{"id":50167,"date":"2024-12-10T00:37:32","date_gmt":"2024-12-10T00:37:32","guid":{"rendered":"https:\/\/greenschoolsgreenfuture.org\/?p=50167"},"modified":"2025-08-30T17:21:11","modified_gmt":"2025-08-30T17:21:11","slug":"the-worlds-10-most-powerful-supercomputers","status":"publish","type":"post","link":"https:\/\/greenschoolsgreenfuture.org\/fr\/the-worlds-10-most-powerful-supercomputers\/","title":{"rendered":"The World\u2019s 10 Most Powerful Supercomputers"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

*content from Visual Capitalist; link to original<\/a>*<\/b><\/em><\/p>

\"world's
Image Credit: Visual Capitalist<\/figcaption><\/figure>

Ranked: The World\u2019s 10 Most Powerful Supercomputers<\/b><\/h2>

This was originally posted on our\u00a0Voronoi app<\/a>. Download the app for free on\u00a0iOS<\/a>\u00a0or\u00a0Android<\/a>\u00a0and discover incredible data-driven charts from a variety of trusted sources.<\/i><\/p>

According to the latest supercomputer ranking from\u00a0TOP500<\/a>,\u00a0El Capitan<\/b>\u00a0is the world\u2019s most powerful system, capable of achieving 1,742 petaflops.<\/p>

In this graphic, we visualize the performance and power consumption of the world\u2019s top 10 supercomputers.<\/p>

Data and Key Takeaways<\/b><\/h3>

The data we used to create this graphic is listed in the table below. Figures come from TOP500\u2019s November 2024 ranking.<\/p>

Country<\/b><\/b><\/p><\/td>

System<\/b><\/b><\/p><\/td>

Manufacturer<\/b><\/b><\/p><\/td>

Hardware supplier<\/b><\/b><\/p><\/td>

Max Performance
(PFlop\/s)<\/b><\/b><\/p><\/td>

Power
(kW)<\/b><\/b><\/p><\/td><\/tr><\/thead>

\u00a0US<\/p><\/td>

El Capitan<\/p><\/td>

HP Enterprise<\/p><\/td>

AMD<\/p><\/td>

1,742<\/p><\/td>

29,581<\/p><\/td><\/tr>

\u00a0US<\/p><\/td>

Frontier<\/p><\/td>

HP Enterprise<\/p><\/td>

AMD<\/p><\/td>

1,353<\/p><\/td>

24,607<\/p><\/td><\/tr>

\u00a0US<\/p><\/td>

Aurora<\/p><\/td>

HP Enterprise<\/p><\/td>

Intel<\/p><\/td>

1,012<\/p><\/td>

38,698<\/p><\/td><\/tr>

\u00a0US<\/p><\/td>

Eagle<\/p><\/td>

Microsoft<\/p><\/td>

Intel
NVIDIA<\/p><\/td>

561<\/p><\/td>

\u00a0<\/td><\/tr>

\u00a0Italy<\/p><\/td>

HPC6<\/p><\/td>

HP Enterprise<\/p><\/td>

AMD<\/p><\/td>

478<\/p><\/td>

8,461<\/p><\/td><\/tr>

\u00a0Japan<\/p><\/td>

Supercomputer
Fugaku<\/p><\/td>

Fujitsu<\/p><\/td>

Fujitsu<\/p><\/td>

442<\/p><\/td>

29,899<\/p><\/td><\/tr>

\u00a0Switzerland<\/p><\/td>

Alps<\/p><\/td>

HP Enterprise<\/p><\/td>

NVIDIA<\/p><\/td>

435<\/p><\/td>

7,124<\/p><\/td><\/tr>

\u00a0Finland<\/p><\/td>

LUMI<\/p><\/td>

HP Enterprise<\/p><\/td>

AMD<\/p><\/td>

380<\/p><\/td>

7,107<\/p><\/td><\/tr>

\u00a0Italy<\/p><\/td>

Leonardo<\/p><\/td>

EVIDEN<\/p><\/td>

Intel
NVIDIA<\/p><\/td>

241<\/p><\/td>

7,494<\/p><\/td><\/tr>

\u00a0US<\/p><\/td>

Tuolumne<\/p><\/td>

HP Enterprise<\/p><\/td>

AMD<\/p><\/td>

208<\/p><\/td>

3,387<\/p><\/td><\/tr><\/tbody><\/table>

These ranking highlights America\u2019s position as a global leader in computing power. For instance, the top three supercomputers are located in the U.S., and all of them are classified as\u00a0exascale systems<\/b>.<\/p>

This is a significant change from the\u00a02021 ranking<\/a>, in which Japan\u2019s\u00a0Supercomputer Fugaku<\/b>\u00a0held the top spot.<\/p>

The winner of this year\u2019s ranking is\u00a0El Capitan<\/b>, which became operational in 2024 and is the third exascale system deployed by the United States.<\/p>

Sponsored by the U.S. Department of Energy, El Capitan was manufactured by HP Enterprise Cray and features an unknown number of AMD Instict MI300A accelerated processing units (APUs).<\/p>

What\u2019s An Exascale Computer?<\/b><\/h3>

An exascale computer is capable of performing at least 1\u00a0exaflop<\/b>\u00a0(1 quintillion operations per second).<\/p>

Note that in this ranking, performance is measured in petaflops (1 quadrillion). 1,000 petaflops is equal to 1 exaflop.<\/p>

In realistic terms, exascale computers can handle massive datasets and solve problems at unprecedented speed. Use cases include:<\/p>