supercomputers (1).docx

8/12/2019 supercomputers (1).docx

1/35

An assignment report on Supercomputers Information Technology for Business

Department of Business and Industrial Management Page 1

What is a Supercomputer?

A supercomputer is a computer at the frontline of contemporary processing capacity

particularly speeds of calculation. A large computer or collection of computers that act as onelarge computer capable of processing enormous amounts of data. Supercomputers are used

for very complex jobs such as nuclear research or collecting and calculating weather patterns.

Below is an example picture of a super computer at the William R. Wiley Environmental

Molecular Sciences Laboratory, the Linux-based supercomputer is composed of nearly 2,000

processors. Courtesy: Pacific Northwest National Laboratory. Supercomputers are the

bodybuilders of the computer world. They boast tens of thousands of times the computing

power of a desktop and cost tens of millions of dollars. They fill enormous rooms, which are

chilled to prevent their thousands of microprocessor cores from overheating. And they

perform trillions, or even thousands of trillions, of calculations per second.

All of that power means supercomputers are perfect for tacklingbig scientific problems,from

uncovering the origins of the universe to delving into the patterns of protein folding that

make life possible. Here are some of the most intriguing questions being tackled by

supercomputers today.

A supercomputer is a computer that performs at or near the currently highest operational rate

for computers. A supercomputer is typically used for scientific and engineering applications

that must handle very large databases or do a great amount of computation (or both).

At any given time, there are usually a few well-publicized supercomputers that operate at

extremely high speeds. The term is also sometimes applied to far slower (but still

impressively fast) computers. Most supercomputers are really multiple computers that

performparallel processing. In general, there are two parallel processing approaches:symmetric multiprocessing (SMP)and massively parallel processing (MPP).

IBM'sRoadrunner is the fastest supercomputer in the world, twice as fast asBlue Gene and

six times as fast as any of the other current supercomputers. At the lower end of

supercomputing, a new trend called clustering, takes more of a build-it-yourself approach to

supercomputing. TheBeowulf Project offers guidance on how to put together a number of

off-the-shelf personal computer processors, usingLinux operating systems, and
http://www.livescience.com/strangenews/090507-top10-greatest-mysteries.htmlhttp://searchdatacenter.techtarget.com/definition/parallel-processinghttp://searchdatacenter.techtarget.com/definition/SMPhttp://whatis.techtarget.com/definition/MPP-massively-parallel-processinghttp://searchdatacenter.techtarget.com/definition/IBM-Roadrunnerhttp://searchdatacenter.techtarget.com/definition/Blue-Genehttp://searchenterpriselinux.techtarget.com/definition/Beowulfhttp://searchenterpriselinux.techtarget.com/definition/Linuxhttp://searchenterpriselinux.techtarget.com/definition/Linuxhttp://searchenterpriselinux.techtarget.com/definition/Beowulfhttp://searchdatacenter.techtarget.com/definition/Blue-Genehttp://searchdatacenter.techtarget.com/definition/IBM-Roadrunnerhttp://whatis.techtarget.com/definition/MPP-massively-parallel-processinghttp://searchdatacenter.techtarget.com/definition/SMPhttp://searchdatacenter.techtarget.com/definition/parallel-processinghttp://www.livescience.com/strangenews/090507-top10-greatest-mysteries.html


2/35



interconnecting the processors withFast Ethernet.Applications must be written to manage

the parallel processing.

Perhaps the best-known builder of supercomputers has been Cray Research, now a part of

Silicon Graphics. In September 2008, Cray and Microsoft launched CX1, a $25,000 personal

supercomputer aimed markets such as aerospace, automotive, academic, financial services

and life sciences. CX1 runs Windows HPC (High Performance Computing) Server 2008.

In the United States, somesupercomputer centres are interconnected on an Internet

backbone known asvBNS or NSFNet. This network is the foundation for an evolving

network infrastructure known as the National Technology Grid.Internet2 is a university-led

project that is part of this initiative.

Supercomputers were introduced in the 1960s, made initially and, for decades, primarily by

Seymour Cray at Control Data Corporation (CDC), Cray Research and subsequent companies

bearing his name or monogram. While the supercomputers of the 1970s used only a few

processors, in the 1990s machines with thousands of processors began to appear and, by the

end of the 20th century, massively parallel supercomputers with tens of thousands of "off-

the-shelf" processors were the norm. As of November 2013, China's Tianhe-2 supercomputer

is the fastest in the world at 33.86 petaFLOPS.

Systems with massive numbers of processors generally take one of two paths: In one

approach (e.g., in distributed computing), a large number of discrete computers (e.g., laptops)

distributed across a network (e.g., the internet) devote some or all of their time to solving a

common problem; each individual computer (client) receives and completes many small

tasks, reporting the results to a central server which integrates the task results from all the

clients into the overall solution. In another approach, a large number of dedicated processorsare placed in close proximity to each other (e.g. in a computer cluster); this saves

considerable time moving data around and makes it possible for the processors to work

together (rather than on separate tasks), for example in mesh and hypercube architectures.

The use of multi-core processors combined with centralization is an emerging trend; one can

think of this as a small cluster (the multicore processor in a smartphone, tablet, laptop, etc.)

that both depends upon and contributes to the cloud.
http://searchnetworking.techtarget.com/definition/Fast-Ethernethttp://whatis.techtarget.com/definition/supercomputer-centerhttp://searchnetworking.techtarget.com/definition/vBNShttp://whatis.techtarget.com/definition/Internet2http://whatis.techtarget.com/definition/Internet2http://searchnetworking.techtarget.com/definition/vBNShttp://whatis.techtarget.com/definition/supercomputer-centerhttp://searchnetworking.techtarget.com/definition/Fast-Ethernet


3/35


4/35



particles and of the origin and nature of the universe. Supercomputers have become an

indispensable tool in weather forecasting: predictions are now based on numerical models. As

the cost of supercomputers declined, their use spread to the world ofonline gaming. In

particular, the 5th through 10th fastest Chinese supercomputers in 2007 were owned by a

company with online rights inChina to theelectronic gameWorld of War craft, which

sometimes had more than a million people playing together in the same gaming world.

Characteristics which make super computers different

from ordinary computer?

Super computers has a big differences from ordinary computers like high speed and it is the

most high speed performance as of today and also capable of manipulating massive amount

of data in a short time.

They are much more faster

Generally used for scientific calculations

Use much more power

Give off more heat

Much more expensive

Usage

Supercomputers play an important role in the field ofcomputational science,and are used for

a wide range of computationally intensive tasks in various fields, includingquantum

mechanics,weather forecasting,climate research,oil and gas exploration,molecular

modeling (computing the structures and properties of chemical compounds,

biologicalmacromolecules, polymers, and crystals), and physical simulations (such as

simulations of the early moments of the universe, airplane and spacecraft aerodynamics, the

detonation ofnuclear weapons,andnuclear fusion). Throughout their history, they have been

essential in the field ofcryptanalysis.
http://www.britannica.com/EBchecked/topic/570533/subatomic-particlehttp://www.britannica.com/EBchecked/topic/1017758/online-gaminghttp://www.britannica.com/EBchecked/topic/111803/Chinahttp://www.britannica.com/EBchecked/topic/183800/electronic-gamehttp://www.britannica.com/EBchecked/topic/1195550/World-of-Warcraft-WoWhttp://en.wikipedia.org/wiki/Computational_sciencehttp://en.wikipedia.org/wiki/Quantum_mechanicshttp://en.wikipedia.org/wiki/Quantum_mechanicshttp://en.wikipedia.org/wiki/Weather_forecastinghttp://en.wikipedia.org/wiki/Climate_researchhttp://en.wikipedia.org/wiki/Oil_and_gas_explorationhttp://en.wikipedia.org/wiki/Computational_chemistryhttp://en.wikipedia.org/wiki/Computational_chemistryhttp://en.wikipedia.org/wiki/Macromoleculeshttp://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/Nuclear_fusionhttp://en.wikipedia.org/wiki/Cryptanalysishttp://en.wikipedia.org/wiki/Cryptanalysishttp://en.wikipedia.org/wiki/Nuclear_fusionhttp://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/Macromoleculeshttp://en.wikipedia.org/wiki/Computational_chemistryhttp://en.wikipedia.org/wiki/Computational_chemistryhttp://en.wikipedia.org/wiki/Oil_and_gas_explorationhttp://en.wikipedia.org/wiki/Climate_researchhttp://en.wikipedia.org/wiki/Weather_forecastinghttp://en.wikipedia.org/wiki/Quantum_mechanicshttp://en.wikipedia.org/wiki/Quantum_mechanicshttp://en.wikipedia.org/wiki/Computational_sciencehttp://www.britannica.com/EBchecked/topic/1195550/World-of-Warcraft-WoWhttp://www.britannica.com/EBchecked/topic/183800/electronic-gamehttp://www.britannica.com/EBchecked/topic/111803/Chinahttp://www.britannica.com/EBchecked/topic/1017758/online-gaminghttp://www.britannica.com/EBchecked/topic/570533/subatomic-particle


5/35



Hardware and Architecture

While the supercomputers of the 1970s used only a fewprocessors,in the 1990s, machines

with thousands of processors began to appear and by the end of the 20th century, massivelyparallel supercomputers with tens of thousands of "off-the-shelf" processors were the norm.

Supercomputers of the 21st century can use over 100,000 processors (some beinggraphic

units)connected by fast connections.

Systems with a massive number of processors generally take one of two paths: in one

approach, known asgrid computing,the processing power of a large number of computers in

distributed, diverse administrative domains, is opportunistically used whenever a computer is

available. In another approach, a large number of processors are used in close proximity toeach other, e.g. in acomputer cluster. In such a centralizedmassively parallel system the

speed and flexibility of the interconnect becomes very important and modern supercomputers

have used various approaches ranging from enhancedInfiniband systems to three-

dimensionaltorus interconnects.The use ofmulti-core processors combined with

centralization is an emerging direction, e.g. as in theCyclops64system.
http://en.wikipedia.org/wiki/Central_processing_unithttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/Grid_computinghttp://en.wikipedia.org/wiki/Computer_clusterhttp://en.wikipedia.org/wiki/Massively_parallelhttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/Torus_interconnecthttp://en.wikipedia.org/wiki/Multi-core_processorhttp://en.wikipedia.org/wiki/Cyclops64http://en.wikipedia.org/wiki/Cyclops64http://en.wikipedia.org/wiki/Multi-core_processorhttp://en.wikipedia.org/wiki/Torus_interconnecthttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/Massively_parallelhttp://en.wikipedia.org/wiki/Computer_clusterhttp://en.wikipedia.org/wiki/Grid_computinghttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/Central_processing_unit


6/35



Operating system

Since the end of the 20th century,supercomputer operating systems have undergone major

transformations, as sea changes have taken place insupercomputer architecture.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.Given that modernmassively parallel supercomputers typically separate

computations from other services by using multiple types ofnodes,they usually run different

operating systems on different nodes, e.g. using a small and efficient lightweight kernel such

asCNK orCNL on compute nodes, but a larger system such as aLinux-derivative on server

andI/O nodes.

While in a traditional multi-user computer systemjob scheduling is in effect

ataskingproblem 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 dealing with inevitable hardware failures

when tens of thousands of processors are present.

Although most modern supercomputers use theLinux operating system, each manufacturer

has made its own specific changes to the Linux-derivative they use, 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.

Software tools and message passing

The parallel architectures of supercomputers often dictate the use of special programming

techniques to exploit their speed. Software tools for distributed processing include

standardAPIs such asMPI andPVM,VTL, andopen source-based software solutions such

asBeowulf.In the most common scenario, environments such asPVM andMPI for loosely connected

clusters andOpenMP 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 asCUDA.Moreover, it is quite difficult to debug and test parallel

programs.Special techniques need to be used for testing and debugging such applications
http://en.wikipedia.org/wiki/Supercomputer_operating_systemshttp://en.wikipedia.org/wiki/Supercomputer_architecturehttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/Massively_parallelhttp://en.wikipedia.org/wiki/Locale_(computer_hardware)http://en.wikipedia.org/wiki/Lightweight_Kernel_Operating_Systemhttp://en.wikipedia.org/wiki/CNK_operating_systemhttp://en.wikipedia.org/wiki/Compute_Node_Linuxhttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/I/Ohttp://en.wikipedia.org/wiki/Job_schedulinghttp://en.wikipedia.org/wiki/Task_schedulinghttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/Application_programming_interfacehttp://en.wikipedia.org/wiki/Message_Passing_Interfacehttp://en.wikipedia.org/wiki/Parallel_Virtual_Machinehttp://en.wikipedia.org/wiki/Virtual_tape_libraryhttp://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Beowulf_(computing)http://en.wikipedia.org/wiki/Parallel_Virtual_Machinehttp://en.wikipedia.org/wiki/Message_Passing_Interfacehttp://en.wikipedia.org/wiki/OpenMPhttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/CUDAhttp://en.wikipedia.org/wiki/Testing_high-performance_computing_applicationshttp://en.wikipedia.org/wiki/Testing_high-performance_computing_applicationshttp://en.wikipedia.org/wiki/CUDAhttp://en.wikipedia.org/wiki/GPGPUhttp://en.wikipedia.org/wiki/OpenMPhttp://en.wikipedia.org/wiki/Message_Passing_Interfacehttp://en.wikipedia.org/wiki/Parallel_Virtual_Machinehttp://en.wikipedia.org/wiki/Beowulf_(computing)http://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Virtual_tape_libraryhttp://en.wikipedia.org/wiki/Parallel_Virtual_Machinehttp://en.wikipedia.org/wiki/Message_Passing_Interfacehttp://en.wikipedia.org/wiki/Application_programming_interfacehttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/Task_schedulinghttp://en.wikipedia.org/wiki/Job_schedulinghttp://en.wikipedia.org/wiki/I/Ohttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/Compute_Node_Linuxhttp://en.wikipedia.org/wiki/CNK_operating_systemhttp://en.wikipedia.org/wiki/Lightweight_Kernel_Operating_Systemhttp://en.wikipedia.org/wiki/Locale_(computer_hardware)http://en.wikipedia.org/wiki/Massively_parallelhttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/Supercomputer_architecturehttp://en.wikipedia.org/wiki/Supercomputer_operating_systems


7/35



Performance metrics

Top supercomputer speeds:logscalespeedover 60 years

In general, the speed of supercomputers is measured andbenchmarked in "FLOPS"(Floating

Point Operations Per Second), and not in terms ofMIPS,i.e. as "instructions per second", as

is the case with general purpose computers.[69]These measurements are commonly used with

anSI prefix such astera-, combined into the shorthand "TFLOPS" (1012FLOPS,

pronounced teraflops), orpeta-, combined into the shorthand "PFLOPS" (1015FLOPS,

pronounced petaflops.) "Petascale"supercomputers can process one quadrillion (1015) (1000

trillion) FLOPS.Exascale is computing performance in the exaflops range. An exaflop is one

quintillion (1018) FLOPS (one million teraflops).

Appl icat ions of sup ercomputersThe stages of supercomputer application may be summarized in the following table:

Decade Uses and computer involved

1970s Weather forecasting, aerodynamic research (Cray-1).

1980s Probabilistic analysis, radiation shielding modelling (CDC Cyber).

1990s Brute force code breaking (EFF DES cracker),
http://en.wikipedia.org/wiki/Logarithmic_scalehttp://en.wikipedia.org/wiki/Logarithmic_scalehttp://en.wikipedia.org/wiki/Benchmark_(computing)http://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Million_instructions_per_secondhttp://en.wikipedia.org/wiki/Supercomputer#cite_note-Xifu-69http://en.wikipedia.org/wiki/Supercomputer#cite_note-Xifu-69http://en.wikipedia.org/wiki/Supercomputer#cite_note-Xifu-69http://en.wikipedia.org/wiki/SI_prefixhttp://en.wikipedia.org/wiki/Tera-http://en.wikipedia.org/wiki/Peta-http://en.wikipedia.org/wiki/Petascalehttp://en.wikipedia.org/wiki/Exascale_computinghttp://en.wikipedia.org/wiki/Cray-1http://en.wikipedia.org/wiki/CDC_Cyberhttp://en.wikipedia.org/wiki/EFF_DES_crackerhttp://en.wikipedia.org/wiki/File:Supercomputing-rmax-graph.pnghttp://en.wikipedia.org/wiki/EFF_DES_crackerhttp://en.wikipedia.org/wiki/CDC_Cyberhttp://en.wikipedia.org/wiki/Cray-1http://en.wikipedia.org/wiki/Exascale_computinghttp://en.wikipedia.org/wiki/Petascalehttp://en.wikipedia.org/wiki/Peta-http://en.wikipedia.org/wiki/Tera-http://en.wikipedia.org/wiki/SI_prefixhttp://en.wikipedia.org/wiki/Supercomputer#cite_note-Xifu-69http://en.wikipedia.org/wiki/Million_instructions_per_secondhttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Benchmark_(computing)http://en.wikipedia.org/wiki/Logarithmic_scale


8/35



2000s3D nuclear test simulations as a substitute for legal conductNuclear Non-

Proliferation Treaty (ASCI Q).

2010s Molecular Dynamics Simulation (Tianhe-1A)

The IBMBlue Gene/P computer has been used to simulate a number of artificial neurons

equivalent to approximately one percent of a human cerebral cortex, containing 1.6 billion

neurons with approximately 9 trillion connections. The same research group also succeeded

in using a supercomputer to simulate a number of artificial neurons equivalent to the entiretyof a rat's brain.

Modern-day weather forecasting also relies on supercomputers. TheNational Oceanic and

Atmospheric Administration uses supercomputers to crunch hundreds of millions of

observations to help make weather forecasts more accurate.

In 2011, the challenges and difficulties in pushing the envelope in supercomputing were

underscored byIBM's abandonment of theBlue Waterspetascale project.
http://en.wikipedia.org/wiki/Nuclear_Non-Proliferation_Treatyhttp://en.wikipedia.org/wiki/Nuclear_Non-Proliferation_Treatyhttp://en.wikipedia.org/wiki/ASCI_Qhttp://en.wikipedia.org/wiki/Tianhe-1Ahttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/National_Oceanic_and_Atmospheric_Administrationhttp://en.wikipedia.org/wiki/National_Oceanic_and_Atmospheric_Administrationhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Blue_Watershttp://en.wikipedia.org/wiki/Blue_Watershttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/National_Oceanic_and_Atmospheric_Administrationhttp://en.wikipedia.org/wiki/National_Oceanic_and_Atmospheric_Administrationhttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/Tianhe-1Ahttp://en.wikipedia.org/wiki/ASCI_Qhttp://en.wikipedia.org/wiki/Nuclear_Non-Proliferation_Treatyhttp://en.wikipedia.org/wiki/Nuclear_Non-Proliferation_Treaty


9/35



Supercomputers Operating System

Early sys tems

The firstCray-1(sample shown with internals) was delivered to the customer without an operating system. [8]

TheCDC 6600,generally considered the first supercomputer in the world, ran theChippewa

Operating System, which was then deployed on various otherCDC 6000

series computers. The Chippewa was a rather simple job control oriented system derived

from the earlierCDC 3000,but it influenced the laterKRONOS andSCOPE systems.

The firstCray 1 was delivered to the Los Alamos Lab without an operating system, or any

other software. Los Alamos developed not only the application software for it, but also the

operating system. The main timesharing system for the Cray 1, the Cray Time Sharing

System (CTSS), was then developed at the Livermore Labs as a direct descendant of

theLivermore Time Sharing System (LTSS) for the CDC 6600 operating system from twenty

years earlier.

The rising software costs in developing a supercomputer soon became dominant, as

evidenced by the fact that in the 1980s the cost for software development at Cray came to

equal what they spent on hardware. That trend was partly responsible for a move away from

the in-houseCray Operating System toUNICOS system based onUnix. In 1985, theCray

2 was the first system to ship with the UNICOS operating system.

Around the same time, theEOS operating system was developed byETA Systems for use in

theirETA10 supercomputers. Written inCybil, a Pascal-like language fromControl Data

Corporation,EOS highlighted the stability problems in developing stable operating systems

for supercomputers and eventually a Unix-like system was offered on the same machine. The

lessons learned from the development of ETA system software included the high level of risk
http://en.wikipedia.org/wiki/Cray-1http://en.wikipedia.org/wiki/Cray-1http://en.wikipedia.org/wiki/Cray-1http://en.wikipedia.org/wiki/Supercomputer_operating_systems#cite_note-8http://en.wikipedia.org/wiki/Supercomputer_operating_systems#cite_note-8http://en.wikipedia.org/wiki/Supercomputer_operating_systems#cite_note-8http://en.wikipedia.org/wiki/CDC_6600http://en.wikipedia.org/wiki/Chippewa_Operating_Systemhttp://en.wikipedia.org/wiki/Chippewa_Operating_Systemhttp://en.wikipedia.org/wiki/CDC_6000_serieshttp://en.wikipedia.org/wiki/CDC_6000_serieshttp://en.wikipedia.org/wiki/Job_controlhttp://en.wikipedia.org/wiki/CDC_3000http://en.wikipedia.org/wiki/CDC_KRONOShttp://en.wikipedia.org/wiki/CDC_SCOPE_(software)http://en.wikipedia.org/wiki/Cray_1http://en.wikipedia.org/wiki/Cray_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Cray_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Livermore_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Cray_Operating_Systemhttp://en.wikipedia.org/wiki/UNICOShttp://en.wikipedia.org/wiki/Unixhttp://en.wikipedia.org/wiki/Cray_2http://en.wikipedia.org/wiki/Cray_2http://en.wikipedia.org/wiki/EOS_(operating_system)http://en.wikipedia.org/wiki/ETA_Systemshttp://en.wikipedia.org/wiki/ETA10http://en.wikipedia.org/wiki/Cybil_(computer_language)http://en.wikipedia.org/wiki/Control_Data_Corporationhttp://en.wikipedia.org/wiki/Control_Data_Corporationhttp://en.wikipedia.org/wiki/File:Cray_1_IMG_9126.jpghttp://en.wikipedia.org/wiki/Control_Data_Corporationhttp://en.wikipedia.org/wiki/Control_Data_Corporationhttp://en.wikipedia.org/wiki/Cybil_(computer_language)http://en.wikipedia.org/wiki/ETA10http://en.wikipedia.org/wiki/ETA_Systemshttp://en.wikipedia.org/wiki/EOS_(operating_system)http://en.wikipedia.org/wiki/Cray_2http://en.wikipedia.org/wiki/Cray_2http://en.wikipedia.org/wiki/Unixhttp://en.wikipedia.org/wiki/UNICOShttp://en.wikipedia.org/wiki/Cray_Operating_Systemhttp://en.wikipedia.org/wiki/Livermore_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Cray_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Cray_Time_Sharing_Systemhttp://en.wikipedia.org/wiki/Cray_1http://en.wikipedia.org/wiki/CDC_SCOPE_(software)http://en.wikipedia.org/wiki/CDC_KRONOShttp://en.wikipedia.org/wiki/CDC_3000http://en.wikipedia.org/wiki/Job_controlhttp://en.wikipedia.org/wiki/CDC_6000_serieshttp://en.wikipedia.org/wiki/CDC_6000_serieshttp://en.wikipedia.org/wiki/Chippewa_Operating_Systemhttp://en.wikipedia.org/wiki/Chippewa_Operating_Systemhttp://en.wikipedia.org/wiki/CDC_6600http://en.wikipedia.org/wiki/Supercomputer_operating_systems#cite_note-8http://en.wikipedia.org/wiki/Cray-1


10/35



associated with the development of a new supercomputer operating system, and the

advantages of using Unix with its large existing base of system software libraries.

By the middle 1990s, despite the existing investment in older operating systems, the trend

was towards the use of Unix-based systems, which also facilitated the use ofinteractive userinterfacesforscientific computing across multiple platforms. The move towards a 'commodity

OS' was not without its opponents who cited the fast pace and focus of Linux development as

a major obstacle towards adoption. As one author wrote "Linux will likely catch up, but we

have large-scale systems now". Nevertheless, that trend continued to build momentum and by

2005, virtually all supercomputers used some UNIX like OS. These variants of UNIX

includedAIX from IBM, the open sourceLinux system, and other adaptations such

asUNICOS from Cray. By the end of the 20th century, Linux was estimated to command thehighest share of the supercomputing pie.

Modern approaches

TheBlue Gene/P supercomputer atArgonne National Lab

The IBMBlue Gene supercomputer uses theCNK operating system on the compute nodes,

but uses a modifiedLinux-based kernel calledINK (for I/O Node Kernel) on the I/O

nodes. CNK is alightweight kernel that runs on each node and supports a single application

running for a single user on that node. For the sake of efficient operation, the design of CNK

was kept simple and minimal, with physical memory being statically mapped and the CNK

neither needing nor providing scheduling or context switching. CNK does not even

implementfile I/O on the compute node, but delegates that to dedicated I/O nodes. However,

given that on the Blue Gene multiple compute nodes share a single I/O node, the I/O node

operating system does require multi-tasking, hence the selection of the Linux-based operating

system.
http://en.wikipedia.org/wiki/GUIhttp://en.wikipedia.org/wiki/GUIhttp://en.wikipedia.org/wiki/Scientific_computinghttp://en.wikipedia.org/wiki/AIXhttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/UNICOShttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/CNK_operating_systemhttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/INK_(operating_system)http://en.wikipedia.org/wiki/Lightweight_Kernel_Operating_Systemhttp://en.wikipedia.org/wiki/Input/outputhttp://en.wikipedia.org/wiki/File:IBM_Blue_Gene_P_supercomputer.jpghttp://en.wikipedia.org/wiki/Input/outputhttp://en.wikipedia.org/wiki/Lightweight_Kernel_Operating_Systemhttp://en.wikipedia.org/wiki/INK_(operating_system)http://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/CNK_operating_systemhttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/Blue_Genehttp://en.wikipedia.org/wiki/UNICOShttp://en.wikipedia.org/wiki/Linuxhttp://en.wikipedia.org/wiki/AIXhttp://en.wikipedia.org/wiki/Scientific_computinghttp://en.wikipedia.org/wiki/GUIhttp://en.wikipedia.org/wiki/GUI


11/35



While in traditional multi-user computer systems and early supercomputers,job

scheduling was in effect aschedulingproblem 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. The need to tune task scheduling and tune the

operating system in different configurations of a supercomputer is essential. A typical parallel

job scheduler has amaster scheduler which instructs a number of slave schedulers to launch,

monitor and controlparallel jobs,and periodically receives reports from them about the status

of job progress.

Some, but not all supercomputer schedulers attempt to maintain locality of job execution.

ThePBS Pro scheduler used on theCray XT3 andCray XT4 systems does not attempt to

optimize locality on its three dimensionaltorus interconnect, but simply uses the firstavailable processor. On the other hand, IBM's scheduler on the Blue Gene supercomputers

aims to exploit locality and minimize network contention by assigning tasks from the same

application to one or more midplanes of an 8x8x8 node group. TheSLURM scheduler uses a

best fit algorithm, and performsHilbert curve scheduling in order to optimize locality of task

assignments. A number of modern supercomputers such as theTianhe-I use the SLURM job

scheduler which arbitrates contention for resources across the system. SLURM isopen

source,Linux-based, is quite scalable, and can manage thousands of nodes in a computer

cluster with a sustained throughput of over 100,000 jobs per hour.
http://en.wikipedia.org/wiki/Job_schedulinghttp://en.wikipedia.org/wiki/Job_schedulinghttp://en.wikipedia.org/wiki/Task_schedulinghttp://en.wikipedia.org/wiki/Master/slave_(technology)http://en.wikipedia.org/wiki/Parallel_processinghttp://en.wikipedia.org/wiki/PBS_Prohttp://en.wikipedia.org/wiki/Cray_XT3http://en.wikipedia.org/wiki/Cray_XT4http://en.wikipedia.org/wiki/Torus_interconnecthttp://en.wikipedia.org/wiki/Simple_Linux_Utility_for_Resource_Managementhttp://en.wikipedia.org/wiki/Hilbert_curve_schedulinghttp://en.wikipedia.org/wiki/Tianhe-Ihttp://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Open_sourcehttp://en.wikipedia.org/wiki/Tianhe-Ihttp://en.wikipedia.org/wiki/Hilbert_curve_schedulinghttp://en.wikipedia.org/wiki/Simple_Linux_Utility_for_Resource_Managementhttp://en.wikipedia.org/wiki/Torus_interconnecthttp://en.wikipedia.org/wiki/Cray_XT4http://en.wikipedia.org/wiki/Cray_XT3http://en.wikipedia.org/wiki/PBS_Prohttp://en.wikipedia.org/wiki/Parallel_processinghttp://en.wikipedia.org/wiki/Master/slave_(technology)http://en.wikipedia.org/wiki/Task_schedulinghttp://en.wikipedia.org/wiki/Job_schedulinghttp://en.wikipedia.org/wiki/Job_scheduling


12/35



Applications of super computers

Recreating the Big Bang

It takes big computers to look into the biggest question of all: What is the origin of the

universe?

The "Big Bang," or the initial expansion of all energy and matter in the universe, happened

more than 13 billion years ago in trillion-degree Celsius temperatures, but supercomputer

simulations make it possible to observe what went on during the universe's birth. Researchers

at the Texas Advanced Computing Centre (TACC) at the University of Texas in Austin have

also used supercomputers to simulate the formation of the first galaxy, while scientists at

NASAs Ames Research Centre in Mountain View, Calif., have simulated the creation of

stars from cosmic dust and gas.

Supercomputer simulations also make it possible for physicists to answer questions about the

unseen universe of today. Invisible dark matter makes up about 25 percent of the universe,

anddark energy makes up more than 70 percent, but physicists know little about either.

Using powerful supercomputers like IBM's Roadrunner at Los Alamos National Laboratory,researchers can run models that require upward of a thousand trillion calculations per second,

allowing for the most realistic models of these cosmic mysteries yet.

Understanding earthquakes

Other supercomputer simulations hit closer to home. By modeling the three-dimensional

structure of the Earth, researchers can predict howearthquake waves will travel both locally

and globally. It's a problem that seemed intractable two decades ago, says Princeton
http://www.space.com/scienceastronomy/big-bang-universe-beginning-100319.htmlhttp://www.space.com/scienceastronomy/090427-mm-dark-energy.htmlhttp://www.livescience.com/environment/earthquake-world-threat-100302.htmlhttp://www.livescience.com/environment/earthquake-world-threat-100302.htmlhttp://www.space.com/scienceastronomy/090427-mm-dark-energy.htmlhttp://www.space.com/scienceastronomy/big-bang-universe-beginning-100319.html


13/35



geophysicist Jeroen Tromp. But by using supercomputers, scientists can solve very complex

equations that mirror real life.

"We can basically say, if this is your best model of what the earth looks like in a 3-D sense,

this is what the waves look like," Tromp said.

By comparing any remaining differences between simulations and real data, Tromp and his

team are perfecting their images of the earth's interior. The resulting techniques can be used

to map the subsurface for oil exploration or carbon sequestration, and can help researchers

understand the processes occurring deep in the Earth's mantle and core.

Folding Proteins

In 1999, IBM announced plans to build the fastest supercomputer the world had ever seen.

The first challenge for this technological marvel, dubbed "Blue Gene"?

Unravelling the mysteries of folding. Proteinsare made of long strands of amino acids folded

into complex three-dimensional shapes. Their function is driven by their form. When a

protein misfolds, there can be serious consequences, including disorders like cystic fibrosis,

Mad Cow disease and Alzheimer's disease. Finding out how proteins foldand how folding

can go wrongcould be the first step in curing these diseases.

Blue Gene isn't the only supercomputer to work on this problem, which requires massive

amounts of power to simulate mere microseconds of folding time. Using simulations,

researchers have uncovered the folding strategies of several proteins, including one found in

the lining of the mammalian gut. Meanwhile, the Blue Gene project has expanded. As of

November 2009, a Blue Gene system in Germany is ranked as the fourth-most powerful

supercomputer in the world, with a maximum processing speed of a thousand trillion

calculations per second.


14/35



Mapping the blood stream

Think you have a pretty good idea of how your blood flows? Think again. The total length of

all of the veins, arteries and capillaries in the human body is between 60,000 and 100,000

miles. To map blood flow through this complex system in real time, Brown University

professor of applied mathematics George Karniadakis works with multiple laboratories and

multiple computer clusters.

In a 2009 paper in the journal Philosophical Transactions of the Royal Society, Karniadakas

and his team describe the flow of blood through thebrain of a typical person compared with

blood flow in the brain of a person with hydrocephalus, a condition in which cranial fluid

builds up inside the skull. The results could help researchers better understand strokes,

traumatic brain injury and other vascular brain diseases, the authors write.

Modeling swine flu

Potential pandemics like the H1N1 swine flu require a fast response on two fronts: First,

researchers have to figure out how the virus is spreading. Second, they have to find drugs tostop it.

Supercomputers can help with both. During the recent H1N1 outbreak, researchers at

Virginia Polytechnic Institute and State University in Blacksburg, Va., used an advanced

model of disease spread called EpiSimdemics to predict the transmission of the flu. The

program, which is designed to model populations up to 300 million strong, was used by the

U.S. Department of Defense during the outbreak, according to a May 2009 report in IEEE

Spectrum magazine.
http://www.technewsdaily.com/361-new-implants-mold-to-brain-like-shrink-wrap.htmlhttp://www.technewsdaily.com/361-new-implants-mold-to-brain-like-shrink-wrap.html


15/35



Meanwhile, researchers at the University of Illinois at Urbana-Champaign and the University

of Utah were using supercomputers to peer into the virus itself. Using the Ranger

supercomputer at the TACC in Austin, Texas, the scientists unraveled the structure of swine

flu. They figured out how drugs would bind to the virus and simulated the mutations that

might lead to drug resistance. The results showed that the virus was not yet resistant, but

would be soon, according to a report by the TeraGrid computing resources center. Such

simulations can help doctors prescribe drugs that won't promote resistance.

Testing nuclear weapons

Since 1992, the United States has banned the testing ofnuclear weapons.But that doesn't

mean the nuclear arsenal is out of date.

The Stockpile Stewardship program uses non-nuclear lab tests and, yes, computer simulations

to ensure that the country's cache of nuclear weapons are functional and safe. In 2012, IBM

plans to unveil a new supercomputer, Sequoia, at Lawrence Livermore National Laboratory

in California. According to IBM, Sequoia will be a 20 petaflop machine, meaning it will be

capable of performing twenty thousand trillion calculations each second. Sequoia's primedirective is to create better simulations of nuclear explosions and to do away with real-world.
http://www.livescience.com/technology/090922-nuclear-weapons-science.htmlhttp://www.livescience.com/technology/090922-nuclear-weapons-science.html


16/35



Forecasting hurricanes

With Hurricane Ike bearing down on the Gulf Coast in 2008, forecasters turned to Ranger for

clues about the storm's path. This supercomputer, with its cowboy moniker and 579 trillion

calculations per second processing power, resides at the TACC in Austin, Texas. Using data

directly from National Oceanographic and Atmospheric Agency airplanes, Ranger calculated

likely paths for the storm. According to a TACC report, Ranger improved the five-day

hurricane forecast by 15 percent.

Simulations are also useful after a storm. When Hurricane Rita hit Texas in 2005, Los

Alamos National Laboratory in New Mexico lent manpower and computer power to model

vulnerable electrical lines and power stations, helping officials make decisions about

evacuation, power shutoff and repairs.

Predicting climate change

The challenge of predicting global climate is immense. There are hundreds of variables, from

the reflectivity of the earth's surface (high for icy spots, low for dark forests) to the vagaries

of ocean currents. Dealing with these variables requires supercomputing capabilities.Computer power is so coveted by climate scientists that the U.S. Department of Energy gives

out access to its most powerful machines as a prize.

The resulting simulations both map out the past and look into the future. Models of the

ancient past can be matched with fossil data to check for reliability, making future predictions

stronger. New variables, such as the effect of cloud cover on climate, can be explored. One

model, created in 2008 at Brookhaven National Laboratory in New York, mapped the aerosol

particles and turbulence of clouds to a resolution of 30 square feet. These maps will have to


17/35



become much more detailed before researchers truly understand how clouds affect climate

over time.

Building brains

So how do supercomputers stack up tohuman? Well, they're really good at computation: It

would take 120 billion people with 120 billion calculators 50 years to do what the Sequoia

supercomputer will be able to do in a day. But when it comes to the brain's ability to process

information in parallel by doing many calculations simultaneously, even supercomputers lag

behind. Dawn, a supercomputer at Lawrence Livermore National Laboratory, can simulate

the brain power of a catbut 100 to 1,000 times slower than a real cat brain.

Nonetheless, supercomputers are useful for modeling the nervous system. In 2006,

researchers at the colePolytechniqueFdrale de Lausanne in Switzerland successfully

simulated a 10,000-neuron chunk of a rat brain called a neocortical unit. With enough of

these units, the scientists on this so-called "Blue Brain" project hope to eventually build a

complete model of the human brain.

The brain would not be an artificial intelligence system, but rather a working neural circuit

that researchers could use to understand brain function and test virtual psychiatric treatments.But Blue Brain could be even better than artificial intelligence, lead researcher Henry

Markram told The Guardian newspaper in 2007: "If we build it right, it should speak."


18/35



How super computer is different from other computers??

Mainframe computers were introduced in 1975. A mainframe computer is a large computer in

term of price, power and speed. It is more powerful than minicomputer. Mainframe computer

can serve up to 50,000 users simultaneously. Its price is $5000 to $5 million. These

computers can store large amount of data, information and instructions. The users access a

mainframe computer through terminal or personal computer.A typical mainframe computer

can execute 16 million instructions per second. Qualified operators and programmers are

required to use these computers. Mainframe computers can accept all types of high-level

languages. Different types of peripheral devices can be attached with mainframe computer.

Examples:

1- IBM4381

2- NEC 610

3- DEC 10 etc.

Super Computer: Super computer were introduced in 1980. Super computer is the biggest in

size and the most expensive in price than any other computers. It is the most sophisticated,

complex and advanced computer. It has very large storage capacity. It can process trillions of

instructions in one second. Its price is $500000 to $350 million. Super computer use high

speed facilities such as satellite for online processing.

A supercomputer can handle high amounts of scientific computation. It is maintained in a

special room. It is 50000 times faster than that of microcomputers, which are very common

nowadays. The cost that is associated with a supercomputer is roughly $20 million. Due to its

high cost it is not used for domestic or office level of work.

Examples:

1- CRAY-XP

2- ETA-10 etc.


19/35



It is used in areas such as defence, weaponry systems, weather forecasting or scientific

research. It was first used for defence purposes and was used to keep the record information

of war weapons and its allied products.

For example George and David Chudnovsky broke the world record for PI calculation by

using two supercomputers to calculate PI to 480 million decimal places (PI is a commonly

used mathematical constant that is based on the relationship of a circle's circumference to its

diameter). From there onwards the value of PI became popular for geographically related

calculations. In the next few years, more and more large industries will start using

supercomputers such as the parallel computer, which will have hundreds or even thousands of

processors.

Mainframe computers are used in large scale organization whereas super computers are

considered to be fast with regardless of its size.Mainframes are generally called as an

operating system whereas super computers are a mini computers.

A MAINFRAME is one form of a computer system that is generally more powerful than

other typical mini systems. They r used in large organizations 4 large scale jobs& also

mainframes themselves may vary widely cost capability.

The kind traditionally used as the main record-keeper and data processor for large businesses

and government facilities. But Super-computer" is a term used for very fast computers,

regardless of their physical size. It used to be that a computer that could perform more than

one gigaflop (one billion operations per second) was considered to be a supercomputer. Now,

most high-end personal computers operate at that speed The most largest ,fastest the most

expensive computers in the world is SUPER COMPUTER. They are used for Bio-Medical

Research, Weather Forecasting,and Chemical Analysis in Laboratory etc.NEC'sEarth

Simulator in Japan is now world's fastest computer.


20/35



Top 10 Supercomputers in world

The following table gives the Top 10 positions of the supercomputers on November 18, 2013.

R

a

n

k

Rmax

RpeakName

Computer

design

Processor

type,

interconnect

VendorSite

Country, year

1 33.86354.902

Tianhe-2

NUDT

Xeon E52692 +XeonPhi 31S1P, THExpress-2

NUDT National Supercomputing Center in GuangChina,2013

217.59027.113

Titan

Cray XK7Opteron 6274 +TeslaK20X,Cray GeminiInterconnect

CrayOak Ridge National Laboratory

United States,2012

3 17.17320.133 Sequoia Blue Gene/QPowerPC A2,Custom IBM Lawrence Livermore National LaboratoryUnited States,2013

410.51011.280

K computerRIKENSPARC64 VIIIfx,Tofu

FujitsuRIKEN

Japan,2011

58.58610.066

MiraBlue Gene/QPowerPC A2,Custom

IBMArgonne National Laboratory

United States,2013

6 5.1688.520 Stampede

PowerEdge C8220

Xeon E52680 +XeonPhi,Infiniband

Dell Texas Advanced Computing CenterUnited States,2013

75.0085.872

JUQUEENBlue Gene/QPowerPC A2,Custom

IBMForschungszentrumJlich

Germany,2013

84.2935.033

VulcanBlue Gene/QPowerPC A2,Custom

IBM

Lawrence Livermore National LaboratoryUnited States,2013
http://en.wikipedia.org/wiki/Tianhe-2http://en.wikipedia.org/wiki/Tianhe-2http://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/National_Supercomputing_Center_in_Guangzhou_(NSCC-GZ)http://en.wikipedia.org/wiki/Chinahttp://en.wikipedia.org/wiki/Titan_(supercomputer)http://en.wikipedia.org/wiki/Cray_XK7http://en.wikipedia.org/wiki/Opteron_6274http://en.wikipedia.org/wiki/Nvidia_Teslahttp://en.wikipedia.org/wiki/Nvidia_Teslahttp://en.wikipedia.org/wiki/Crayhttp://en.wikipedia.org/wiki/Oak_Ridge_National_Laboratoryhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/IBM_Sequoiahttp://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Lawrence_Livermore_National_Laboratoryhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/K_computerhttp://en.wikipedia.org/wiki/K_computerhttp://en.wikipedia.org/wiki/RIKENhttp://en.wikipedia.org/wiki/SPARC64_VIIIfxhttp://en.wikipedia.org/wiki/Fujitsuhttp://en.wikipedia.org/wiki/Fujitsuhttp://en.wikipedia.org/wiki/RIKENhttp://en.wikipedia.org/wiki/Japanhttp://en.wikipedia.org/wiki/IBM_Mirahttp://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Texas_Advanced_Computing_Center#Stampedehttp://en.wikipedia.org/wiki/PowerEdgehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/Dellhttp://en.wikipedia.org/wiki/Dellhttp://en.wikipedia.org/wiki/Texas_Advanced_Computing_Centerhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Blue_Gene#Installations_2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Forschungszentrum_J%C3%BClichhttp://en.wikipedia.org/wiki/Germanyhttp://en.wikipedia.org/wiki/Blue_Gene#Installations_2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Lawrence_Livermore_National_Laboratoryhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Lawrence_Livermore_National_Laboratoryhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/Blue_Gene#Installations_2http://en.wikipedia.org/wiki/Germanyhttp://en.wikipedia.org/wiki/Forschungszentrum_J%C3%BClichhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/Blue_Gene#Installations_2http://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Texas_Advanced_Computing_Centerhttp://en.wikipedia.org/wiki/Dellhttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/PowerEdgehttp://en.wikipedia.org/wiki/Texas_Advanced_Computing_Center#Stampedehttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Argonne_National_Laboratoryhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/IBM_Mirahttp://en.wikipedia.org/wiki/Japanhttp://en.wikipedia.org/wiki/RIKENhttp://en.wikipedia.org/wiki/Fujitsuhttp://en.wikipedia.org/wiki/SPARC64_VIIIfxhttp://en.wikipedia.org/wiki/RIKENhttp://en.wikipedia.org/wiki/K_computerhttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Lawrence_Livermore_National_Laboratoryhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/PowerPC_A2http://en.wikipedia.org/wiki/Blue_Gene/Qhttp://en.wikipedia.org/wiki/IBM_Sequoiahttp://en.wikipedia.org/wiki/United_Stateshttp://en.wikipedia.org/wiki/Oak_Ridge_National_Laboratoryhttp://en.wikipedia.org/wiki/Crayhttp://en.wikipedia.org/wiki/Nvidia_Teslahttp://en.wikipedia.org/wiki/Nvidia_Teslahttp://en.wikipedia.org/wiki/Opteron_6274http://en.wikipedia.org/wiki/Cray_XK7http://en.wikipedia.org/wiki/Titan_(supercomputer)http://en.wikipedia.org/wiki/Chinahttp://en.wikipedia.org/wiki/National_Supercomputing_Center_in_Guangzhou_(NSCC-GZ)http://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/Tianhe-2


21/35



The following table gives the Top 10 positions of the supercomputers on November 18, 2013.

R

a

n

k

Rmax

RpeakName

Computer

designProcessor

type,

interconnect

VendorSite

Country, year

92.8973.185

SuperMUCiDataPlex DX360M4Xeon E52680,Infiniband

IBMLeibniz-Rechenzentrum

Germany,2012

102.566

4.701Tiahne-1A

NUDTXeon E52692 +XeonPhi 31S1P, THExpress-2

NUDTNational Supercomputing Center in Tianjin

China.

RankIn 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.

Rmax The highest score measured using the LINPACK benchmark suite. This is the

number that is used to rank the computers. Measured in quadrillions of floating point

operations per second, i.e. petaflops.

RpeakThis is the theoretical peak performance of the system. Measured in Pflops.

NameSome supercomputers are unique, at least on its location, and are therefore christened

by its owner.

ComputerThe computing platform as it is marketed.

Processor cores The number of active processor cores actively used running LINPACK.

After this figure is the processor architecture of the cores named.

VendorThe manufacturer of the platform and hardware.

SiteThe name of the facility operating the supercomputer.

CountryThe country in which the computer is situated.
http://en.wikipedia.org/wiki/SuperMUChttp://en.wikipedia.org/wiki/IDataPlexhttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Leibniz-Rechenzentrumhttp://en.wikipedia.org/wiki/Germanyhttp://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Xeon_Phihttp://en.wikipedia.org/wiki/Ivy_Bridge_(microarchitecture)http://en.wikipedia.org/wiki/National_University_of_Defense_Technologyhttp://en.wikipedia.org/wiki/Germanyhttp://en.wikipedia.org/wiki/Leibniz-Rechenzentrumhttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Infinibandhttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/Sandy_Bridge-Ehttp://en.wikipedia.org/wiki/IDataPlexhttp://en.wikipedia.org/wiki/SuperMUC


22/35



1. Tianhe-2 (MilkyWay-2)

Country:China

Site:National University of Defence Technology (NUDT)

Manufacturer:NUDT

Cores:3,120,000

Linpack Performance (Rmax):33,862.7 TFlop/s

Theoretical Peak (Rpeak):54,902.4 TFlop/s

Power:17,808.00 kW

Memory:1,024,000 GB

Interconnect:TH Express-2

Operating System:Kylin Linux

Compiler:ICC

Math Library:Intel MKL-11.0.0

MPI:MPICH2 with a customized GLEX channel
http://www.china.org.cn/top10/index.htm


23/35



2. Titan

Country:U.S.

Site:DOE/SC/Oak Ridge National Laboratory

System URL:http://www.olcf.ornl.gov/titan/

Manufacturer:Cray Inc.

Cores:560,640



Power:8,209.00 kW

Memory:710,144 GB

Interconnect:Cray Gemini interconnect

Operating System:Cray Linux Environment
http://www.olcf.ornl.gov/titan/http://www.china.org.cn/top10/2013-06/21/content_29187340_10.htmhttp://www.olcf.ornl.gov/titan/


24/35



3. Sequoia

Country:U.S.

Site:DOE/NNSA/LLNL

Manufacturer:IBM

Cores:1,572,864



Power:7,890.00 kW

Memory:1,572,864 GB

Interconnect:Custom Interconnect

Operating System:Linux
http://www.china.org.cn/top10/2013-06/21/content_29187340_9.htm


25/35



4. K computer

Country:Japan

Site:RIKEN Advanced Institute for Computational Science (AICS)

Manufacturer:Fujitsu

Cores:705,024



Power:12,659.89 kW

Memory:1,410,048 GB




26/35



5. Mira

Country:U.S.

Site:DOE/SC/Argonne National Laboratory

Manufacturer:IBM

Cores:786,432



Power:3,945.00 kW




27/35



6. Stampede

Country:U.S.

Site:Texas Advanced Computing Center/Univ. of Texas, Austin

System URL:http://www.tacc.utexas.edu/stampede

Manufacturer:Dell

Cores:462,462



Power:4,510.00 kW

Memory:192,192 GB

Interconnect:Infiniband FDR


Compiler:Intel

Math Library:MKL
http://www.tacc.utexas.edu/stampedehttp://www.china.org.cn/top10/2013-06/21/content_29187340_6.htmhttp://www.tacc.utexas.edu/stampede


28/35



7. JUQUEEN

Country:Germany

Site:ForschungszentrumJuelich (FZJ)

System URL:http://www.fz-

juelich.de/ias/jsc/EN/Expertise/Supercomputers/JUQUEEN/JUQUEEN_node.html

Manufacturer:IBM

Cores:458,752



Power:2,301.00 kW

Memory:458,752 GB


http://www.fz-juelich.de/ias/jsc/EN/Expertise/Supercomputers/JUQUEEN/JUQUEEN_node.htmlhttp://www.fz-juelich.de/ias/jsc/EN/Expertise/Supercomputers/JUQUEEN/JUQUEEN_node.htmlhttp://www.china.org.cn/top10/2013-06/21/content_29187340_5.htmhttp://www.fz-juelich.de/ias/jsc/EN/Expertise/Supercomputers/JUQUEEN/JUQUEEN_node.htmlhttp://www.fz-juelich.de/ias/jsc/EN/Expertise/Supercomputers/JUQUEEN/JUQUEEN_node.html


29/35



8. Vulcan

Country:U.S.

Site:DOE/NNSA/LLNL

Manufacturer:IBM

Cores:393,216



Power:1,972.00 kW

Memory:393,216 GB




30/35



9. SuperMUC

Country:Germany

Site:Leibniz Rechenzentrum

System URL:http://www.lrz.de/services/compute/supermuc/

Manufacturer:IBM

Cores:147,456



Power:3,422.67 kW

Interconnect:Infiniband FDR

http://www.lrz.de/services/compute/supermuc/http://www.china.org.cn/top10/2013-06/21/content_29187340_3.htmhttp://www.lrz.de/services/compute/supermuc/


31/35



10.Tianhe-1A (MilkyWay-1A)

Country:China

Site:National Supercomputing Center in Tianjin

Manufacturer:NUDT

Cores:186,368



Power:4,040.00 kW

Memory:229,376 GB

Interconnect:Proprietary


Compiler:ICC

MPI:MPICH2 with a custom GLEX channel


32/35



Supercomputing in India

India'ssupercomputerprogram was started in late 1980s becauseCraysupercomputers were

denied for import due to an arms embargo imposed on India, as it was a dual use technologyand could be used for developingnuclear weapons.

PARAM 8000 is considered India's firstsupercomputer. It was indigenously built in 1990

by Centre for Development of Advanced Computing and was replicated and installed at

ICAD Moscow in 1991 under Russian collaboration.

India's Rank in Top500super computersAs of June 2013, India has 11 systems on theTop500 list ranking 36, 69, 89, 95, 174, 245,

291, 309, 310, 311 and 439.

Rank Site NameRmax

(TFlop/s)Rpeak

(TFlop/s)

36Indian Institute of Tropical

MeteorologyiDataPlex DX360M4 719.2 790.7

69Centre for Development of

Advanced ComputingPARAM Yuva - II 386.7 529.4

89 National Centre for Medium RangeWeather Forecasting

iDataPlex DX360M4 318.4 350.1

95

CSIR Centre for Mathematical

Modelling and Computer

Simulation

Cluster Platform 3000

BL460c Gen8303.9 360.8
http://en.wikipedia.org/wiki/Indiahttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/Crayhttp://en.wikipedia.org/wiki/Supercomputershttp://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/PARAMhttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Top500http://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Indian_Institute_of_Tropical_Meteorologyhttp://en.wikipedia.org/wiki/Indian_Institute_of_Tropical_Meteorologyhttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/PARAM#Param_Yuva_IIhttp://en.wikipedia.org/wiki/National_Centre_for_Medium_Range_Weather_Forecastinghttp://en.wikipedia.org/wiki/National_Centre_for_Medium_Range_Weather_Forecastinghttp://en.wikipedia.org/wiki/National_Centre_for_Medium_Range_Weather_Forecastinghttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/CSIR_Centre_for_Mathematical_Modelling_and_Computer_Simulationhttp://en.wikipedia.org/wiki/National_Centre_for_Medium_Range_Weather_Forecastinghttp://en.wikipedia.org/wiki/National_Centre_for_Medium_Range_Weather_Forecastinghttp://en.wikipedia.org/wiki/PARAM#Param_Yuva_IIhttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Indian_Institute_of_Tropical_Meteorologyhttp://en.wikipedia.org/wiki/Indian_Institute_of_Tropical_Meteorologyhttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Top500http://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/PARAMhttp://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/Supercomputershttp://en.wikipedia.org/wiki/Crayhttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/India


33/35



174Vikram Sarabhai Space

Centre,ISRO

SAGA -

Z24XX/SL390s Cluster188.7 394.8

245 Manufacturing CompanyIndiaCluster Platform 3000

BL460c Gen8149.2 175.7

291Computational Research

Laboratories

EKA - Cluster Platform

3000 BL460c 132.8 172.6

309 Semiconductor Company (F)Cluster Platform 3000

BL460c Gen8129.2 182.0

310 Semiconductor Company (F)Cluster Platform 3000

BL460c Gen8129.2 182.0

311 Network CompanyCluster Platform 3000

BL460c Gen8128.8 179.7

439 IT Services Provider (B)Cluster Platform 3000

BL460c Gen8104.2 199.7
http://en.wikipedia.org/wiki/Vikram_Sarabhai_Space_Centrehttp://en.wikipedia.org/wiki/Vikram_Sarabhai_Space_Centrehttp://en.wikipedia.org/wiki/ISROhttp://en.wikipedia.org/wiki/Indiahttp://en.wikipedia.org/wiki/Computational_Research_Laboratorieshttp://en.wikipedia.org/wiki/Computational_Research_Laboratorieshttp://en.wikipedia.org/wiki/Computational_Research_Laboratorieshttp://en.wikipedia.org/wiki/EKA_(supercomputer)http://en.wikipedia.org/wiki/EKA_(supercomputer)http://en.wikipedia.org/wiki/EKA_(supercomputer)http://en.wikipedia.org/wiki/EKA_(supercomputer)http://en.wikipedia.org/wiki/EKA_(supercomputer)http://en.wikipedia.org/wiki/Computational_Research_Laboratorieshttp://en.wikipedia.org/wiki/Computational_Research_Laboratorieshttp://en.wikipedia.org/wiki/Indiahttp://en.wikipedia.org/wiki/ISROhttp://en.wikipedia.org/wiki/Vikram_Sarabhai_Space_Centrehttp://en.wikipedia.org/wiki/Vikram_Sarabhai_Space_Centre


34/35



PARAM SERIES

After being deniedCraysupercomputers as a result of a technologyembargo,India started a

program to develop indigenous supercomputers and supercomputing technologies.

Supercomputers were considered a double edged weapon capable of assisting in the

development ofnuclear weapons.[5]For the purpose of achieving self-sufficiency in the field,

theCentre for Development of Advanced Computing (C-DAC) was set up in 1988 by the

then Department of Electronics with Dr.Vijay Bhatkar as its Director. The project was given

an initial run of 3 years and an initial funding of 300,000,000. Because the same amount of

money and time was usually expended to purchase a supercomputer from the US. In 1990,

aprototype was produced and wasbenchmarked at the 1990 Zurich Supercomputing Show. It

surpassed most other systems, placing India second after US.

The final result of the effort was the PARAM 8000, which was installed in 1991. It is

considered India's first supercomputer.

PARAM 8000

Unveiled in 1991, PARAM 8000 usedInmos T800transputers.Transputers were a fairly new

and innovativemicroprocessor architecture designed forparallel processing at the time. It

was a distributedMIMD architecture with a reconfigurable interconnection network. It had

64CPUs.

PARAM 8600

PARAM 8600 was an improvement over PARAM 8000. It was a 256 CPU computer. For

every four Inmos T800, it employed anIntel i860 coprocessor. The result was over

5GFLOPS at peak forvector processing.Several of these models were exported.

PARAM 9900/SS

PARAM 9900/SS was designed to be aMPP system. It used theSuperSPARC IIprocessor.

The design was changed to be modular so that newer processors could be easily

accommodated. Typically, it used 32-40 processors. But, it could be scaled up to 200 CPUs

using theclose network topology.PARAM 9900/USwas theUltraSPARC variant

and PARAM 9900/AAwas the DEC variant.
http://en.wikipedia.org/wiki/Crayhttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/Embargohttp://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/PARAM#cite_note-5http://en.wikipedia.org/wiki/PARAM#cite_note-5http://en.wikipedia.org/wiki/PARAM#cite_note-5http://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/Vijay_bhatkarhttp://en.wikipedia.org/wiki/Prototypehttp://en.wikipedia.org/wiki/Benchmark_(computing)http://en.wikipedia.org/wiki/Inmoshttp://en.wikipedia.org/wiki/Transputerhttp://en.wikipedia.org/wiki/Microprocessorhttp://en.wikipedia.org/wiki/Parallel_processinghttp://en.wikipedia.org/wiki/MIMDhttp://en.wikipedia.org/wiki/CPUhttp://en.wikipedia.org/wiki/Intel_i860http://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Vector_processinghttp://en.wikipedia.org/wiki/Massively_parallel_(computing)http://en.wikipedia.org/wiki/SuperSPARChttp://en.wikipedia.org/wiki/Clos_networkhttp://en.wikipedia.org/wiki/UltraSPARChttp://en.wikipedia.org/wiki/UltraSPARChttp://en.wikipedia.org/wiki/Clos_networkhttp://en.wikipedia.org/wiki/SuperSPARChttp://en.wikipedia.org/wiki/Massively_parallel_(computing)http://en.wikipedia.org/wiki/Vector_processinghttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Intel_i860http://en.wikipedia.org/wiki/CPUhttp://en.wikipedia.org/wiki/MIMDhttp://en.wikipedia.org/wiki/Parallel_processinghttp://en.wikipedia.org/wiki/Microprocessorhttp://en.wikipedia.org/wiki/Transputerhttp://en.wikipedia.org/wiki/Inmoshttp://en.wikipedia.org/wiki/Benchmark_(computing)http://en.wikipedia.org/wiki/Prototypehttp://en.wikipedia.org/wiki/Vijay_bhatkarhttp://en.wikipedia.org/wiki/Centre_for_Development_of_Advanced_Computinghttp://en.wikipedia.org/wiki/PARAM#cite_note-5http://en.wikipedia.org/wiki/Nuclear_weaponshttp://en.wikipedia.org/wiki/Embargohttp://en.wikipedia.org/wiki/Supercomputerhttp://en.wikipedia.org/wiki/Cray


35/35


PARAM 10000

In 1998, the PARAM 10000 was unveiled. PARAM 10000 used several independent nodes,

each based on theSun Enterprise 250 server and each such server contained two

400MhzUltraSPARC IIprocessors. The base configuration had three compute nodes and aserver node. The peak speed of this base system was 6.4GFLOPS.A typical system would

contain 160CPUs and be capable of 100GFLOPS.But; it was easily scalable to

theTFLOP range.

PARAM Padma

PARAM Padma (PadmameansLotusinSanskrit)was introduced in April 2003.It had a peak

speed of 1024 GFLOPS (about 1 TFLOP) and peak storage of 1 TB. It used

248IBMPower4CPUs of 1 GHz each. Theoperating system was IBM AIX 5.1L. It used

PARAMnet II as its primary interconnects. It was the first Indian supercomputer to break the

1 TFLOP barriers.

PARAM Yuva

PARAM Yuva (Yuvameans YouthinSanskrit) was unveiled in November 2008. It has a

maximum sustainable speed (Rmax) of 38.1 TFLOPS and a peak speed (Rpeak) of 54

TFLOPS.[10]There are 4608 cores in it, based onIntel 73XX of 2.9 GHz each. It has a storagecapacity of 25 TB up to 200 TB. It uses PARAMnet 3 as its primary interconnects.

ParamYuva II

ParamYuva II was made by Centre for Development of Advanced Computing in a period of

three months, at a cost of 16 crore (US$2 million), and was unveiled on 8 February 2013. It

performs at a peak of 524 teraflops and consumes 35% less energy as compared to

ParamYuva. It delivers sustained performance of 360.8 teraflops on the community standard

Linpack benchmark, and would have been ranked 62 in the November 2012 ranking list of

Top500. In terms of power efficiency, it would have been ranked 33rd in the November 2012

List of Top Green500 supercomputers of the world. It is the first Indian supercomputer

achieving more than 500 teraflops.
http://en.wikipedia.org/wiki/Sun_Enterprisehttp://en.wikipedia.org/wiki/Mhzhttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/CPUhttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Sanskrithttp://en.wikipedia.org/wiki/Bytehttp://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Power4http://en.wikipedia.org/wiki/Operating_systemhttp://en.wikipedia.org/wiki/IBM_AIXhttp://en.wikipedia.org/wiki/Sanskrithttp://en.wikipedia.org/wiki/PARAM#cite_note-top500yuva-10http://en.wikipedia.org/wiki/PARAM#cite_note-top500yuva-10http://en.wikipedia.org/wiki/PARAM#cite_note-top500yuva-10http://en.wikipedia.org/wiki/Tigerton_(microprocessor)#Tigertonhttp://en.wikipedia.org/wiki/Tigerton_(microprocessor)#Tigertonhttp://en.wikipedia.org/wiki/PARAM#cite_note-top500yuva-10http://en.wikipedia.org/wiki/Sanskrithttp://en.wikipedia.org/wiki/IBM_AIXhttp://en.wikipedia.org/wiki/Operating_systemhttp://en.wikipedia.org/wiki/Power4http://en.wikipedia.org/wiki/IBMhttp://en.wikipedia.org/wiki/Bytehttp://en.wikipedia.org/wiki/Sanskrithttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/CPUhttp://en.wikipedia.org/wiki/FLOPShttp://en.wikipedia.org/wiki/Mhzhttp://en.wikipedia.org/wiki/Mhzhttp://en.wikipedia.org/wiki/Sun_Enterprise

supercomputers (1).docx

Documents