than ever before, with nine systems in the top 10 installed before 2012.

The total combined performance of the top 500 computers has grown to 363 Pflop/s (a petaflop is the ability of a computer to do one quadrillion floating point operations per second) compared with 309 Pflop/s six months ago and 274 Pflop/s a year ago. This increase demonstrates a significant slowdown in growth, compared to the previous long-term trend.

Top 10 supercomputers


1. Tianhe-2 – China

The Tianhe-2 (Milky Way-2), built by China’s National University of Defence Technology (NUDT) for the National Supercomputer Center in Guangzho. It’s the most powerful computer in the world and performs at 33.86 petaflop/s (Pflop/s) on the Linpack benchmark.

The system has 3,120,000 computing cores made up from 16,000 computer nodes, each comprising two Intel Ivy Bridge Xeon processors and three Xeon Phi coprocessor chips.

2. Titan – United States

The Titan computer is a Cray XK7 system used by the United States Department of Energy at their Oak Ridge National Laboratory. The former top-ranked Jaguar supercomputer was upgraded in 2012 to become the then most powerful computer (until the Tianhe machine overtook it).

The system performs at 17.59 Pflop/s using 261,632 NVIDIA K20x cores.

3. Sequoia – United States 

The Sequoia computer is based on the now unsupported IBM BlueGene framework. It has been used to make key advances in climate, astronomy and energy application areas.

Located in California’s Lawrence Livermore National Laboratory, the Sequoia platform has achieved 17.17 Pflop/s and uses 1,572,864 cores.

4. K Computer – Japan

The K computer was manufactured by Fujitsu at the RIKEN Advanced Institute for Computational Science (AICS) in Kobe, Japan.

This system hit 10.51 Pflop/s and uses 705,024 SPARC64 processing cores.

5. Mira – Unites States

Also built around the BlueGene architecture, the Mira is one of the older computers on the list. Primarily used by the Unites States Department of Energy (and now housed at the Argonne National Laboratory outside Chicago), it is being succeeded by the upcoming Aurora supercomputer.

The Mira computer has peaked at 8.59 Pflop/s and uses 786,432 cores.

6. Piz Daint – Switzerland

The Piz Daint, a Cray XC30 system, is the most powerful computer in Europe. It’s installed at the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland.

Piz Daint achieved 6.27 Pflop/s on the Linpack benchmark, using 73,808 NVIDIA K20x accelerator cores.

7. Shaheen II – Saudi Arabia

The Shaheen II is the newest computer in the top 10 list. Based around a Cray XC40 system, it went live in 2015 and is the only computer from the region in the top 10. It’s located at the King Abdullah University of Science and Technology.

The platform has performed at 5.536 PFlop/s and uses 196,608 Intel Xeon E5-2698v3 cores.

8. Stampede – United States

The Stampede computer is a Dell PowerEdge C8220 system based around interlinked powerful desktop computers.

It’s based at the Texas Advanced Computing Center and has reached 5.17 Pflop/s.

9. Juqueen – Germany

The only other Europe-based computer, housed at the Forschungszentrum Juelich in Germany, is based on the older BlueGene architecture from IBM. It has reached 5.01 Pflop/s.

10. Vulcan – United States

The Vulcan computer is another IBM BlueGene and is installed at Lawrence Livermore National Laboratory, along with No 3, the Sequoia. It has reached a speed of 4.29 Pflop/s.

President Obama has called for the US to build the world’s fastest computer by 2025 – one that would be 20 times faster than the current fastest, China’s Tianhe-2. It would perform complex simulations and calculations to aid scientific research and national security projects. Currently, the US has almost half of the top 500 fastest supercomputers, but loses out to China when it comes to the top individual spot.

Have you read?
Will we be able to talk to computers?
Artificial intelligence: can we manage the risk?

New laws for a future of cloud computing

Author: Chris Parker is Head of Digital Media for the World Economic Forum.

Image: The BlueGene/L supercomputer at the Lawerence Livermore National Laboratory in California, October 27, 2005. 

Don't miss any update on this topic

Create a free account and access your personalized content collection with our latest publications and analyses.

Sign up for free

License and Republishing

World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.

The views expressed in this article are those of the author alone and not the World Economic Forum.

Stay up to date:

Digital Communications

Share:
The Big Picture
Explore and monitor how Digital Communications is affecting economies, industries and global issues
A hand holding a looking glass by a lake
Crowdsource Innovation
Get involved with our crowdsourced digital platform to deliver impact at scale
World Economic Forum logo
Global Agenda

The Agenda Weekly

A weekly update of the most important issues driving the global agenda

Subscribe today

You can unsubscribe at any time using the link in our emails. For more details, review our privacy policy.

Schwab Foundation for Social Entrepreneurship: Annual Report 2023-24

Why should businesses design  goods for better accessibility to people with disabilities?

About us

Engage with us

  • Sign in
  • Partner with us
  • Become a member
  • Sign up for our press releases
  • Subscribe to our newsletters
  • Contact us

Quick links

Language editions

Privacy Policy & Terms of Service

Sitemap

© 2024 World Economic Forum