For commercial failures, see list of commercial failures.

In computing, FLOPS is an abbreviation of 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. A commercial failure is a product that does not reach expectations of success, failing to come even close. ... Originally, the word computing was synonymous with counting and calculating, and a science that deals with the original sense of computing mathematical calculations. ... A drawing of a desktop computer. ... A floating-point number is a digital representation for a number in a certain subset of the rational numbers, and is often used to approximate an arbitrary real number on a computer. ... A calculation is a deliberate process for transforming one or more inputs into one or more results. ... Million instructions per second (MIPS) is a measure of a computers processor speed. ...

Computing devices exhibit an enormous range of performance levels in floating-point applications, so it makes sense to introduce larger units than the FLOPS. The standard SI prefixes can be used for this purpose, resulting in such units as the megaFLOPS (MFLOPS, 10⁶ FLOPS), the gigaFLOPS (GFLOPS, 10⁹ FLOPS), the teraFLOPS (TFLOPS, 10¹² FLOPS), and the petaFLOPS (PFLOPS, 10¹⁵ FLOPS). An SI prefix is a prefix that can be applied to an SI unit to form a decimal multiple or submultiple. ...

The performance spectrum

A cheap but modern desktop computer using, for example, a Pentium 4 or Athlon 64 CPU, typically runs at a clock frequency in excess of 2 GHz and provides computational performance in the range of a few GFLOPS. Even some video game consoles of the late 1990s and early 2000s, such as the Gamecube and Dreamcast, had performance in excess of one GFLOPS (but see below). Desktop computer with several common peripherals (Monitor, keyboard, mouse, speakers, microphone and a printer) A desktop computer is an independent personal computer that is made especially for use on a desk in an office or home. ... Pentium 4 (with hyper-threading) brand logo The Pentium 4 is a seventh-generation x86 architecture microprocessor produced by Intel and is their first all-new CPU design, called the NetBurst architecture, since the Pentium Pro of 1995. ... The Athlon 64 (codenamed ClawHammer, Newcastle, Winchester, Venice, and San Diego) represents AMDs entry into the consumer 64-bit microprocessor market, released on September 23, 2003. ... Intel 80486DX2 microprocessor in a ceramic PGA package A central processing unit (CPU), or sometimes simply processor, is the component in a digital computer that interprets and executes instructions and data contained in software. ... A gigahertz is a billion hertz or a thousand megahertz, a measure of frequency. ... The XBox 360 is an example of a current generation video game console. ... The 1990s decade refers to the years from 1990 to 1999, inclusive, the last decade of the 20th Century. ... Saddam Hussein shortly after his capture Major controversy over U. S. presidential election (November 7-December 13, 2000) September 11, 2001 terrorist attack on New Yorks World Trade Center and Virginias Pentagon killing almost 3000 people. ... The Nintendo GameCube (Japanese: ゲームキューブ; originally code-named Dolphin during development; abbreviated as GCN) is Nintendos fourth home video game console, belonging to the 128-bit era; the same generation as Segas Dreamcast, Sonys PlayStation 2, and Microsofts Xbox. ... Sega Dreamcast The Sega Dreamcast (Japanese: ドリームキャスト; code-named Katana during development) was Segas last video game console. ...

The original supercomputer, the Cray-1, was set up at Los Alamos National Laboratory in 1976. The Cray-1 was capable of 80 MFLOPS (or, according to another source, 138–250 MFLOPS). In fewer than 30 years since then, the computational speed of supercomputers has jumped a millionfold. A supercomputer is a computer that leads the world in terms of processing capacity, particularly speed of calculation, at the time of its introduction. ... CRAY-1 at the EPFL in Switzerland. ... Los Alamos National Laboratory, aerial view from 1995. ... 1976 (MCMLXXVI) is a leap year starting on Thursday (link will take you to calendar). ...

According to Top500.org, the fastest computer in the world as of October 2005 was the IBM Blue Gene/L supercomputer, measuring a peak of 280.6 TFLOPS. That's more than twice the previous Blue Gene/L record of 136.8 teraFLOPS, set when only half the machine was installed. Blue Gene (unveiled October 27th, 2005) contains 131,072 processor cores, yet each of these cores are quite similar to those found in many mid-performance computers (PowerPC 440). Look up October in Wiktionary, the free dictionary October is the tenth month of the year in the Gregorian Calendar and one of seven Gregorian months with the length of 31 days. ... 2005 (MMV) was a common year starting on Saturday of the Gregorian calendar. ... Blue Gene/L Blue Gene is a computer architecture project designed to produce several next-generation supercomputers, designed to reach operating speeds in the petaflops range, and currently reaching speeds over 360 teraflops. ... PowerPC 440 is a low power microprocessor. ...

Listed first on the top500.org website (see above for link), it is a joint project of the Lawrence Livermore National Laboratory and IBM Article.

Distributed computing uses the Internet to link personal computers to achieve a similar effect: it has allowed SETI@home, the largest such project, to compute data at more than 100 TFLOPS. Folding@home, the most powerful distributed computing project, has been able to sustain over 200 TFLOPS. As of June 2005, GIMPS is sustaining 17 TFLOPS, while Einstein@home is actually crunching more than 50 TFLOPS against 167 TFLOPS of its theoretical computing speed. In computer science, distributed computing studies the coordinated use of physically distributed computers. ... SETI@home logo SETI@home (SETI at home) is a grid computing (distributed computing in the projects own terminology) project using Internet-connected computers, hosted by the Space Sciences Laboratory, at the University of California, Berkeley, in the United States. ... The Microsoft Windows Folding@Home client displays a 3D model of the protein being simulated. ... 2005 (MMV) was a common year starting on Saturday of the Gregorian calendar. ... The Great Internet Mersenne Prime Search, or GIMPS, is a collaborative project of volunteers, who use Prime95 and MPrime, special software that can be downloaded from the Internet for free, in order to search for Mersenne prime numbers. ... A screenshot of the Einstein@home graphics. ...

Pocket calculators are at the other end of the performance spectrum. Each calculation request to a typical calculator requires only a single operation, so there is rarely any need for its response time to exceed that needed by the operator. Any response time below 0.1 second is experienced as instantaneous by a human operator, so a simple calculator could be said to operate at about 10 FLOPS. A basic arithmetic calculator. ... In telecommunication, response time is the time a system or functional unit takes to react to a given input. ...

Humans are even worse floating-point processors. If it takes a person a quarter of an hour to carry out a pencil-and-paper long division problem with 10 significant digits, that person would be calculating in the milliFLOPS range. Bear in mind, however, that a purely mathematical test may not truly measure a human's FLOPS, as a human is also processing smells, sounds, touch, sight and motor coordination. This takes an average human's FLOPS up to an estimated 10 quadrillion FLOPS (roughly 10 PFLOPS). [1] Human beings are defined variously in biological, spiritual, and cultural terms, or in combinations thereof. ... --This article needs to be improved. ...

FLOPS as a measure of performance

In order for FLOPS to be useful as a measure of floating-point performance, a standard benchmark must be available on all computers of interest. One example is the LINPACK benchmark. In computing, a benchmark is the result of running a computer program, or a set of programs, in order to assess the relative performance of an object, by running a number of standard tests and trials against it. ... LINPACK is a software library for performing numerical linear algebra on digital computers. ...

FLOPS in isolation are arguably not very useful as a benchmark for modern computers. There are many factors in computer performance other than raw floating-point computation speed, such as I/O performance, interprocessor communication, cache coherence, and the memory hierarchy. This means that supercomputers are in general only capable of a small fraction of their "theoretical peak" FLOPS throughput (obtained by adding together the theoretical peak FLOPS performance of every element of the system). Even when operating on large highly parallel problems, their performance will be bursty, mostly due to the residual effects of Amdahl's law. Real benchmarks therefore measure both peak actual FLOPS performance as well as sustained FLOPS performance. Cache coherency (alternatively cache coherence or cache consistency) refers to the integrity of data stored in local caches of a shared resource. ... The hierarchical arrangement of storage in current computer architectures is called the memory hierarchy. ... Amdahls law, named after computer architect Gene Amdahl, is used to find the maximum expected improvement to an overall system when only part of the system is improved. ...

For ordinary (non-scientific) applications, integer operations (measured in MIPS) are far more common. Measuring floating point operation speed, therefore, does not predict accurately how the processor will perform on just any problem. However, for many scientific jobs such as analysis of data, a FLOPS rating is effective. The integers consist of the positive natural numbers (1, 2, 3, …), their negatives (−1, −2, −3, ...) and the number zero. ... Million instructions per second (MIPS) is a measure of a computers processor speed. ...

Historically: the earliest reliably documented serious use of the Floating Point Operation as metric appears to be AEC justification to Congress for purchasing a Control Data CDC 6600 in the mid-1960s. The computing world is saddled with this marginal metric ever since. If an earlier reliability documented use can be found, please get verification with a second independent source (it should be more than casual academic citation). AEC is a three-letter acronym which can refer to several different things: The United States Atomic Energy Commission, a civilian organization that oversaw development of atomic science and technology from 1946 to 1974. ... The CDC 6600 was a mainframe computer from Control Data Corporation, first manufactured in 1965. ...

The terminology is currently so confusing that Export Control is now governed by millions of "Theoretical Operations Per Second" or MTOPS.

FLOPS, GPUs, and game consoles

Very high FLOPS figures are often quoted for inexpensive computer video cards and game consoles. A GeForce 4 4200-based graphics card A graphics card or video card is a component of a computer which is designed to convert a logical representation of an image stored in memory to a signal that can be used as input for a display medium, most often a monitor... The Nintendo GameCube is an example of a popular video game console. ...

For example, the Xbox 360 has been announced as having a system floating point performance of around one hundred GFLOPS, while the PS3 has been announced as having 218 GFLOPS. By comparison, a high-end general-purpose PC would have a FLOPS rating of around ten GFLOPS, if the performance of its CPU alone was considered. The 1 or 2 TFLOPS ratings that were sometimes mentioned regarding the consoles would even appear to class them as supercomputers. The Xbox 360 is Microsofts newest video game console, the successor to their original Xbox. ... The Sony PlayStation 3 (colloquially known as the PS3) will be the new video game console in Sonys PlayStation series. ... A supercomputer is a computer that leads the world in terms of processing capacity, particularly speed of calculation, at the time of its introduction. ...

However, these FLOPS figures should be treated with caution, as they are the product of marketing. The game console figures are often based on total system performance (CPU + GPU). In the extreme case, the TFLOPS figure is primarily derived from the function of the single-purpose texture filtering unit of the GPU. This piece of logic is tasked with doing a weighted average of sometimes hundreds of pixels in a texture during a look-up (particularly when performing a quadrilinear anisotropically filtered fetch from a 3D texture). However, single-purpose hardware can never be included in an honest FLOPS figure. GeForce 6600GT (NV43) GPU Radeon 9800 Pro (R350) GPU A Graphics Processing Unit or GPU (also occasionally called Visual Processing Unit or VPU) is a dedicated graphics rendering device for a personal computer or game console. ...

Still, the programmable pixel pipelines of modern GPUs are capable of a theoretic peak performance that is an order of a magnitude higher than a CPU. An NVIDIA 7800 GTX 512 is capable of around 200 GFLOPS. This is possible because 3D graphics operations are a classic example of a highly parallelizable problem which can easily be split between different execution units and pipelines, allowing a high speed gain to be obtained from scaling the number of logic gates while taking advantage of the fact that the cost-efficiency sweet spot of (number of transistors)*frequency lies at around 500 MHz. This has to do with the imperfection rate in the manufacturing process, which rises exponentially with frequency. While CPUs dedicate a few transistors to run at very high frequency in order to process a single thread of execution very quickly, GPUs pack a great deal more transistors running at a low speed because they are designed to simultaneously process a large number of pixels with no requirement that each pixel be completed quickly. Moreover, GPUs are not designed to perform branch operations (IF statements which determine what will be executed based on the value of a piece of data) well. The circuits for this, in particular the circuits for predicting how a program will branch to ready data for it, consume an inordinant number of transistors on a CPU that could be used for FLOPS. Lastly, GPUs are designed to be fed a continuous stream of predetermined data. CPUs, meanwhile, access data more unpredictably. This requires them to include an amount of on-chip memory called a cache for quick random access. This cache eats up the majority of CPU transistors. Parallel computing is the simultaneous execution of the same task (split up and specially adapted) on multiple processors in order to obtain results faster. ... The term scaling can have several manings: Scaling can be defined as the determination of the interdependency of variables in a physical system. ... A conditional statement, in computer science, is a vital part of a programming language. ...

The tasks which can be performed well on the GPU are thus slightly more limited, yet some problems can take advantage of the specialized processing very well. Even those that are inefficient in implementation have to be ten times less efficient to lose out in the end. General purpose computing on GPUs is an emerging field which hopes to utilize the vast advantage in raw FLOPS, as well as memory bandwidth, of modern video cards. A few applications can even take advantage of the texture fetch unit in computing averages in (1, 2, or 3 dimensional) sorted data for a further boost in performance.

cost of computing

• 1997: about US$30,000 per Gflops; with two 16-Pentium-Pro–processor Beowulf-class computers, Loki and Hyglac
• 2000, May: $640 per Gflops, KLAT2, University of Kentucky
• 2003, August: $82 per Gflops, KASY0, University of Kentucky
• 2006: about $5 per Gflops in the XBOX 360 in case Linux will be implented as intended [2]

This trend toward low cost follows Moore's law. Growth of transistor counts for Intel processors (dots) and Moores Law (upper line=18 months; lower line=24 months) Moores law is the empirical observation that at our rate of technological development, the complexity of an integrated circuit, with respect to minimum component cost will double in about...

Trivia

In the Star Trek fictional universe, circa 2364, the android Data was constructed with an initial linear computational speed rated at 60 trillion operations per second, or 60 TFLOPS (and thereby, potentially 'dating' the series Star Trek: The Next Generation in which he appears); however, he was later able to infinitely exceed this limit by modifying his hardware and software. Star Trek collectively refers to a science-fiction franchise spanning six unique television series, 726 episodes and ten motion pictures in addition to hundreds of novels, video games, and other works of fiction all set within the same fictional universe created by Gene Roddenberry in the mid-1960s. ... A fictional universe is a cohesive imaginary world that serves as the setting or backdrop for one or (more commonly) multiple works of fiction. ... Look up Circa on Wiktionary, the free dictionary The Latin word circa, literally meaning about, is often used to describe various dates (often birth and death dates) that are uncertain. ... (Redirected from 2364) (23rd century - 24th century - 25th century - more centuries) The 24th century (Gregorian Calendar) comprises the years 2301-2400. ... The android Data, portrayed by Brent Spiner, from the TV series Star Trek: The Next Generation An android is an artificially created robot, an automaton, that resembles a human being usually both in appearance and behavior. ... Data, played by Brent Spiner, is a character in the Star Trek fictional universe. ... Datateknologerna vid Ã…bo Akademi r. ... The title as it appeared in most episodes opening credits. ...

External links

• Current GIMPS throughput
• Top500.org
• Oscar Linux-cluster ranking list by CPUs/types and respective FLOPS
• COBRAPoint implements Gigaflops