The 8 Most Powerful Computers in The World

1. Frontier (United States)

Frontier was built in 2022 by the American multinational information technology company Hewlett Packard Enterprise in collaboration with its subsidiary Cray. It’s the world’s first exascale supercomputer which means it can compute at least one quintillion (10^18) calculations per second. Frontier has a total of 8,730,112 cores and scores 1.1 EFLOPS (or exaflops) on Linpack benchmark tests. It’s based on the latest HPE Cray EX235a architecture and uses a combination of AMD’s 3rd generation 64-core 2GHz 7A53s CPUs and MI250X GPUs. Frontier is also the most efficient supercomputer in the world, with a power efficiency rating of 52.23 gigaflops/watt. Each of its 74 computing cabinets weigh about 8,000 pounds (~3.63 tons), and the entire system costs a whopping $600 million in total.

2. Fugaku (Japan)

Fugaku was built in 2020 by the Japanese IT giant Fujitsu as a successor to the company’s older K computer built in 2011. It was designed to solve the world’s biggest problems, especially slowing down climate change. Fugaku was the world’s fastest supercomputer before Frontier dethroned it in May 2022. It has a total of 7,630,848 cores and scores an impressive 442 PFLOPS (or petaflops), meaning it can do 442 quadrillion calculations per second. It runs on Fujitsu’s A64FX 48-core 2.2GHz processor and has a power efficiency rating of just 14.78 gigaflops/watt, making it quite inefficient by today’s standards. The system cost more than $1 billion, and each of its cabinets weighs 1.6 tons, totaling ~700 tons. 3. LUMI (Finland) LUMI (Large Unified Modern Infrastructure) was built in 2022 by HPE and is located in Finland, making it Europe’s fastest supercomputer. LUMI has a total of 1,110,144 cores and clocks a speed of 151.9 PFLOPS. LUMI runs on the same processor as Frontier and has a power efficiency rating of 51.63 gigaflops/watt, making it the second most efficient supercomputer in the world.

4. Summit (United States)

Summit was built in 2018 by IBM for conducting scientific research. It’s located at Oak Ridge National Laboratory in the US, i.e., the same site as Frontier. Summit has a total of 2,414,592 cores and scores 148.6 PFLOPS. Summit runs on IBM’s POWER9 22-core 3.07GHz CPUs and Nvidia Tesla V100 GPUs and has a power efficiency rating of 14.72 gigaflops/watt, similar to Fugaku.

5. Sierra (United States)

Sierra was built in 2018 and is very similar to Summit as both supercomputers use the same IBM POWER9 22-core CPU architecture and Nvidia Tesla V100 GPUs. However, while Summit was made for scientific research, Sierra was made for running simulations to test and maintain the United States’ nuclear weapons. By running nuclear weapon simulations, the National Nuclear Security Administration (NNSA) of the US can check the effectiveness of its nuclear weapons without physical testing, which helps save costs. Sierra has a total of 1,572,480 cores and scores 94.64 PFLOPS and has a power efficiency of 12.72 gigaflops/watt.

6. Sunway TaihuLight (China)

Sixth on the list, we find our first Chinese supercomputer, Sunway TaihuLight. It was built in 2016 for various purposes such as weather forecasting, pharmaceutical research, life sciences research, and more. Sunway TaihuLight has a total of 10,649,600 CPU cores and scores 93.01 PFLOPS. It runs on the Sunway SW26010 260-core 1.45GHz processor and has a power efficiency rating of just a mere 6.05 gigaflops/watt, making it the most inefficient supercomputer on this list.

7. Perlmutter (United States)

Built in 2021 by HPE, Perlmutter is the world’s seventh most powerful supercomputer—named after the Nobel Prize winner Saul Perlmutter. Just like Sunway TaihuLight, it was made for various purposes, including nuclear fusion simulations, climate projections, material and biological research, and computational cosmology. It is currently located at the National Energy Research Scientific Computing Center (NERSC) and is used by the United States Department of Energy. Perlmutter uses AMD 7763 64-core 2.45GHz CPUs and Nvidia A100 GPUs and has a total of 761,856 cores and clocks a speed of 70.87 PFLOPS, and has a power efficiency rating of 27.37 gigaflops/watt.

8. Selene (United States)

Selene was built in 2020 by Nvidia and is named after the Greek goddess of the moon. Its most prominent purpose was realized in 2020 when the Illinois-based national research lab Argonne National Laboratory used it to study the coronavirus and a potential cure. Selene is also used to train Google’s natural language processing model BERT. Selene has a total of 555,520 cores and scores 63.46 PFLOPS on benchmarks. It is built on the NVIDIA DGX SuperPOD reference architecture and runs on AMD 7742 64-core 2.25GHz processors. It has a power efficiency rating of 24 gigaflops/watt.

Supercomputers Aren’t Science Fiction—They’re Already Here

It’s truly mind-blowing to see just how powerful supercomputers are. The job that would take humans several years to perform and regular personal computers weeks, supercomputers can do in a few seconds. It won’t be long until Frontier is outcompeted by yet another supercomputer that’s faster and more efficient. Modern laptops, PCs, and gaming consoles can already be classified as supercomputers, but they are no match for the best we’ve created. Luckily, as is the nature of tech, it’ll continue to get smaller and eventually end up in our personal gadgets, helping us extend our knowledge and create massive new industries, ready for us to mold.  

Leave a Reply

Your email address will not be published. Required fields are marked *