US
back on top
The
latest TOP500 list of the fastest supercomputers in the world is out, and while the
US is back in pole position for the first time in six years, Chinese machines
continue to dominate the wider list.
The
new TOP500 list is led by Summit, a US
Department of Energy supercomputer capable of performing 122 quadrillion
floating-point operations per second.
While
there are many changes in the top 25, most of machines still rely on vast
numbers of Intel CPUs, aided by Nvidia GPUs or many-core Intel Xeon Phi
processors.
Here
are the 25 most powerful machines in the TOP500 list of supercomputers.
Here
we go:
1.
Summit
Summit
is housed at Oak Ridge National Laboratory (ORNL), where it aids in research
into subjects like material science, cancer, and fusion energy for the US
Department of Energy (DoE).
The
last time a US supercomputer topped the TOP500 list of the world's fastest
supercomputers was in 2012, when the spot was held by the Titan supercomputer,
also based at ORNL.
The
machine has 4,356 nodes, each equipped with two 22-core Power9 CPUs, and six
Nvidia Tesla V100 GPUs. Its nodes are linked using a Mellanox dual-rail EDR
InfiniBand network.
Processor cores: 2,282,544
Max performance (Linpack benchmark):
122.3PFlop/s
Memory: 2.8PB
Power consumption: 8,805.50kW
Image:
Oak Ridge National Laboratory
2.
Sunway TaihuLight
The
former number one machine, the Sunway TaihuLight until recently set a new
standard for supercomputing speed.
Based
in the National Supercomputing Center in the city of Wuxi, the Chinese system
performs calculations to aid research and engineering work, ranging from
climate modelling to advanced manufacturing.
Unlike
most other supercomputers, the TaihuLight doesn't rely on Intel CPUs but
instead utilises a custom ShenWei processor, a RISC CPU with 260 cores, and
custom interconnects made in Wuxi.
Processor cores: 10,649,600
Max performance (Linpack benchmark): 93PFLOPS
- quadrillion floating point operations per second
Memory: 1.3PB
Power consumption: 15,371kW
Image:
National Supercomputing Center
3.
Sierra
Tasked
with the crucial role of simulating tests of nuclear weapons in the US
stockpile, this new machine is based at the Lawrence Livermore National
Laboratory in California.
The
supercomputer relies on a mix of IBM Power9 CPUs and Nvidia Volta GPUs and is
significantly more capable than the lab's existing Sequoia supercomputer, with
Sierra able to sustain four-to-six times the performance and five-to-seven times
the workload of the older machine.
Processor cores: 1,572,480
Max performance (Linpack benchmark):
71,610TFlop/s
Memory: 1.4PB
Image:
Lawrence Livermore National Laboratory
4.
Tianhe-2
Once
the fastest supercomputer in the world, the Tianhe-2 is capable of more than 33
quadrillion calculations per second.
Otherwise
known as the Milky Way 2, the Tianhe-2 supercomputer memory is based in the
National Supercomputer Center in Guangzho, China.
The
machine is capable of carrying out a massive number of operations in parallel,
spreading tasks between its millions of cores. Each of the machine's nodes has
two Intel Xeon E5 Ivy Bridge processors and custom-built Matrix-2000
coprocessors.
Processor cores: 4,981,760
Max performance (Linpack benchmark): 61.4PFLOPS
- quadrillion floating point operations per second
Memory: 2.3PB
Power consumption: 18,482kW
Image:
Zhao zilong - Imaginechina
5.
ABCI
Based
at the National Institute of Advanced Industrial Science and Technology in
Japan, ABCI (AI Bridging Cloud Infrastructure) is engaged in research and
development of artificial intelligence technologies.
As
well as being a processing powerhouse, the system also ranks highly for energy
efficiency, claiming eighth place in the Green500 list for its 12.054 gigaflops
per watt operating performance.
The
Fujitsu-built supercomputer is powered by 20-core Intel Xeon Gold processors,
along with Nvidia Tesla V100 GPUs.
Processor cores: 391,680
Max performance (Linpack benchmark):
19,880TFlop/s
Memory: 417,792GB
Power consumption: 1,649.25kW
Image:
National Institute of Advanced Industrial Science and Technology
6. Piz
Daint
The
fastest system in Europe and number six machine in the world is Piz Daint,
based at the Swiss National Supercomputing Centre.
A
recent upgrade to the Cray XC50 research machine doubled its performance, with
Nvidia Tesla P100 GPUs added to its cluster of 2.2GHz Intel Xeon E5-2692 CPUs.
The
Piz Daint has come a long way, entering the TOP500 supercomputer list at number
114 in 2012, but steadily climbing thanks to repeated upgrades.
Processor cores: 361,760
Max performance (Linpack benchmark): 19.6PFLOPS
- quadrillion floating point operations per second
Memory: 340,480GB
Power consumption: 2,272kW
Image:
Swiss National Supercomputing Center
7.
Titan
Once
the world's fastest, this US-based supercomputer slips down to seventh place.
Capable
of handling more than 17 quadrillion calculations per second, Titan helps
researchers at the US Oak Ridge National Laboratory probe climate change,
alternate fuel sources, astrophysics and other major scientific challenges.
The
Cray XK7 machine relies on a mix of processors, both AMD Opteron 6274
processors, clocked at 2.2GHz, and NVIDIA K20x accelerators.
Processor cores: 560,640
Max performance (Linpack benchmark): 17.6PFLOPS
- quadrillion floating point operations per second
Memory: 710TB
Power consumption: 8,209kW
Image:
Oak Ridge National Laboratory
8.
Sequoia
Another
former frontrunner, Sequoia was not only the most powerful supercomputer in its
day but also one of the most efficient.
The
IBM Blue Gene/Q system remains a processing powerhouse, and is used used by the
US Lawrence Livermore National Laboratory to model massively complex processes,
ranging from approximating the universe to the beating of a human heart. It
relies on more than one million Power BQC cores.
Processor cores: 1,572,864
Max performance (Linpack benchmark): 17.2PFLOPS
- quadrillion floating point operations per second
Memory: 1.6PB
Power consumption: 7,890kW
Image:
Lawrence Livermore National Laboratory
9.
Trinity
The
Trinity supercomputer is another machine engaged in helping the US test the
effectiveness of its nuclear arsenal.
Based
at Los Alamos National Laboratory, Trinity simulates nuclear explosions using
hundreds of thousands of processors.
Processor cores: 979,968
Max performance (Linpack benchmark): 14.1PFLOPS
- quadrillion floating point operations per second
Power consumption: 3,844kW
Image:
Los Alamos National Laboratory
10.
Cori
The
flagship machine at the National Energy Research Scientific Computing Center in
Berkeley, California, Cori was a new entry in the list last year.
Named
after the pioneering biochemist Gerty Cori, the system runs on a mix of Intel
Xeon Haswell processors and Intel Xeon Phi many-core CPUs.
Processor cores: 622,336
Max performance (Linpack benchmark): 14PFLOPS
- quadrillion floating point operations per second
Memory: 878,592GB
Power consumption: 3,939kW
Image:
National Energy Research Scientific Computing Center
11.
Nurion
The
research system is a type of Cray CS500 supercomputer, seen above, and relies
on a mix of 68-core Intel Xeon Phi co-processors and Intel Omni-Path
interconnects.
Processor cores: 570,020
Max performance (Linpack benchmark):
13,929.3TFlop/s
Image:
Cray
12.
Oakforest-PACS
Formerly
Japan's fastest supercomputer, the machine is based at Joint Center for
Advanced High Performance Computing in Kashiwa.
Dropping
slightly down the rankings this year, the Oakforest-PACS relies on an array of
68-core Intel Xeron Phi 7250 processors.
Processor cores: 556,104
Max performance (Linpack benchmark): 13.6PFLOPS
- quadrillion floating point operations per second
Memory: 919,296GB
Power consumption: 2,719kW
Image:
University of Tokyo
13.
HPC4
Hosted
outside of Milan, this Spanish machine will be used for seismic and
petroleum-system modelling.
Noted
for its energy efficiency, the supercomputer uses a mix of 24-core Intel
Platinum 8160 CPUs and Nvidia Tesla P100 GPUs.
Processor cores: 253,600
Max performance (Linpack benchmark):
12,210TFlop/s
Memory: 304,320GB
Image:
Eni S.p.A.
14.
Tera 1000-2
The
Bull Sequana X1000 supercomputer has been installed at the French Alternative
Energies and Atomic Energy Commission. Its installation is part of the Tera
1000 project to eventually develop an exascale supercomputer.
Processor cores: 561,408
Max performance (Linpack benchmark):
11,965.5 TFlop/s
Memory: 1.6PB
Power consumption: 1,248.00kW
Image:
Philippe Stroppa
15.
Stampede2
The
Texas Advanced Computing Center's latest supercomputer is the Stampede2. It,
like the original Stampede built in 2012, is a Dell machine.
Processor cores: 367,024
Max performance (Linpack benchmark): 10.7
TFlop/s
Memory: 736,512GB
Image:
Texas ACC
16. K
computer
Japan's
K computer has been a fixture in the top 25 for many years.
Situated
in Kobe's RIKEN Advanced Institute for Computational Science, the K computer's
ample processing power helps tackle pressing global challenges in areas ranging
from disaster prevention to medical research.
It
relies upon more than 700,000 SPARC64 VIIIfx processors, each rated at 2GHz.
Processor cores: 705,024
Max performance (Linpack benchmark): 10.5PFLOPS
- quadrillion floating point operations per second
Memory: 1.4PB
Power consumption: 12,660kW
Image:
Riken Advanced Institute for Computational Science
17.
Mira
Capable
of some 8.6 quadrillion calculations per second, Mira plays a pivotal role in
research at the Argonne National Laboratory in Illinois.
The
IBM BlueGene supercomputer helps US researchers model everything from the
performance of jet engines to the inner workings of the human body.
Driving
this machine are a host of 16-core, 1.6GHz Power BQC processors.
Processor cores: 786,432
Max performance (Linpack benchmark): 8.6PFLOPS
- quadrillion floating point operations per second
Power consumption: 3,945kW
Image:
Argonne National Laboratory
18.
Marconi
The
Marconi supercomputer used by the Italian research consortium Cineca slips down
the charts slightly, despite another recent upgrade.
Processor cores: 312,936
Max performance (Linpack benchmark): 8,413.1
TFlop/s
Memory: 455,168GB
Image:
Francesco Pierantoni
19.
TSUBAME3.0
Used
by the Tokyo Institute of Technology for computational modelling and
simulations, work on TSUBAME 3.0 was started in August of last year.
Processor cores: 135,828
Max performance (Linpack benchmark): 8,125
TFlop/s
Memory: 137,984GB
Power consumption: 792.08kW
Image:
Nvidia / Tokyo Institute of Technology
20.
United Kingdom Meteorological Office
It
might not have a name, but the UKMO's supercomputer is the 20th fastest in the
world. The Cray XC40 was first launched in 2016 and has cracked the top 25 once
again in this list.
Processor cores: 241,920
Max performance (Linpack benchmark):
7,038.93 TFlop/s
Memory: 430,080GB
Image:
UK Met Office
21.
Theta
A
recent specs boost helps Argonne's Theta supercomputer retain its place in the
top 25.
Processor cores: 280,320
Max performance (Linpack benchmark): 6,920.9
TFlop/s
Image
Argonne National Lab
22. MareNostrum
Another
relative newcomer to the top 500 list is the Barcelona Supercomputing Center's
MareNostrum.
Processor cores: 153,216
Max performance (Linpack benchmark): 6,470.8
TFlop/s
Memory: 331,776 GB
Power consumption: 1,632.00kW
Image:
Barcelona SCC
23.
JUWELS Module 1
The
first module in the JUWELS supercomputer, the German machine consist of about
2,550 compute nodes, each with two Intel Xeon 24-core Skylake CPUs and 96 GiB
of memory. About 1 in 50 nodes also use Nvidia Volta GPUs to boost their
parallel processing.
Work
on adding a second module, optimized for massively parallel workloads, is
scheduled to begin in 2020.
Processor cores: 114,480
Max performance (Linpack benchmark):
6,177.7TFlop/s
Memory: 264,096GB
Power consumption: 1,361kW
Image:
Forschungszentrum Juelich
24.
Pleiades
Venerable
in supercomputer years, NASA's Pleiades has been around since 2011. Its place
on the list has risen as high as number 7 but amid fierce competition this year
drops to 24.
Processor cores: 241,108
Max performance (Linpack benchmark):
5,951.55 TFlop/s
Memory: 917,344 GB
Power consumption: 4,407kW
Image:
NASA
25.
Japan Meteorological Agency Cray XC50
This
latest Japan Meteorological Agency (JMA) machine can manage 10 times more
calculations than its predecessor, as well as handling more data.
Alongside
being used to help compile everyday forecasts, the JMA computer will help
predict extreme weather, such as typhoons and torrential rain.
Processor cores: 135,792
Max performance (Linpack benchmark):
5,730.5TFlop/s
Power consumption: 1,354kW
Image:
Japan Meteorological Agency
The U.S is the leading nation in the SUPERCOMPUTER trend and they are the highest exporter of CHIPS and TECHNOLOGY in the industry, no wonder they also have the highest number of SUPERCOMPUTER in the country. watch out for more here as they evolve. thank you.
No comments:
Post a Comment