Past, Present and Future of Super Computers

Many definitions of supercomputers have come and gone. Some favorites of the past are any computer costing more than ten million dollars, whose performance is limited by input/output (I/O) rather than by the CPU, that is “only one” generation behind what you really need.

We’ve all heard of supercomputers. Unlike mainframes and minicomputers, supercomputers are used for the heavy stuff like weather maps, construction of atom bombs, finding oil, earthquake prediction, and sciences where a lot of calculations must be done. They are also used to help governments eavesdrop on anything passing through telephone, data lines, e-mail, or radio waves; and anything that is written, etc.

In computing, FLOPS (or flops) is an acronym meaning Floating Point Operations per Second. This is used as a measure of a computer’s performance, especially in fields of scientific calculations that make heavy use of floating point calculations. (Compare to MIPS — million instructions per second.) One should speak in the singular of a FLOPS and not of a FLOP, although the latter is frequently encountered. The final S stands for second and does not indicate a plural. The standard SI prefixes can be used for this purpose, resulting in such units as megaflops (MFLOPS, 106 FLOPS), gigaflops (GFLOPS, 109 FLOPS), teraflops (TFLOPS, 1012 FLOPS), petaFLOPS (PFLOPS, 1015 FLOPS) and exaFLOPS (EFLOPS, 1018 FLOPS).

Though all contemporary personal computers perform in the tens or hundreds of megaflops, they still cannot solve certain problems fast enough. It was only in the beginning of 2000 that the supercomputing arena moves into the gigaflops region. What this means is that you can have a computer calculate problems at the speed of a few gigaflops, but doing the same calculations at “just” 100 megaflops and within acceptable time, too, is almost impossible. Meaning, with supercomputers you can do calculations within a time limit or session that is acceptable to the user. To put it stronger: you can do anything in real time with a supercomputer that cannot be done in your lifetime with one single PC.

Blue Gene L Super 16 Racks Super Computer

According to the Top 500 Super Computers, the fastest computer in the world as of June 2006 was the IBM Blue Gene/L supercomputer, measuring a peak of 207.3 TFLOPS. It has been designed in such as way to provide efficient cooling. In June of 2006, a new computer was announced by Japanese research institute RIKEN, the MDGRAPE-3. The computer’s performance tops out at one petaflop, over three times faster than the Blue Gene/L. MDGRAPE-3 is not a general purpose computer, which is why it does not appear in the Top 500 list.

Why are thousands of processors used in supercomputers? Have you ever thought of that? The most obvious reason is that our technology is not capable of producing a chip that powerful as yet. The other reason is that since our technology is not capable of making that super chip, YET, we combine many chips to form one ‘virtual’ processor, operating as one big single CPU. Yet another reason is money, to put many single reasonably cheap CPUs in a large array is mostly cheaper than to produce a giant one. With the contemporary technology available to us now, we would have to produce a CPU the size of several square meters. So the technology to make one is not in place yet. What is needed is the implementation of new technology, something like bio neural processors, quantum based CPU’s and also an upcoming field, CPUs based on light.

Construction of supercomputers is an awesome and very expensive task. To get a machine from the laboratory to the market may take several years. The most recent development costs of supercomputers varied between 150 to 500 million dollars or more. This is one of the major reasons that the development of a supercomputer is kept very hush-hush. The latest supers are only possible to create with the help of governments and one or more large size companies. Using a supercomputer is expensive as well. As a user, you are charged according to the time you use the system what is expressed in the number of processor (CPU) seconds your program runs. In the recent past, Cray (one of the first supercomputers) time was $1,000 per hour. The use of this “Cray time” was a very common way to express computer costs in time and dollars.

Who really needs supercomputing today are mostly scientists performing mass computing at ultra high speed. They use such computers in all imaginable disciplines: space exploration and related imagery, environmental simulations (global warming effects) mathematics, physics, gene technology, and many others. More real world examples are: industrial and technological applications, world spanning financial and economical systems in which speed is essential. Also, more and more supercomputers are used for creating simulations for building airplanes, creating new chemical substances, new materials, and testing car crashes without having to crash a car. Supercomputers are used for applications where it will take more than a few days to get the results or when the results are impossible for a slower computer to calculate. Supercomputers have been used to improve car and plane safety, predict dangerous weather accurately, and to design life-saving drugs quickly.

Atanasoff-Berry Computer (ABC)

The Atanasoff-Berry Computer (ABC) was the first electronic digital computing device built by Dr. Atanasoff and Clifford E. Berry at Iowa State College during 1939–42. The machine, conceived in 1937, was capable of solving up to 29 simultaneous linear equations and was successfully tested, though its input/output mechanism was still unreliable in 1942. The ABC pioneered important elements of modern computing, including binary arithmetic and electronic switching elements, but its special-purpose nature and lack of a changeable, stored program distinguish it from modern computers. The system weighed more than seven hundred pounds (320 kg). It contained approximately 1 mile (1.6 km) of wire, 280 dual-triode vacuum tubes, 31 thyratrons. The original ABC was eventually dismantled, and all of its pieces except for one memory drum were discarded. In 1997, a team of researchers from Ames Laboratory (located on the Iowa State campus) finished building a working replica of the Atanasoff-Berry Computer for a cost of $350,000. This replica dispelled any doubt over whether or not the ABC actually could perform the tasks it was designed to do. The new ABC is now on permanent display in the first floor lobby of the Durham Center for Computation and Communication at Iowa State University.

In the mainframe area in the early 1960s; the bunch was the major players in that field. Others entered the arena in supercomputing after CDC and Cray showed it was possible to create supers. In 40 years there are but a few players left in the supercomputing arena like Cray, Dell, HP, Amdahl, Compaq, IBM, NEC, SGI, Sun, etc

The Blue Gene/L supercomputer has broken its own record to achieve more than double the number of calculations it can do a second. It reached 280.6 teraflops – that is 280.6 trillion calculations a second. The IBM machine, at the US Lawrence Livermore National Laboratory, officially became the most powerful computer on the planet in June 06. Blue Gene’s performance, while it has been under construction, has quadrupled in just 12 months. Blue Gene will work on materials ageing calculations, molecular dynamics, material modeling as well as turbulence and instability in hydrodynamics. Their massive brains will be able to perform half a petaflop together – that is half a quadrillion (1,000,000,000,000,000) calculations a second.

A supercomputer generates large amounts of heat and must be cooled. Cooling most supercomputers is a major HVAC (Heating Ventilating and Air Conditioning) problem. Supercomputers consume and produce massive amounts of data in a very short period of time. According to Ken Batcher, “A supercomputer is a device for turning compute-bound problems into I/O-bound problems.” Much work on external storage bandwidth is needed to ensure that this information can be transferred quickly and stored/retrieved correctly. The challenge which was a dream has undertaken by company, RIKEN, Intel K.K., and SGI Japan, Ltd. They have recently announced that they have succeeded in building a high-speed computer system, named “MDGRAPE-3″, for carrying out molecular dynamics simulations at a theoretical speed of one petaflops. The system consists of 201 units of 24 specially designed MDGRAPE-3 chips (a total of 4808 chips), plus 64 servers each with 256 of the new Dual-Core Intel Xeon Processor 5000 series processors, and 37 servers each containing 74 Intel Xeon Processor 3.2GHz (2MB L2 cache) processors.

Read More about  Atanasoft Berry Computer>>

Design for Compact Super Computer

Popular Internet search engine Google is reportedly developing one of the world’s most powerful supercomputers in a bid to outstrip rivals Yahoo and Microsoft. According to The Telegraph, Google is building a vast complex said to be the size of two football pitches with cooling towers four floors high in Oregon. The new Google “powerplant”, which is known as “Project 02”. The new Oregon centre will form just a part of Google’s global computing system, called the “Googleplex”.

Computers are constructing and testing new computers, which in their turn are even faster, and so on….

Related Articles:

• FlOPS – Wikipedia
• Top500 Super Computers
• About Supercomputing Seminar In IIT Bombay

Advertisement