Supercomputer

 Article

 Talk

 Read

 Edit

 View history

Tools

Appearance

hide

Text

Small

Standard

Large

Width


Standard

Wide

Color

Automatic

Light

Dark

Checked

From Wikipedia, the free encyclopedia

For other uses, see Supercomputer (disambiguation).

The Blue Gene/P supercomputer

"Intrepid" at Argonne National Laboratory (pictured 2007) runs 164,000 processor cores
using normal data center air conditioning, grouped in 40 racks/cabinets connected by a high-
speed 3D torus network.[1][2]

A supercomputer is a type of computer with a high level of performance as compared to a

general-purpose computer. Supercomputers play an important role in the field
of computational science, and are used for a wide range of computationally intensive tasks
in various fields including quantum mechanics, weather forecasting, climate research, oil and
gas exploration, molecular modeling (computing the structures and properties of chemical
compounds, biological macromolecules, polymers, and crystals), and physical simulations
(such as simulations of aerodynamics, of the early moments of the universe, and of nuclear
weapons). They have been essential in the field of cryptanalysis.[3]
The performance of a supercomputer is commonly measured in floating-point operations
per second (FLOPS) instead of million instructions per second (MIPS). Since 2022, exascale
supercomputers have existed which can perform over 1018 FLOPS.[4] For comparison, a
desktop computer has performance in the range of hundreds of gigaFLOPS (1011) to tens of
teraFLOPS (1013).[5][6] Since November 2017, all of the world's fastest 500 supercomputers run
on Linux-based operating systems.[7] Additional research is being conducted in the United
States, the European Union, Taiwan, Japan, and China to build faster, more powerful and
technologically superior exascale supercomputers.[8]

Supercomputers were introduced in the 1960s, and for several decades the fastest was
made by Seymour Cray at Control Data Corporation (CDC), Cray Research and subsequent
companies bearing his name or monogram. The first such machines were highly tuned
conventional designs that ran quicker than their more general-purpose contemporaries.
Through the decade, increasing amounts of parallelism were added, with one to
four processors being typical. In the 1970s, vector processors operating on large arrays of
data came to dominate. A notable example is the highly successful Cray-1 of 1976. Vector
computers remained the dominant design into the 1990s. From then until today, massively
parallel supercomputers with tens of thousands of off-the-shelf processors became the
norm.[9][10]

The U.S. has long been a leader in the supercomputer field, initially through Cray's nearly
uninterrupted dominance, and later through a variety of technology companies. Japan made
significant advancements in the field during the 1980s and 1990s, while China has become
increasingly active in supercomputing in recent years. As of November 2024, Lawrence
Livermore National Laboratory's El Capitan is the world's fastest supercomputer.[11] The US
has five of the top 10; Italy two, Japan, Finland, Switzerland have one each.[12]

History

Main article: History of supercomputing

 A circuit board from the IBM 7030

The CDC 6600. Behind the system console are two of

the "arms" of the plus-sign shaped cabinet with the covers opened. Each arm of the machine
had up to four such racks. On the right is the cooling system.

A Cray-1 preserved at the Deutsches Museum

In 1960, UNIVAC built the Livermore Atomic Research Computer (LARC), today considered
among the first supercomputers, for the US Navy Research and Development Center. It still
used high-speed drum memory, rather than the newly emerging disk drive technology.
[13]
Also, among the first supercomputers was the IBM 7030 Stretch. The IBM 7030 was built
by IBM for the Los Alamos National Laboratory, which then in 1955 had requested a
computer 100 times faster than any existing computer. The IBM 7030 used transistors,
magnetic core memory, pipelined instructions, prefetched data through a memory controller
and included pioneering random access disk drives. The IBM 7030 was completed in 1961
and despite not meeting the challenge of a hundredfold increase in performance, it was
purchased by the Los Alamos National Laboratory. Customers in England and France also
bought the computer, and it became the basis for the IBM 7950 Harvest, a supercomputer
built for cryptanalysis.[14]

The third pioneering supercomputer project in the early 1960s was the Atlas at
the University of Manchester, built by a team led by Tom Kilburn. He designed the Atlas to
have memory space for up to a million words of 48 bits, but because magnetic storage with
such a capacity was unaffordable, the actual core memory of the Atlas was only 16,000
words, with a drum providing memory for a further 96,000 words. The Atlas
Supervisor swapped data in the form of pages between the magnetic core and the drum.
The Atlas operating system also introduced time-sharing to supercomputing, so that more
than one program could be executed on the supercomputer at any one time.[15] Atlas was a
joint venture between Ferranti and Manchester University and was designed to operate at
processing speeds approaching one microsecond per instruction, about one million
instructions per second.[16]

The CDC 6600, designed by Seymour Cray, was finished in 1964 and marked the transition
from germanium to silicon transistors. Silicon transistors could run more quickly and the
overheating problem was solved by introducing refrigeration to the supercomputer design.
[17]
Thus, the CDC6600 became the fastest computer in the world. Given that the 6600
outperformed all the other contemporary computers by about 10 times, it was dubbed
a supercomputer and defined the supercomputing market, when one hundred computers
were sold at $8 million each.[18][19][20][21]

Cray left CDC in 1972 to form his own company, Cray Research.[19] Four years after leaving
CDC, Cray delivered the 80 MHz Cray-1 in 1976, which became one of the most successful
supercomputers in history.[22][23] The Cray-2 was released in 1985. It had eight central
processing units (CPUs), liquid cooling and the electronics coolant liquid Fluorinert was
pumped through the supercomputer architecture. It reached 1.9 gigaFLOPS, making it the
first supercomputer to break the gigaflop barrier.[24]

Massively parallel designs

Main articles: Supercomputer architecture and Parallel computer hardware

 A cabinet of the massively parallel Blue Gene/L, showing
the stacked blades, each holding many processors

The only computer to seriously challenge the Cray-1's performance in the 1970s was
the ILLIAC IV. This machine was the first realized example of a true massively
parallel computer, in which many processors worked together to solve different parts of a
single larger problem. In contrast with the vector systems, which were designed to run a
single stream of data as quickly as possible, in this concept, the computer instead feeds
separate parts of the data to entirely different processors and then recombines the results.
The ILLIAC's design was finalized in 1966 with 256 processors and offer speed up to
1 GFLOPS, compared to the 1970s Cray-1's peak of 250 MFLOPS. However, development
problems led to only 64 processors being built, and the system could never operate more
quickly than about 200 MFLOPS while being much larger and more complex than the Cray.
Another problem was that writing software for the system was difficult, and getting peak
performance from it was a matter of serious effort.

But the partial success of the ILLIAC IV was widely seen as pointing the way to the future of
supercomputing. Cray argued against this, famously quipping that "If you were plowing a
field, which would you rather use? Two strong oxen or 1024 chickens?"[25] But by the early
1980s, several teams were working on parallel designs with thousands of processors,
notably the Connection Machine (CM) that developed from research at MIT. The CM-1 used
as many as 65,536 simplified custom microprocessors connected together in a network to
share data. Several updated versions followed; the CM-5 supercomputer is a massively
parallel processing computer capable of many billions of arithmetic operations per second.
[26]

In 1982, Osaka University's LINKS-1 Computer Graphics System used a massively

parallel processing architecture, with 514 microprocessors, including 257 Zilog Z8001 control
processors and 257 iAPX 86/20 floating-point processors. It was mainly used for rendering
realistic 3D computer graphics.[27] Fujitsu's VPP500 from 1992 is unusual since, to achieve
higher speeds, its processors used GaAs, a material normally reserved for microwave
applications due to its toxicity.[28] Fujitsu's Numerical Wind Tunnel supercomputer used 166
vector processors to gain the top spot in 1994 with a peak speed of 1.7 gigaFLOPS
(GFLOPS) per processor.[29][30] The Hitachi SR2201 obtained a peak performance of
600 GFLOPS in 1996 by using 2048 processors connected via a fast three-
dimensional crossbar network.[31][32][33] The Intel Paragon could have 1000 to 4000 Intel
i860 processors in various configurations and was ranked the fastest in the world in 1993.
The Paragon was a MIMD machine which connected processors via a high speed two-
dimensional mesh, allowing processes to execute on separate nodes, communicating via
the Message Passing Interface.[34]

Software development remained a problem, but the CM series sparked off considerable
research into this issue. Similar designs using custom hardware were made by many
companies, including the Evans & Sutherland ES-1, MasPar, nCUBE, Intel iPSC and
the Goodyear MPP. But by the mid-1990s, general-purpose CPU performance had improved
so much in that a supercomputer could be built using them as the individual processing
units, instead of using custom chips. By the turn of the 21st century, designs featuring tens
of thousands of commodity CPUs were the norm, with later machines adding graphic
units to the mix.[9][10]

In 1998, David Bader developed the first Linux supercomputer using commodity parts.
[35]
While at the University of New Mexico, Bader sought to build a supercomputer running
Linux using consumer off-the-shelf parts and a high-speed low-latency interconnection
network. The prototype utilized an Alta Technologies "AltaCluster" of eight dual, 333 MHz,
Intel Pentium II computers running a modified Linux kernel. Bader ported a significant
amount of software to provide Linux support for necessary components as well as code from
members of the National Computational Science Alliance (NCSA) to ensure interoperability,
as none of it had been run on Linux previously.[36] Using the successful prototype design, he
led the development of "RoadRunner," the first Linux supercomputer for open use by the
national science and engineering community via the National Science Foundation's National
Technology Grid. RoadRunner was put into production use in April 1999. At the time of its
deployment, it was considered one of the 100 fastest supercomputers in the world. [36]
[37]
Though Linux-based clusters using consumer-grade parts, such as Beowulf, existed prior
to the development of Bader's prototype and RoadRunner, they lacked the scalability,
bandwidth, and parallel computing capabilities to be considered "true" supercomputers. [36]
 The CPU share of TOP500

Diagram of a three-dimensional torus

interconnect used by systems such as Blue Gene, Cray XT3, etc.

Systems with a massive number of processors generally take one of two paths. In the grid
computing approach, the processing power of many computers, organized as distributed,
diverse administrative domains, is opportunistically used whenever a computer is available.
[38]
In another approach, many processors are used in proximity to each other, e.g. in
a computer cluster. In such a centralized massively parallel system the speed and flexibility
of the interconnect becomes very important and modern supercomputers have used various
approaches ranging from enhanced Infiniband systems to three-dimensional torus
interconnects.[39][40] The use of multi-core processors combined with centralization is an
emerging direction, e.g. as in the Cyclops64 system.[41][42]

As the price, performance and energy efficiency of general-purpose graphics processing

units (GPGPUs) have improved, a number of petaFLOPS supercomputers such as Tianhe-
I and Nebulae have started to rely on them.[43] However, other systems such as the K
computer continue to use conventional processors such as SPARC-based designs and the
overall applicability of GPGPUs in general-purpose high-performance computing applications
has been the subject of debate, in that while a GPGPU may be tuned to score well on
specific benchmarks, its overall applicability to everyday algorithms may be limited unless
significant effort is spent to tune the application to it.[44] However, GPUs are gaining ground,
and in 2012 the Jaguar supercomputer was transformed into Titan by retrofitting CPUs with
GPUs.[45][46][47]
High-performance computers have an expected life cycle of about three years before
requiring an upgrade.[48] The Gyoukou supercomputer is unique in that it uses both a
massively parallel design and liquid immersion cooling.

Special purpose supercomputers

A number of special-purpose systems have been designed, dedicated to a single problem.

This allows the use of specially programmed FPGA chips or even custom ASICs, allowing
better price/performance ratios by sacrificing generality. Examples of special-purpose
supercomputers include Belle,[49] Deep Blue,[50] and Hydra[51] for playing chess, Gravity
Pipe for astrophysics,[52] MDGRAPE-3 for protein structure prediction and molecular
dynamics,[53] and Deep Crack for breaking the DES cipher.[54]

Energy usage and heat management

See also: Computer cooling and Green500

The Summit supercomputer was as of November 2018 the

fastest supercomputer in the world.[55] With a measured power efficiency of 14.668
GFlops/watt it is also the third most energy efficient in the world.[56]

Throughout the decades, the management of heat density has remained a key issue for
most centralized supercomputers.[57][58][59] The large amount of heat generated by a system
may also have other effects, e.g. reducing the lifetime of other system components.[60] There
have been diverse approaches to heat management, from pumping Fluorinert through the
system, to a hybrid liquid-air cooling system or air cooling with normal air
conditioning temperatures.[61][62] A typical supercomputer consumes large amounts of
electrical power, almost all of which is converted into heat, requiring cooling. For
example, Tianhe-1A consumes 4.04 megawatts (MW) of electricity.[63] The cost to power and
cool the system can be significant, e.g. 4 MW at $0.10/kWh is $400 an hour or about $3.5
million per year.
 An IBM HS20 blade

Heat management is a major issue in complex electronic devices and affects powerful
computer systems in various ways.[64] The thermal design power and CPU power
dissipation issues in supercomputing surpass those of traditional computer
cooling technologies. The supercomputing awards for green computing reflect this issue.[65]
[66][67]

The packing of thousands of processors together inevitably generates significant amounts

of heat density that need to be dealt with. The Cray-2 was liquid cooled, and used
a Fluorinert "cooling waterfall" which was forced through the modules under pressure.
[61]
However, the submerged liquid cooling approach was not practical for the multi-cabinet
systems based on off-the-shelf processors, and in System X a special cooling system that
combined air conditioning with liquid cooling was developed in conjunction with the Liebert
company.[62]

In the Blue Gene system, IBM deliberately used low power processors to deal with heat
density.[68] The IBM Power 775, released in 2011, has closely packed elements that require
water cooling.[69] The IBM Aquasar system uses hot water cooling to achieve energy
efficiency, the water being used to heat buildings as well.[70][71]

The energy efficiency of computer systems is generally measured in terms of "FLOPS per
watt". In 2008, Roadrunner by IBM operated at 376 MFLOPS/W.[72][73] In November 2010,
the Blue Gene/Q reached 1684 MFLOPS/W[74] and in June 2011 the top two spots on
the Green 500 list were occupied by Blue Gene machines in New York (one achieving
2097 MFLOPS/W) with the DEGIMA cluster in Nagasaki placing third with 1375 MFLOPS/W.
[75]

Because copper wires can transfer energy into a supercomputer with much higher power
densities than forced air or circulating refrigerants can remove waste heat,[76] the ability of
the cooling systems to remove waste heat is a limiting factor.[77][78] As of 2015, many existing
supercomputers have more infrastructure capacity than the actual peak demand of the
machine – designers generally conservatively design the power and cooling infrastructure to
handle more than the theoretical peak electrical power consumed by the supercomputer.
Designs for future supercomputers are power-limited – the thermal design power of the
supercomputer as a whole, the amount that the power and cooling infrastructure can
handle, is somewhat more than the expected normal power consumption, but less than the
theoretical peak power consumption of the electronic hardware.[79]

Software and system management

Operating systems

Main article: Supercomputer operating systems

Since the end of the 20th century, supercomputer operating systems have undergone major
transformations, based on the changes in supercomputer architecture.[80] While early
operating systems were custom tailored to each supercomputer to gain speed, the trend has
been to move away from in-house operating systems to the adaptation of generic software
such as Linux.[81]

Since modern massively parallel supercomputers typically separate computations from other
services by using multiple types of nodes, they usually run different operating systems on
different nodes, e.g. using a small and efficient lightweight kernel such as CNK or CNL on
compute nodes, but a larger system such as a full Linux distribution on server and I/O nodes.
[82][83][84]

While in a traditional multi-user computer system job scheduling is, in effect,

a tasking problem for processing and peripheral resources, in a massively parallel system,
the job management system needs to manage the allocation of both computational and
communication resources, as well as gracefully deal with inevitable hardware failures when
tens of thousands of processors are present.[85]

Although most modern supercomputers use Linux-based operating systems, each

manufacturer has its own specific Linux distribution, and no industry standard exists, partly
due to the fact that the differences in hardware architectures require changes to optimize
the operating system to each hardware design.[80][86]

Software tools and message passing

Main article: Message passing in computer clusters

See also: Parallel computing and Parallel programming model

Wide-angle view of the ALMA correlator[87]

The parallel architectures of supercomputers often dictate the use of special programming
techniques to exploit their speed. Software tools for distributed processing include
standard APIs such as MPI[88] and PVM, VTL, and open source software such as Beowulf.

In the most common scenario, environments such as PVM and MPI for loosely connected
clusters and OpenMP for tightly coordinated shared memory machines are used. Significant
effort is required to optimize an algorithm for the interconnect characteristics of the
machine it will be run on; the aim is to prevent any of the CPUs from wasting time waiting
on data from other nodes. GPGPUs have hundreds of processor cores and are programmed
using programming models such as CUDA or OpenCL.

Moreover, it is quite difficult to debug and test parallel programs. Special techniques need to
be used for testing and debugging such applications.

Distributed supercomputing

Opportunistic approaches

Main article: Grid computing

Example architecture of a grid computing system

connecting many personal computers over the internet

Opportunistic supercomputing is a form of networked grid computing whereby a "super

virtual computer" of many loosely coupled volunteer computing machines performs very
large computing tasks. Grid computing has been applied to a number of large-
scale embarrassingly parallel problems that require supercomputing performance scales.
However, basic grid and cloud computing approaches that rely on volunteer
computing cannot handle traditional supercomputing tasks such as fluid dynamic
simulations.[89]

The fastest grid computing system is the volunteer computing project Folding@home (F@h).
As of April 2020, F@h reported 2.5 exaFLOPS of x86 processing power. Of this, over
100 PFLOPS are contributed by clients running on various GPUs, and the rest from various
CPU systems.[90]

The Berkeley Open Infrastructure for Network Computing (BOINC) platform hosts a number
of volunteer computing projects. As of February 2017, BOINC recorded a processing power
of over 166 petaFLOPS through over 762 thousand active Computers (Hosts) on the network.
[91]

As of October 2016, Great Internet Mersenne Prime Search's (GIMPS) distributed Mersenne
Prime search achieved about 0.313 PFLOPS through over 1.3 million computers.[92] The
PrimeNet server has supported GIMPS's grid computing approach, one of the earliest
volunteer computing projects, since 1997.

Quasi-opportunistic approaches

Main article: Quasi-opportunistic supercomputing

Quasi-opportunistic supercomputing is a form of distributed computing whereby the "super

virtual computer" of many networked geographically disperse computers performs
computing tasks that demand huge processing power.[93] Quasi-opportunistic
supercomputing aims to provide a higher quality of service than opportunistic grid
computing by achieving more control over the assignment of tasks to distributed resources
and the use of intelligence about the availability and reliability of individual systems within
the supercomputing network. However, quasi-opportunistic distributed execution of
demanding parallel computing software in grids should be achieved through the
implementation of grid-wise allocation agreements, co-allocation subsystems,
communication topology-aware allocation mechanisms, fault tolerant message passing
libraries and data pre-conditioning.[93]

High-performance computing clouds

Cloud computing with its recent and rapid expansions and development have grabbed the
attention of high-performance computing (HPC) users and developers in recent years. Cloud
computing attempts to provide HPC-as-a-service exactly like other forms of services
available in the cloud such as software as a service, platform as a service, and infrastructure
as a service. HPC users may benefit from the cloud in different angles such as scalability,
resources being on-demand, fast, and inexpensive. On the other hand, moving HPC
applications have a set of challenges too. Good examples of such challenges
are virtualization overhead in the cloud, multi-tenancy of resources, and network latency
issues. Much research is currently being done to overcome these challenges and make HPC
in the cloud a more realistic possibility.[94][95][96][97]

In 2016, Penguin Computing, Parallel Works, R-HPC, Amazon Web Services, Univa, Silicon
Graphics International, Rescale, Sabalcore, and Gomput started to offer HPC cloud
computing. The Penguin On Demand (POD) cloud is a bare-metal compute model to execute
code, but each user is given virtualized login node. POD computing nodes are connected via
non-virtualized 10 Gbit/s Ethernet or QDR InfiniBand networks. User connectivity to the
POD data center ranges from 50 Mbit/s to 1 Gbit/s.[98] Citing Amazon's EC2 Elastic Compute
Cloud, Penguin Computing argues that virtualization of compute nodes is not suitable for
HPC. Penguin Computing has also criticized that HPC clouds may have allocated computing
nodes to customers that are far apart, causing latency that impairs performance for some
HPC applications.[99]

Performance measurement

Capability versus capacity

Supercomputers generally aim for the maximum in capability computing rather than
capacity computing. Capability computing is typically thought of as using the maximum
computing power to solve a single large problem in the shortest amount of time. Often a
capability system is able to solve a problem of a size or complexity that no other computer
can, e.g. a very complex weather simulation application.[100]

Capacity computing, in contrast, is typically thought of as using efficient cost-effective

computing power to solve a few somewhat large problems or many small problems.
[100]
Architectures that lend themselves to supporting many users for routine everyday tasks
may have a lot of capacity but are not typically considered supercomputers, given that they
do not solve a single very complex problem.[100]

Performance metrics

See also: LINPACK benchmarks and Grid computing § Fastest virtual supercomputers

Top supercomputer
speeds: logscale speed over 60 years

In general, the speed of supercomputers is measured and benchmarked in FLOPS (floating-

point operations per second), and not in terms of MIPS (million instructions per second), as
is the case with general-purpose computers.[101] These measurements are commonly used
with an SI prefix such as tera-, combined into the shorthand TFLOPS (1012 FLOPS,
pronounced teraflops), or peta-, combined into the shorthand PFLOPS (1015 FLOPS,
pronounced petaflops.) Petascale supercomputers can process one quadrillion (1015)
(1000 trillion) FLOPS. Exascale is computing performance in the exaFLOPS (EFLOPS) range. An
EFLOPS is one quintillion (1018) FLOPS (one million TFLOPS). However, the performance of a
supercomputer can be severely impacted by fluctuation brought on by elements like system
load, network traffic, and concurrent processes, as mentioned by Brehm and Bruhwiler
(2015).[102]

No single number can reflect the overall performance of a computer system, yet the goal of
the Linpack benchmark is to approximate how fast the computer solves numerical problems
and it is widely used in the industry.[103] The FLOPS measurement is either quoted based on
the theoretical floating point performance of a processor (derived from manufacturer's
processor specifications and shown as "Rpeak" in the TOP500 lists), which is generally
unachievable when running real workloads, or the achievable throughput, derived from
the LINPACK benchmarks and shown as "Rmax" in the TOP500 list.[104] The LINPACK
benchmark typically performs LU decomposition of a large matrix.[105] The LINPACK
performance gives some indication of performance for some real-world problems, but does
not necessarily match the processing requirements of many other supercomputer
workloads, which for example may require more memory bandwidth, or may require better
integer computing performance, or may need a high performance I/O system to achieve high
levels of performance.[103]

The TOP500 list

Main article: TOP500

Further information: List of fastest computers and History of supercomputing

Top 20 supercomputers in the

world (June 2014)

Since 1993, the fastest supercomputers have been ranked on the TOP500 list according to
their LINPACK benchmark results. The list does not claim to be unbiased or definitive, but it
is a widely cited current definition of the "fastest" supercomputer available at any given
time.
This is a list of the computers which appeared at the top of the TOP500 list since June 1993,
[106]
and the "Peak speed" is given as the "Rmax" rating. In 2018, Lenovo became the world's
largest provider for the TOP500 supercomputers with 117 units produced.[107]

Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

1,051
,392
(43,8
Lawrenc
08 × 9,988,
e
24- 224
1,7 Livermo
core (43,80
42. HPE re
El Opti 8× 11,0 Slings Linux
1 00 Cray National 20
Cap mized 228 39,6 hot- HPE (TOSS
2,7 EX255 Laborat 24
itan 4th AMD I 16 11 )
46. a ory
Gene nstinct
38 Unit
ration MI300
ed
EPYC A)
States
24C
@1.8
GHz)

2 1,3 Fro HPE 614,6 8,451, 9,06 Slings HPE Oak 20 Linux
53. ntie Cray 56 520 6,17 hot- Ridge 22 (HPE
00 r EX235 (9,60 (38,41 6 11 National Cray
2,0 a 4× 6× Laborat OS)
55. 64- 220 ory
72 core AMD I
Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

Opti
mized
3rd
Gene nstinct Unit
ration MI250 ed
EPYC X) States
64C
@2.0
GHz)

1,104
,896
(21,2 8,159, Argonn Linux
1,0 48 × 232 e (SUSE
12. 52- (63,74 National Linux
HPE 9,26 Slings
00 Aur core 4× Laborat 20 Enter
3 Cray 4,12 hot- HPE
1,9 ora Intel 128 ory 23 prise
EX 8 11
80. Xeon Intel Unit Serve
01 Max Max ed r 15
9470 1550) States SP4)
@2.4
GHz)

4 561 Eagl Micros 172,8 1,900, 2,07 NVIDI Micr Microso 20 Linux
.20 e oft 00 800 3,60 A osoft ft 23 (Ubu
846 (3,60 (14,40 Infinib ntu
Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

0×
48-
core
0×
Intel
132
Xeon Unit
Nvidia and 22.04
.84 NDv5 Platin 0 ed
Hoppe NDR LTS)
um States
r H100
8480
)
C @2.
0 GHz
)

5 477 HPC HPE 213,1 2,930, 3,14 Slings HPE Eni 20 Linux
.90 6 Cray 20 400 3,52 hot- S.p.A 24 (RHEL
606 EX235 (3,33 (13,32 0 11 Eur 8.9)
.97 a 0× 0× opean
64- 220 Union, F
core AMD I errera
Opti nstinct Erbogno
mized MI250 ne, I
3rd X) taly
Gene
ration
EPYC
64C
Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

@2.0
GHz)

7,630
,848
Riken
(158,
Center
Superc 976 ×
442 Tofu for
omput 48- 7,63 Linux
.01 Fug interc Fujits Comput 20
6 er core F - 0,84 (RHEL
537 aku onnec u ational 20
Fugak ujitsu 8 )
.21 tD Science
u A64F
Jap
X @2.
an
2 GHz
)

7 434 Alp HPE 748,8 1,372, 2,12 Slings HPE CSCS 20 Linux
.90 s Cray 00 800 1,60 hot- Swiss 24 (HPE
574 EX254 (10,4 (10,40 0 11 National Cray
.84 n 00 × 0× Superco OS)
72- 132 mputing
Arm Nvidia Centre
Neov Hoppe Switz
erse r H100 erland
V2 )
cores
Nvidi
Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

a
Grace
@3.1
GHz)

186,6
24
(2,91
6× 2,566,
EuroHP
64- 080
C JU
core (11,66
379 HPE Eur Linux
Opti 4× 2,75 Slings
.70 LU Cray opean 20 (HPE
8 mized 220 2,70 hot- HPE
531 MI EX235 Union, K 22 Cray
3rd AMD I 4 11
.51 a ajaani, OS)
Gene nstinct
Finl
ration MI250
and
EPYC X)
64C
@2.0
GHz)

9 241 Leo BullSe 110,5 1,714, 1,82 Quad- Atos EuroHP 20 Linux
.20 nar quana 92 176 4,76 rail C JU 23 (RHEL
306 do XH200 (3,45 (15,87 8 NVIDI Eur 8)[109]
.31 0 6× 2× A opean
32- 108 N HDR1
 Top 10 positions of the 64th TOP500 in November 2024 [108]

R
Tot
m
al
R a
Acc Co
an x
eler res Op
k R Ma
N CP ator (C Inte Y era
(p p nuf Site
a Mo U (e.g. PU rco e tin
re e act count
m del cor GPU s+ nne a g
vi a ure ry
e es ) Ac ct r syst
o k r
(Pe
core cel em
us
taF
s era
)
LO
tor
PS)
s)

core
Xeon
vidia Union,
Platin 00 Infi
Amper Bologna
um niban
e A10 , Ital
8358 d
0) y
@2.6
GHz)

110,5
92
(4,60
Lawrenc
8×
1,050, e
24-
624 Livermo
core
208 HPE (4,608 re
Tuo Opti 1,16 Slings Linux
10 .10 Cray × 228 National 20
lum mized 1,21 hot- HPE (TOSS
288 EX255 AMD I Laborat 24
ne 4th 6 11 )
.88 a nstinct ory
Gene
MI300 Unit
ration
A) ed
EPYC
States
24C
@1.8
GHz)

Legend:[110]
  Rank – Position within the TOP500 ranking. In the TOP500 list table, the computers
are ordered first by their Rmax value. In the case of equal performances (Rmax value)
for different computers, the order is by Rpeak. For sites that have the same
computer, the order is by memory size and then alphabetically.

 Rmax – The highest score measured using the LINPACK benchmarks suite. This is the
number that is used to rank the computers. Measured in quadrillions of 64-
bit floating point operations per second, i.e., petaFLOPS.[111]

 Rpeak – This is the theoretical peak performance of the system. Computed in

petaFLOPS.

 Name – Some supercomputers are unique, at least in their location, and are thus
named by their owner.

 Model – The computing platform as it is marketed.

 Processor – The instruction set architecture or processor microarchitecture,

alongside GPU and accelerators when available.

 Interconnect – The interconnect between computing nodes. InfiniBand is most used

(38%) by performance share, while Gigabit Ethernet is most used (54%) by number of
computers.

 Manufacturer – The manufacturer of the platform and hardware.

 Site – The name of the facility operating the supercomputer.

 Country – The country in which the computer is located.

 Year – The year of installation or last major update.

 Operating system – The operating system that the computer uses.

Applications

The application of supercomputers has evolved significantly since the 1970s, expanding
across numerous fields of scientific and governmental research. In the 1970s, the Cray-1
supercomputer was instrumental in early weather forecasting and aerodynamic research.
The scope broadened in the 1980s with machines like the CDC Cyber facilitating probabilistic
analyses and modeling radiation shielding. The 1990s saw supercomputers, such as the EFF
DES cracker, applied to brute-force tasks like code-breaking.

Moving into the 2000s, supercomputers became crucial for national security applications;
the ASCI Q was used to conduct 3D nuclear test simulations, satisfying the requirements of
the Nuclear Non-Proliferation Treaty without physical testing. The 2010s brought
advancements in molecular dynamics simulations, exemplified by the use of the Tianhe-1A.
The trend has continued into the 2020s, with supercomputers providing powerful tools for
research into outbreak prevention and electrochemical reactions.
Beyond these specific decades, supercomputers have been pivotal in major scientific
endeavors. For instance, the IBM Blue Gene/P was used to simulate a network of artificial
neurons equivalent to one percent of a human cerebral cortex (1.6 billion neurons and 9
trillion connections), and the same team later simulated the entirety of a rat's brain. [112]

Modern applications are diverse and critical. Weather forecasting relies heavily on
supercomputing power, with the National Oceanic and Atmospheric Administration utilizing
these systems to process vast quantities of observational data to enhance forecast accuracy.
[113]
The United States also employs supercomputers through the Advanced Simulation and
Computing Program to maintain and simulate its nuclear stockpile.[114]

The field has its challenges, as highlighted by IBM's abandonment of the ambitious Blue
Waters petascale[115] project in 2011. Despite such setbacks, the utility of supercomputers
continues to grow. A recent example of their critical role occurred in early 2020, when
supercomputers were rapidly deployed to run extensive simulations using numerous
paralleled CPUs to identify compounds with the potential to stop the spread of COVID-19. [116]
[117][118]

Taiwania 3 is a Taiwanese supercomputer which

assisted the scientific community in fighting COVID-19. It was launched in 2020 and has a
capacity of about two to three PetaFLOPS.

Development and trends

Distribution of TOP500
supercomputers among different countries, in November 2025

In the 2010s, China, the United States, the European Union, and others competed to be the
first to create a 1 exaFLOP (1018 or one quintillion FLOPS) supercomputer.[119] Erik P.
DeBenedictis of Sandia National Laboratories has theorized that a zettaFLOPS (1021 or one
sextillion FLOPS) computer is required to accomplish full weather modeling, which could
cover a two-week time span accurately.[120][121][122] Such systems might be built around 2030.
[123]

Many Monte Carlo simulations use the same algorithm to process a randomly generated
data set; particularly, integro-differential equations describing physical transport processes,
the random paths, collisions, and energy and momentum depositions of neutrons, photons,
ions, electrons, etc. The next step for microprocessors may be into the third dimension; and
specializing to Monte Carlo, the many layers could be identical, simplifying the design and
manufacture process.[124]

The cost of operating high performance supercomputers has risen, mainly due to increasing
power consumption. In the mid-1990s a top 10 supercomputer required in the range of
100 kilowatts, in 2010 the top 10 supercomputers required between 1 and 2 megawatts.
[125]
A 2010 study commissioned by DARPA identified power consumption as the most
pervasive challenge in achieving Exascale computing.[126] At the time a megawatt per year in
energy consumption cost about 1 million dollars. Supercomputing facilities were constructed
to efficiently remove the increasing amount of heat produced by modern multi-core central
processing units. Based on the energy consumption of the Green 500 list of supercomputers
between 2007 and 2011, a supercomputer with 1 exaFLOPS in 2011 would have required
nearly 500 megawatts. Operating systems were developed for existing hardware to conserve
energy whenever possible.[127] CPU cores not in use during the execution of a parallelized
application were put into low-power states, producing energy savings for some
supercomputing applications.[128]

The increasing cost of operating supercomputers has been a driving factor in a trend toward
bundling of resources through a distributed supercomputer infrastructure. National
supercomputing centers first emerged in the US, followed by Germany and Japan. The
European Union launched the Partnership for Advanced Computing in Europe (PRACE) with
the aim of creating a persistent pan-European supercomputer infrastructure with services to
support scientists across the European Union in porting, scaling and optimizing
supercomputing applications.[125] Iceland built the world's first zero-emission supercomputer.
Located at the Thor Data Center in Reykjavík, Iceland, this supercomputer relies on
completely renewable sources for its power rather than fossil fuels. The colder climate also
reduces the need for active cooling, making it one of the greenest facilities in the world of
computers.[129]

Funding supercomputer hardware also became increasingly difficult. In the mid-1990s a top
10 supercomputer cost about 10 million euros, while in 2010 the top 10 supercomputers
required an investment of between 40 and 50 million euros.[125] In the 2000s national
governments put in place different strategies to fund supercomputers. In the UK the national
government funded supercomputers entirely and high performance computing was put
under the control of a national funding agency. Germany developed a mixed funding model,
pooling local state funding and federal funding.[125]

In fiction

Main article: AI takeover

Examples of supercomputers in fiction include HAL 9000, Multivac, The Machine

Stops, GLaDOS, SHODAN, The Evitable Conflict, Vulcan's Hammer, Colossus, WOPR, AM,
and Deep Thought. A supercomputer from Thinking Machines was mentioned as the
supercomputer used to sequence the DNA extracted from preserved parasites in the Jurassic
Park series.

See also

 ACM/IEEE Supercomputing Conference

 ACM SIGHPC

 High-performance computing

 High-performance technical computing

 Jungle computing

 Metacomputing

 Nvidia Tesla Personal Supercomputer

 Parallel computing

 Supercomputing in China

 Supercomputing in Europe

 Supercomputing in India

 Supercomputing in Japan

 Supercomputing in Taiwan

 SLURM

 Testing high-performance computing applications

 Ultra Network Technologies

 Quantum computing

References

1. "IBM Blue gene announcement". [Link]. 26 June 2007. Archived from the
original on 8 July 2007. Retrieved 9 June 2012.
2. "Intrepid". Argonne Leadership Computing Facility. Argonne National Laboratory.
Retrieved 26 March 2020.

3. Lemke, Tim (8 May 2013). "NSA Breaks Ground on Massive Computing

Center". Archived from the original on 9 June 2013. Retrieved 11 December 2013.

4. "Frontier keeps top spot, but Aurora officially becomes the second exascale
machine". Top 500. Archived from the original on 12 December 1998. Retrieved 13
October 2024.

5. "AMD Playstation 5 GPU Specs". TechPowerUp. Retrieved 11 September 2021.

6. "NVIDIA GeForce GT 730 Specs". TechPowerUp. Retrieved 11 September 2021.

7. "Operating system Family / Linux". [Link]. Archived from the original on 19

November 2012. Retrieved 30 November 2017.

8. Anderson, Mark (21 June 2017). "Global Race Toward Exascale Will Drive
Supercomputing, AI to Masses." [Link]. Retrieved 20 January 2019.

9. Hoffman, Allan R.; et al. (1990). Supercomputers: directions in technology and

applications. National Academies. pp. 35–47. ISBN 978-0-309-04088-4.

10. Hill, Mark Donald; Jouppi, Norman Paul; Sohi, Gurindar (1999). Readings in
computer architecture. Gulf Professional. pp. 40–49. ISBN 978-1-55860-539-8.

11. "El Capitan achieves top spot, Frontier and Aurora follow
behind". [Link]. Archived from the original on 20 November 2024.
Retrieved 19 November 2024.

12. "Japan Captures TOP500 Crown with Arm-Powered Supercomputer - TOP500

website". [Link]. Archived from the original on 26 June 2020.
Retrieved 29 June 2020.

13. Eric G. Swedin; David L. Ferro (2007). Computers: The Life Story of a Technology. JHU
Press. p. 57. ISBN 9780801887741.

14. Eric G. Swedin; David L. Ferro (2007). Computers: The Life Story of a Technology. JHU
Press. p. 56. ISBN 9780801887741.

15. Eric G. Swedin; David L. Ferro (2007). Computers: The Life Story of a Technology. JHU
Press. p. 58. ISBN 9780801887741.

16. The Atlas, University of Manchester, archived from the original on 28 July 2012,
retrieved 21 September 2010

17. The Supermen, Charles Murray, Wiley & Sons, 1997.

18. Paul E. Ceruzzi (2003). A History of Modern Computing. MIT Press. p. 161. ISBN 978-
0-262-53203-7.
19. Hannan, Caryn (2008). Wisconsin Biographical Dictionary. State History Publications.
pp. 83–84. ISBN 978-1-878592-63-7.

20. John Impagliazzo; John A. N. Lee (2004). History of computing in education. Springer
Science & Business Media. p. 172. ISBN 978-1-4020-8135-4.

21. Andrew R. L. Cayton; Richard Sisson; Chris Zacher (2006). The American Midwest: An
Interpretive Encyclopedia. Indiana University Press. p. 1489. ISBN 978-0-253-00349-
2.

22. Readings in computer architecture by Mark Donald Hill, Norman Paul Jouppi,
Gurindar Sohi 1999 ISBN 978-1-55860-539-8 page 41-48

23. Milestones in computer science and information technology by Edwin D. Reilly

2003 ISBN 1-57356-521-0 page 65

24. Due to Soviet propaganda, it can be read sometimes that the Soviet supercomputer
M13 was the first to reach the gigaflops barrier. Actually, the M13 building began in
1984, but it was not operational before 1986. Rogachev Yury Vasilievich, Russian
Virtual Computer Museum Archived 16 June 2021 at the Wayback Machine

25. "Seymour Cray Quotes". BrainyQuote. Archived from the original on 28 December
2018. Retrieved 28 February 2019.

26. Steve Nelson (3 October 2014). "[Link] :

Supercomputers". Archived from the original on 25 December 2014. Retrieved 23
December 2014.

27. "LINKS-1 Computer Graphics System-Computer

Museum". [Link]. Archived from the original on 7 May 2017.
Retrieved 19 April 2017.

28. "VPP500 (1992) - Fujitsu Global". Archived from the original on 7 August 2020.
Retrieved 9 April 2020.

29. "TOP500 Annual Report 1994". [Link]. 1 October 1996. Archived from the
original on 20 January 2019. Retrieved 9 June 2012.

30. N. Hirose & M. Fukuda (1997). "Numerical Wind Tunnel (NWT) and CFD Research at
National Aerospace Laboratory". Proceedings High Performance Computing on the
Information Superhighway. HPC Asia '97. Proceedings of HPC-Asia '97. IEEE Computer
SocietyPages. pp. 99–103. doi:10.1109/HPC.1997.592130. ISBN 0-8186-7901-8.

31. H. Fujii, Y. Yasuda, H. Akashi, Y. Inagami, M. Koga, O. Ishihara, M. Syazwan, H. Wada,

T. Sumimoto, Architecture and performance of the Hitachi SR2201 massively parallel
processor system Archived 17 July 2020 at the Wayback Machine, Proceedings of
11th International Parallel Processing Symposium, April 1997, pages 233–241.
32. Y. Iwasaki, The CP-PACS project, Nuclear Physics B: Proceedings Supplements,
Volume 60, Issues 1–2, January 1998, pages 246–254.

33. A.J. van der Steen, Overview of recent supercomputers Archived 17 July 2020 at
the Wayback Machine, Publication of the NCF, Stichting Nationale Computer
Faciliteiten, the Netherlands, January 1997.

34. Scalable input/output: achieving system balance by Daniel A. Reed 2003 ISBN 978-0-
262-68142-1 page 182

35. "David Bader Selected to Receive the 2021 IEEE Computer Society Sidney Fernbach
Award". IEEE Computer Society. 22 September 2021. Archived from the original on
11 November 2023. Retrieved 12 October 2023.

36. Bader, David A. (2021). "Linux and Supercomputing: How My Passion for Building
COTS Systems Led to an HPC Revolution". IEEE Annals of the History of
Computing. 43 (3): 73–80. Bibcode:2021IAHC...43c..73B. doi:10.1109/
MAHC.2021.3101415. S2CID 237318907.

37. Fleck, John (8 April 1999). "UNM to crank up $400,000 supercomputer

today". Albuquerque Journal. p. D1.

38. Prodan, Radu; Fahringer, Thomas (2007). Grid computing: experiment management,
tool integration, and scientific workflows. Springer. pp. 1–4. ISBN 978-3-540-69261-
4.

39. Knight, Will: "IBM creates world's most powerful computer Archived 1 August 2019
at the Wayback Machine", [Link] news service, June 2007

40. N. R. Agida; et al. (2005). "Blue Gene/L Torus Interconnection Network | IBM Journal
of Research and Development" (PDF). Torus Interconnection Network. p. 265.
Archived from the original (PDF) on 15 August 2011.

41. Niu, Yanwei; Hu, Ziang; Barner, Kenneth; Gao, Guang R. (2005). "Performance
Modelling and Optimization of Memory Access on Cellular Computer Architecture
Cyclops64" (PDF). Network and Parallel Computing. Lecture Notes in Computer
Science. Vol. 3779. pp. 132–143. doi:10.1007/11577188_18. ISBN 978-3-540-29810-
6. Archived (PDF) from the original on 9 October 2022.

42. Analysis and performance results of computing betweenness centrality on IBM

Cyclops64 by Guangming Tan, Vugranam C. Sreedhar and Guang R. Gao The Journal
of Supercomputing Volume 56, Number 1, 1–24 September 2011

43. Prickett, Timothy (31 May 2010). "Top 500 supers – The Dawning of the GPUs".
[Link]. Archived from the original on 7 July 2017. Retrieved 10
August 2017.
44. Hans Hacker; Carsten Trinitis; Josef Weidendorfer; Matthias Brehm
(2010). "Considering GPGPU for HPC Centers: Is It Worth the Effort?". In Rainer Keller;
David Kramer; Jan-Philipp Weiss (eds.). Facing the Multicore-Challenge: Aspects of
New Paradigms and Technologies in Parallel Computing. Springer Science & Business
Media. pp. 118–121. ISBN 978-3-642-16232-9.

45. Damon Poeter (11 October 2011). "Cray's Titan Supercomputer for ORNL Could Be
World's Fastest". [Link]. Archived from the original on 5 December 2012.
Retrieved 15 September 2017.

46. Feldman, Michael (11 October 2011). "GPUs Will Morph ORNL's Jaguar into 20-
Petaflop Titan". [Link]. Archived from the original on 27 July 2012.
Retrieved 9 February 2012.

47. Timothy Prickett Morgan (11 October 2011). "Oak Ridge changes Jaguar's spots
from CPUs to GPUs". [Link]. Archived from the original on 15 October
2012. Retrieved 10 August 2017.

48. "The NETL SuperComputer" Archived 4 September 2015 at the Wayback Machine.
page 2.

49. Condon, J.H. and [Link], "Belle Chess Hardware Archived 1 August 2019 at
the Wayback Machine", In Advances in Computer Chess 3 ([Link]),
Pergamon Press, 1982.

50. Hsu, Feng-hsiung (2002). Behind Deep Blue: Building the Computer that Defeated
the World Chess Champion. Princeton University Press. ISBN 978-0-691-09065-8.

51. C. Donninger, U. Lorenz. The Chess Monster Hydra. Archived 3 April 2021 at
the Wayback Machine Proc. of 14th International Conference on Field-Programmable
Logic and Applications (FPL), 2004, Antwerp – Belgium, LNCS 3203, pp. 927 – 932

52. J Makino and M. Taiji, Scientific Simulations with Special Purpose Computers: The
GRAPE Systems, Wiley. 1998.

53. RIKEN press release, Completion of a one-petaFLOPS computer system for simulation
of molecular dynamics Archived 2 December 2012 at the Wayback Machine

54. Electronic Frontier Foundation (1998). Cracking DES – Secrets of Encryption

Research, Wiretap Politics & Chip Design. Oreilly & Associates Inc. ISBN 978-1-56592-
520-5.

55. Lohr, Steve (8 June 2018). "Move Over, China: U.S. Is Again Home to World's
Speediest Supercomputer". New York Times. Archived from the original on 8 June
2018. Retrieved 19 July 2018.
56. "Green500 List - November 2018". TOP500. Archived from the original on 13
November 2018. Retrieved 19 July 2018.

57. Xue-June Yang; Xiang-Ke Liao; et al. (2011). "The TianHe-1A Supercomputer: Its
Hardware and Software". Journal of Computer Science and Technology. 26 (3): 344–
351. doi:10.1007/s02011-011-1137-8. S2CID 1389468.

58. The Supermen: Story of Seymour Cray and the Technical Wizards Behind the
Supercomputer by Charles J. Murray 1997, ISBN 0-471-04885-2, pages 133–135

59. Parallel Computational Fluid Dyynamics; Recent Advances and Future

Directions edited by Rupak Biswas 2010 ISBN 1-60595-022-X page 401

60. Supercomputing Research Advances by Yongge Huáng 2008, ISBN 1-60456-186-6,

pages 313–314

61. Parallel computing for real-time signal processing and control by M. O. Tokhi,
Mohammad Alamgir Hossain 2003, ISBN 978-1-85233-599-1, pages 201–202

62. Computational science – ICCS 2005: 5th international conference edited by Vaidy S.
Sunderam 2005, ISBN 3-540-26043-9, pages 60–67

63. "NVIDIA Tesla GPUs Power World's Fastest Supercomputer" (Press release). Nvidia.
29 October 2010. Archived from the original on 2 March 2014. Retrieved 21
February 2011.

64. Balandin, Alexander A. (October 2009). "Better Computing Through CPU

Cooling". IEEE.

65. "The Green 500". [Link]. Archived from the original on 26 August 2016.
Retrieved 14 August 2011.

66. "Green 500 list ranks supercomputers". iTnews Australia. Archived from the
original on 22 October 2008.

67. Wu-chun Feng (2003). "Making a Case for Efficient Supercomputing | ACM Queue
Magazine, Volume 1 Issue 7, 10 January 2003 doi 10.1145/957717.957772". ACM
Queue. 1 (7): 54. doi:10.1145/957717.957772. S2CID 11283177.

68. "IBM uncloaks 20 petaflops BlueGene/Q super". The Register. 22 November

2010. Archived from the original on 25 November 2010. Retrieved 25
November 2010.

69. Prickett, Timothy (15 July 2011). "The Register: IBM 'Blue Waters' super node washes
ashore in August". [Link]. Archived from the original on 19 July 2012.
Retrieved 9 June 2012.

70. "IBM Hot Water-Cooled Supercomputer Goes Live at ETH Zurich". IBM News room. 2
July 2010. Archived from the original on 10 January 2011. Retrieved 16 March 2020.
71. Martin LaMonica (10 May 2010). "CNet 10 May 2010". [Link]. Archived
from the original on 1 November 2013. Retrieved 9 June 2012.

72. "Government unveils world's fastest computer". CNN. Archived from the original on
10 June 2008. performing 376 million calculations for every watt of electricity used.

73. "IBM Roadrunner Takes the Gold in the Petaflop Race". Archived from the original
on 17 December 2008. Retrieved 16 March 2020.

74. "IBM Research A Clear Winner in Green 500". Data Center Knowledge | News and
analysis for the data center industry. 18 November 2010. Archived from the original
on 16 August 2011. Retrieved 14 August 2011.

75. "Green 500 list". [Link]. Archived from the original on 3 July 2011.
Retrieved 16 March 2020.

76. Saed G. Younis. "Asymptotically Zero Energy Computing Using Split-Level Charge
Recovery Logic" Archived 3 April 2021 at the Wayback Machine. 1994. page 14.

77. "Hot Topic – the Problem of Cooling Supercomputers" Archived 18 January 2015 at
the Wayback Machine.

78. Anand Lal Shimpi. "Inside the Titan Supercomputer: 299K AMD x86 Cores and 18.6K
NVIDIA GPUs". 2012.

79. Curtis Storlie; Joe Sexton; Scott Pakin; Michael Lang; Brian Reich; William
Rust. "Modeling and Predicting Power Consumption of High-Performance Computing
Jobs" Archived 17 July 2020 at the Wayback Machine. 2014.

80. Encyclopedia of Parallel Computing by David Padua 2011 ISBN 0-387-09765-1 pages
426–429

81. Knowing machines: essays on technical change by Donald MacKenzie 1998 ISBN 0-
262-63188-1 page 149-151

82. Euro-Par 2004 Parallel Processing: 10th International Euro-Par Conference 2004, by
Marco Danelutto, Marco Vanneschi and Domenico Laforenza, ISBN 3-540-22924-8,
page 835

83. Euro-Par 2006 Parallel Processing: 12th International Euro-Par Conference, 2006, by
Wolfgang E. Nagel, Wolfgang V. Walter and Wolfgang Lehner ISBN 3-540-37783-
2 page

84. An Evaluation of the Oak Ridge National Laboratory Cray XT3 by Sadaf R. Alam
etal International Journal of High Performance Computing Applications February
2008 vol. 22 no. 1 52–80
85. Open Job Management Architecture for the Blue Gene/L Supercomputer by Yariv
Aridor et al. in Job scheduling strategies for parallel processing by Dror G. Feitelson
2005 ISBN 978-3-540-31024-2 pages 95–101

86. "Top500 OS chart". [Link]. Archived from the original on 5 March 2012.
Retrieved 31 October 2010.

87. "Wide-angle view of the ALMA correlator". ESO Press Release. Archived from the
original on 20 January 2019. Retrieved 13 February 2013.

88. Nielsen, Frank (2016). Introduction to HPC with MPI for Data Science. Springer.
pp. 185–221. ISBN 978-3-319-21903-5.

89. Rahat, Nazmul. "Chapter 03 Software and System Management". Archived from the
original on 15 August 2021. Retrieved 23 November 2020.

90. Pande lab. "Client Statistics by OS". Folding@home. Stanford University.

Retrieved 10 April 2020.

91. "BOINC Combined". BOINCstats. BOINC. Archived from the original on 19

September 2010. Retrieved 30 October 2016Note this link will give current statistics,
not those on the date last accessed.

92. "Internet PrimeNet Server Distributed Computing Technology for the Great Internet
Mersenne Prime Search". GIMPS. Archived from the original on 25 May 2019.
Retrieved 6 June 2011.

93. Kravtsov, Valentin; Carmeli, David; Dubitzky, Werner; Orda, Ariel; Schuster, Assaf;
Yoshpa, Benny. "Quasi-opportunistic supercomputing in grids, hot topic paper
(2007)". IEEE International Symposium on High Performance Distributed Computing.
IEEE. CiteSeerX [Link].8993. Archived from the original on 28 June 2013.
Retrieved 4 August 2011.

94. Jamalian, S.; Rajaei, H. (1 March 2015). "ASETS: A SDN Empowered Task Scheduling
System for HPCaaS on the Cloud". 2015 IEEE International Conference on Cloud
Engineering. pp. 329–334. doi:10.1109/IC2E.2015.56. ISBN 978-1-4799-8218-
9. S2CID 10974077. Archived from the original on 17 July 2020. Retrieved 4
July 2019.

95. Jamalian, S.; Rajaei, H. (1 June 2015). "Data-Intensive HPC Tasks Scheduling with
SDN to Enable HPC-as-a-Service". 2015 IEEE 8th International Conference on Cloud
Computing. pp. 596–603. doi:10.1109/CLOUD.2015.85. ISBN 978-1-4673-7287-
9. S2CID 10141367. Archived from the original on 17 July 2020. Retrieved 4
July 2019.

96. Gupta, A.; Milojicic, D. (1 October 2011). "Evaluation of HPC Applications on

Cloud". 2011 Sixth Open Cirrus Summit. pp. 22–
 26. CiteSeerX [Link].3936. doi:10.1109/OCS.2011.10. ISBN 978-0-7695-4650-6.
S2CID 9405724.

97. Kim, H.; el-Khamra, Y.; Jha, S.; Parashar, M. (1 December 2009). "An Autonomic
Approach to Integrated HPC Grid and Cloud Usage". 2009 Fifth IEEE International
Conference on e-Science. pp. 366–373. CiteSeerX [Link].7000. doi:10.1109/e-
Science.2009.58. ISBN 978-1-4244-5340-5. S2CID 11502126.

98. Eadline, Douglas. "Moving HPC to the Cloud". Admin Magazine. Archived from the
original on 30 March 2019. Retrieved 30 March 2019.

99. Niccolai, James (11 August 2009). "Penguin Puts High-performance Computing in
the Cloud". PCWorld. IDG Consumer & SMB. Archived from the original on 19 August
2016. Retrieved 6 June 2016.

100. The Potential Impact of High-End Capability Computing on Four Illustrative

Fields of Science and Engineering by Committee on the Potential Impact of High-End
Computing on Illustrative Fields of Science and Engineering and National Research
Council (28 October 2008) ISBN 0-309-12485-9 page 9

101. Xingfu Wu (1999). Performance Evaluation, Prediction and Visualization of

Parallel Systems. Springer Science & Business Media. pp. 114–117. ISBN 978-0-7923-
8462-5.

102. Brehm, M. and Bruhwiler, D. L. (2015) 'Performance Characteristics of the

Plasma Wakefield Acceleration Driven by Proton Bunches'. Journal of Physics:
Conference Series

103. Dongarra, Jack J.; Luszczek, Piotr; Petitet, Antoine (2003), "The LINPACK
Benchmark: past, present and future" (PDF), Concurrency and Computation: Practice
and Experience, 15 (9): 803–
820, doi:10.1002/cpe.728, S2CID 1900724, archived (PDF) from the original on 20
January 2019, retrieved 9 February 2012

104. "Understanding measures of supercomputer performance and storage

system capacity". Indiana University. Archived from the original on 4 December
2017. Retrieved 3 December 2017.

105. "Frequently Asked Questions". [Link]. Archived from the original on 3

April 2021. Retrieved 3 December 2017.

106. "Top500 lists". [Link]. Archived from the original on 1 August 2024.
Retrieved 3 August 2024.

107. "Lenovo Attains Status as Largest Global Provider of TOP500

Supercomputers". Business Wire. 25 June 2018. Archived from the original on 28
June 2018. Retrieved 27 June 2018.
108. "November 2024 | TOP500". [Link]. Archived from the original on
14 August 2025. Retrieved 18 November 2024.

109. Turisini, Matteo; Cestari, Mirko; Amati, Giorgio (15 January

2024). "LEONARDO: A Pan-European Pre-Exascale Supercomputer for HPC and AI
applications". Journal of Large-scale Research Facilities
JLSRF. 9 (1). doi:10.17815/jlsrf-8-186. ISSN 2364-091X. Archived from the original
on 28 February 2025. Retrieved 28 February 2025.

110. "TOP500 DESCRIPTION". [Link]. Archived from the original on 23

June 2020. Retrieved 23 June 2020.

111. "FREQUENTLY ASKED QUESTIONS". [Link]. Archived from the

original on 3 April 2021. Retrieved 23 June 2020.

112. Kaku, Michio. Physics of the Future (New York: Doubleday, 2011), 65.

113. "Faster Supercomputers Aiding Weather Forecasts".

[Link]. 28 October 2010. Archived from the original on 5
September 2005. Retrieved 8 July 2011.

114. "Supercomputers". U.S. Department of Energy. Archived from the original on

7 March 2017. Retrieved 7 March 2017.

115. "IBM Drops 'Blue Waters' Supercomputer Project". International Business

Times. 9 August 2011. Retrieved 14 December 2018. – via EBSCO (subscription
required)

116. "Supercomputer Simulations Help Advance Electrochemical Reaction

Research". [Link]. Archived from the original on 14 May 2020.
Retrieved 12 May 2020.

117. Saltmarsh, Abigail (16 April 2020). "IBM's Summit—The Supercomputer

Fighting Coronavirus". MedicalExpo e-Magazine. Archived from the original on 8
May 2020. Retrieved 12 May 2020.

118. "OSTP Funding Supercomputer Research to Combat COVID-19 –

MeriTalk". Archived from the original on 6 June 2020. Retrieved 12 May 2020.

119. "EU $1.2 supercomputer project to several 10-100 PetaFLOP computers by

2020 and exaFLOP by 2022 | [Link]". [Link]. 4 February
2018. Archived from the original on 17 June 2018. Retrieved 21 May 2018.

120. DeBenedictis, Erik P. (2004). "The Path To Extreme

Computing" (PDF). Zettaflops. Sandia National Laboratories. Archived from the
original (PDF) on 3 August 2007. Retrieved 9 September 2020.
121. Cohen, Reuven (28 November 2013). "Global Bitcoin Computing Power Now
256 Times Faster Than Top 500 Supercomputers, Combined!". Forbes. Archived from
the original on 8 June 2017. Retrieved 1 December 2017.

122. DeBenedictis, Erik P. (2005). "Reversible logic for

supercomputing". Proceedings of the 2nd conference on Computing frontiers. ACM
Press. pp. 391–402. doi:10.1145/1062261.1062325. ISBN 978-1-59593-019-
4. Archived from the original on 3 April 2021. Retrieved 20 December 2008.

123. "IDF: Intel says Moore's Law holds until 2029". Heise Online. 4 April 2008.
Archived from the original on 8 December 2013.

124. Solem, J. C. (1985). "MECA: A multiprocessor concept specialized to Monte

Carlo". Monte-Carlo Methods and Applications in Neutronics, Photonics and
Statistical Physics. Lecture Notes in Physics. Vol. 240. Proceedings of the Joint los
Alamos National Laboratory – Commissariat à l'Energie Atomique Meeting Held at
Cadarache Castle, Provence, France 22–26 April 1985; Monte-Carlo Methods and
Applications in Neutronics, Photonics and Statistical Physics, Alcouffe, R.; Dautray, R.;
Forster, A.; Forster, G.; Mercier, B.; Eds. (Springer Verlag, Berlin). pp. 184–
195. Bibcode:1985LNP...240..184S. doi:10.1007/BFb0049047. ISBN 978-3-540-
16070-0. OSTI 5689714. Archived from the original on 17 July 2020. Retrieved 4
July 2019.

125. Yiannis Cotronis; Anthony Danalis; Dimitris Nikolopoulos; Jack Dongarra

(2011). Recent Advances in the Message Passing Interface: 18th European MPI Users'
Group Meeting, EuroMPI 2011, Santorini, Greece, September 18-21, 2011.
Proceedings. Springer Science & Business Media. ISBN 9783642244483.

126. James H. Laros III; Kevin Pedretti; Suzanne M. Kelly; Wei Shu; Kurt Ferreira;
John Van Dyke; Courtenay Vaughan (2012). Energy-Efficient High Performance
Computing: Measurement and Tuning. Springer Science & Business Media.
p. 1. ISBN 9781447144922.

127. James H. Laros III; Kevin Pedretti; Suzanne M. Kelly; Wei Shu; Kurt Ferreira;
John Van Dyke; Courtenay Vaughan (2012). Energy-Efficient High Performance
Computing: Measurement and Tuning. Springer Science & Business Media.
p. 2. ISBN 9781447144922.

128. James H. Laros III; Kevin Pedretti; Suzanne M. Kelly; Wei Shu; Kurt Ferreira;
John Van Dyke; Courtenay Vaughan (2012). Energy-Efficient High Performance
Computing: Measurement and Tuning. Springer Science & Business Media.
p. 3. ISBN 9781447144922.

129. "Green Supercomputer Crunches Big Data in Iceland". [Link]. 21

May 2015. Archived from the original on 20 May 2015. Retrieved 18 May 2015.
 External links

Wikimedia Commons has media related to Supercomputers.

 McDonnell, Marshall T. (2013). "Supercomputer Design: An Initial Effort to Capture

the Environmental, Economic, and Societal Impacts". Chemical and Biomolecular
Engineering Publications and Other Works.

 v

 t

 e

Parallel computing

 


 





 

 

 


 

 

 


 

 


 





 v

 t

 e

Computer sizes and classes


 

 

 


 





 


 

 






 









 v

 t

 e

Computer science


 






 

 



 




 





 

Portals:

 Electronics

 Illinois

 Linux

 History of science

 Spaceflight

 Computer programming

 United States

Authority control databases

 


 

Categories:

 Supercomputers

 American inventions

 Cluster computing

 Concurrent computing

 Distributed computing architecture

 Parallel computing

 This page was last edited on 30 May 2026, at 03:30 (UTC).

 Text is available under the Creative Commons Attribution-ShareAlike 4.0 License;

additional terms may apply. By using this site, you agree to the Terms of
Use and Privacy Policy. Wikipedia® is a registered trademark of the Wikimedia
Foundation, Inc., a non-profit organization.