supercomputer
A supercomputer is a computer with a high level of performance as compared to a general-purpose computer. The performance of a supercomputer is commonly measured in floating-point operations per second ( FLOPS) instead of million instructions ...
with four
vector processor
In computing, a vector processor or array processor is a central processing unit (CPU) that implements an instruction set where its instructions are designed to operate efficiently and effectively on large one-dimensional arrays of data called ...
s made by
Cray Research
Cray Inc., a subsidiary of Hewlett Packard Enterprise, is an American supercomputer manufacturer headquartered in Seattle, Washington. It also manufactures systems for data storage and analytics. Several Cray supercomputer systems are listed i ...
starting in 1985. At 1.9
GFLOPS
In computing, floating point operations per second (FLOPS, flops or flop/s) is a measure of computer performance, useful in fields of scientific computations that require floating-point calculations. For such cases, it is a more accurate meas ...
peak performance, it was the fastest machine in the world when it was released, replacing the
Cray X-MP
The Cray X-MP was a supercomputer designed, built and sold by Cray Research. It was announced in 1982 as the "cleaned up" successor to the 1975 Cray-1, and was the world's fastest computer from 1983 to 1985 with a quad-processor system performance ...
in that spot. It was, in turn, replaced in that spot by the
Cray Y-MP
The Cray Y-MP was a supercomputer sold by Cray Research from 1988, and the successor to the company's X-MP. The Y-MP retained software compatibility with the X-MP, but extended the address registers from 24 to 32 bits. High-density VLSI ECL tech ...
in 1988.
The Cray-2 was the first of
Seymour Cray
Seymour Roger Cray (September 28, 1925 – October 5, 1996 ) was an American
CDC 8600
The CDC 8600 was the last of Seymour Cray's supercomputer designs while he worked for Control Data Corporation. As the natural successor to the CDC 6600 and CDC 7600, the 8600 was intended to be about 10 times as fast as the 7600, already the f ...
in the early 1970s, but the
emitter-coupled logic
In electronics, emitter-coupled logic (ECL) is a high-speed integrated circuit bipolar transistor logic family. ECL uses an overdriven bipolar junction transistor (BJT) differential amplifier with single-ended input and limited emitter current to ...
(ECL)
transistor
upright=1.4, gate (G), body (B), source (S) and drain (D) terminals. The gate is separated from the body by an insulating layer (pink).
A transistor is a semiconductor device used to Electronic amplifier, amplify or electronic switch, switch e ...
s of the era were too difficult to package into a working machine. The Cray-2 addressed this through the use of ECL
integrated circuit
An integrated circuit or monolithic integrated circuit (also referred to as an IC, a chip, or a microchip) is a set of electronic circuits on one small flat piece (or "chip") of semiconductor material, usually silicon. Large numbers of tiny ...
s, packing them in a novel 3D wiring that greatly increased circuit density.
The dense packaging and resulting heat loads were a major problem for the Cray-2. This was solved in a unique fashion by forcing the electrically inert
Fluorinert
Fluorinert is the trademarked brand name for the line of electronics coolant liquids sold commercially by 3M. As perfluorinated compounds (PFCs), all Fluorinert variants have an extremely high Global Warming Potential (GWP), so should be used wit ...
liquid through the circuitry under pressure and then cooling it outside the processor box. The unique "waterfall" cooler system came to represent high-performance computing in the public eye and was found in many informational films and as a movie prop for some time.
Unlike the original Cray-1, the Cray-2 had difficulties delivering peak performance. Other machines from the company, like the X-MP and Y-MP, outsold the Cray-2 by a wide margin. When Cray began development of the
Cray-3
The Cray-3 was a vector supercomputer, Seymour Cray's designated successor to the Cray-2. The system was one of the first major applications of gallium arsenide (GaAs) semiconductors in computing, using hundreds of custom built ICs packed into ...
, the company chose to develop the
Cray C90
The Cray C90 series (initially named the Y-MP C90) was a vector processor supercomputer launched by Cray Research in 1991. The C90 was a development of the Cray Y-MP
The Cray Y-MP was a supercomputer sold by Cray Research from 1988, and the su ...
series instead. This is the same sequence of events that occurred when the 8600 was being developed, and as in that case, Cray left the company.
Initial design
With the successful launch of his famed
Cray-1
The Cray-1 was a supercomputer designed, manufactured and marketed by Cray Research. Announced in 1975, the first Cray-1 system was installed at Los Alamos National Laboratory in 1976. Eventually, over 100 Cray-1s were sold, making it one of the ...
,
Seymour Cray
Seymour Roger Cray (September 28, 1925 – October 5, 1996 ) was an American
Chippewa Falls, Wisconsin
Chippewa Falls is a city located on the Chippewa River in Chippewa County in the northwestern part of the U.S. state of Wisconsin. The population was 14,778 in the 2021 census. Incorporated as a city in 1869, it is the county seat of Chippewa Cou ...
from
Control Data
Control Data Corporation (CDC) was a mainframe and supercomputer firm. CDC was one of the nine major United States computer companies through most of the 1960s; the others were IBM, Burroughs Corporation, DEC, NCR, General Electric, Honeywel ...
HQ in
Minneapolis, Minnesota
Minneapolis () is the largest city in Minnesota, United States, and the county seat of Hennepin County. The city is abundant in water, with thirteen lakes, wetlands, the Mississippi River, creeks and waterfalls. Minneapolis has its origins ...
, Cray management understood his needs and supported his move to a new lab in
Boulder, Colorado
Boulder is a home rule city that is the county seat and most populous municipality of Boulder County, Colorado, United States. The city population was 108,250 at the 2020 United States census, making it the 12th most populous city in Color ...
. Working as an independent consultant at these new Cray Labs, starting in 1980 he put together a team and started on a completely new design. This Lab would later close, and a decade later a new facility in
Colorado Springs
Colorado Springs is a home rule municipality in, and the county seat of, El Paso County, Colorado, United States. It is the largest city in El Paso County, with a population of 478,961 at the 2020 United States Census, a 15.02% increase since ...
would open.
Cray had previously attacked the problem of increased speed with three simultaneous advances: more functional units to give the system higher parallelism, tighter packaging to decrease signal delays, and faster components to allow for a higher clock speed. The classic example of this design is the
CDC 8600
The CDC 8600 was the last of Seymour Cray's supercomputer designs while he worked for Control Data Corporation. As the natural successor to the CDC 6600 and CDC 7600, the 8600 was intended to be about 10 times as fast as the 7600, already the f ...
, which packed four
CDC 7600
The CDC 7600 was the Seymour Cray-designed successor to the CDC 6600, extending Control Data's dominance of the supercomputer field into the 1970s. The 7600 ran at 36.4 MHz (27.5 ns clock cycle) and had a 65 Kword primary memory (with a 6 ...
-like machines based on ECL logic into a 1 × 1 meter cylinder and ran them at an 8 ns cycle speed (125
MHz
The hertz (symbol: Hz) is the unit of frequency in the International System of Units (SI), equivalent to one event (or cycle) per second. The hertz is an SI derived unit whose expression in terms of SI base units is s−1, meaning that one he ...
). Unfortunately, the density needed to achieve this cycle time led to the machine's downfall. The circuit boards inside were densely packed, and since even a single malfunctioning
transistor
upright=1.4, gate (G), body (B), source (S) and drain (D) terminals. The gate is separated from the body by an insulating layer (pink).
A transistor is a semiconductor device used to Electronic amplifier, amplify or electronic switch, switch e ...
would cause an entire module to fail, packing more of them onto the cards greatly increased the chance of failure. Cooling the closely packed individual components also represented a major challenge.
One solution to this problem, one that most computer vendors had already moved to, was to use
integrated circuit
An integrated circuit or monolithic integrated circuit (also referred to as an IC, a chip, or a microchip) is a set of electronic circuits on one small flat piece (or "chip") of semiconductor material, usually silicon. Large numbers of tiny ...
s (ICs) instead of individual components. Each IC included a selection of components from a module pre-wired into a circuit by the automated construction process. If an IC did not work, another one would be tried. At the time the 8600 was being designed the simple
MOSFET
The metal–oxide–semiconductor field-effect transistor (MOSFET, MOS-FET, or MOS FET) is a type of field-effect transistor (FET), most commonly fabricated by the controlled oxidation of silicon. It has an insulated gate, the voltage of which d ...
-based technology did not offer the speed Cray needed. Relentless improvements changed things by the mid-1970s, however, and the
Cray-1
The Cray-1 was a supercomputer designed, manufactured and marketed by Cray Research. Announced in 1975, the first Cray-1 system was installed at Los Alamos National Laboratory in 1976. Eventually, over 100 Cray-1s were sold, making it one of the ...
had been able to use newer ICs and still run at a respectable 12.5 ns (80 MHz). In fact, the Cray-1 was actually somewhat faster than the 8600 because it packed considerably more logic into the system due to the ICs' small size.
Although IC design continued to improve, the physical size of the ICs was constrained largely by mechanical limits; the resulting component had to be large enough to solder into a system. Dramatic improvements in density were possible, as the rapid improvement in
microprocessor
A microprocessor is a computer processor where the data processing logic and control is included on a single integrated circuit, or a small number of integrated circuits. The microprocessor contains the arithmetic, logic, and control circu ...
design was showing, but for the type of ICs used by Cray, ones representing a very small part of a complete circuit, the design had plateaued. In order to gain another 10-fold increase in performance over the Cray-1, the goal Cray aimed for, the machine would have to grow more complex. So once again he turned to an 8600-like solution, doubling the clock speed through increased density, adding more of these smaller processors into the basic system, and then attempting to deal with the problem of getting heat out of the machine.
Another design problem was the increasing performance gap between the processor and
main memory
Computer data storage is a technology consisting of computer components and recording media that are used to retain digital data. It is a core function and fundamental component of computers.
The central processing unit (CPU) of a computer ...
. In the era of the
CDC 6600
The CDC 6600 was the flagship of the 6000 series of mainframe computer systems manufactured by Control Data Corporation. Generally considered to be the first successful supercomputer, it outperformed the industry's prior recordholder, the IBM ...
memory ran at the same speed as the processor, and the main problem was feeding data into it. Cray solved this by adding ten smaller computers to the system, allowing them to deal with the slower external storage (disks and tapes) and "squirt" data into memory when the main processor was busy. This solution no longer offered any advantages; memory was large enough that entire data sets could be read into it, but the processors ran so much faster than memory that they would often spend long times waiting for data to arrive. Adding four processors simply made this problem worse.
To avoid this problem the new design banked memory and two sets of registers (the B- and T-registers) were replaced with a 16
KWord
KWord is a deprecated word processor and a desktop publishing application, part of the KOffice suite. It has been obsoleted by Calligra Words of the Calligra Suite.
History
KWord was created by Reginald Stadlbauer as part of the KOffice projec ...
block of the very fastest memory possible called a ''Local Memory,'' not a cache, attaching the four ''background processors'' to it with separate high-speed pipes. This Local Memory was fed data by a dedicated ''foreground processor'' which was in turn attached to the main memory through a Gbit/s channel per CPU; X-MPs by contrast had 3, for 2 simultaneous loads and a store and Y-MP/C-90s had 5 channels to avoid the
von Neumann bottleneck
The von Neumann architecture — also known as the von Neumann model or Princeton architecture — is a computer architecture based on a 1945 description by John von Neumann, and by others, in the '' First Draft of a Report on the EDVAC''. T ...
. It was the foreground processor's task to "run" the computer, handling storage and making efficient use of the multiple channels into main memory. It drove the background processors by passing in the instructions they should run via eight 16
word
A word is a basic element of language that carries an semantics, objective or pragmatics, practical semantics, meaning, can be used on its own, and is uninterruptible. Despite the fact that language speakers often have an intuitive grasp of w ...
buffers, instead of tying up the existing cache pipes to the background processors. Modern CPUs use a variation of this design as well, although the foreground processor is now referred to as the ''load/store unit'' and is not a complete machine unto its own.
Main memory banks were arranged in quadrants to be accessed at the same time, allowing programmers to scatter their data across memory to gain higher parallelism. The downside to this approach is that the cost of setting up the ''scatter/gather unit'' in the foreground processor was fairly high. Stride conflicts corresponding to the number of memory banks suffered a performance penalty (latency) as occasionally happened in power-of-2 FFT-based algorithms. As the Cray 2 had a much larger memory than Cray 1s or X-MPs, this problem was easily rectified by adding an extra unused element to an array to spread the work out.
Packed circuit boards and new design ideas
Early Cray-2 models soon settled on a design using large circuit boards packed with ICs. This made them extremely difficult to solder together, and the density was still not enough to reach their performance goals. Teams worked on the design for about two years before even Cray himself "gave up" and decided it would be best if they simply canceled the project and fired everyone working on it. Les Davis, Cray's former design collaborator who had remained at Cray headquarters, decided it should be continued at low priority. After some minor personnel movements, the team continued on much as before.
Six months later Cray had his "
eureka
Eureka (often abbreviated as E!, or Σ!) is an intergovernmental organisation for research and development funding and coordination. Eureka is an open platform for international cooperation in innovation. Organisations and companies applying th ...
" moment. He called the main engineers together for a meeting and presented a new solution to the problem. Instead of making one larger circuit board, each "card" would instead consist of a 3-D stack of eight, connected together in the middle of the boards using pins sticking up from the surface (known as "pogos" or "z-pins"). The cards were packed right on top of each other, so the resulting stack was only about 3 inches high.
With this sort of density there was no way any conventional air-cooled system would work; there was too little room for air to flow between the ICs. Instead the system would be immersed in a tank of a new inert liquid from 3M,
Fluorinert
Fluorinert is the trademarked brand name for the line of electronics coolant liquids sold commercially by 3M. As perfluorinated compounds (PFCs), all Fluorinert variants have an extremely high Global Warming Potential (GWP), so should be used wit ...
. The cooling liquid was forced sideways through the modules under pressure, and the flow rate was roughly one inch per second. The heated liquid was cooled using chilled water heat exchangers and returned to the main tank. Work on the new design started in earnest in 1982, several years after the original start date.
While this was going on the
Cray X-MP
The Cray X-MP was a supercomputer designed, built and sold by Cray Research. It was announced in 1982 as the "cleaned up" successor to the 1975 Cray-1, and was the world's fastest computer from 1983 to 1985 with a quad-processor system performance ...
was being developed under the direction of
Steve Chen
Steve Chen (; born August 25, 1978) is a Taiwanese-American Internet entrepreneur who is one of the co-founders and previous chief technology officer of the video-sharing website YouTube. After having co-founded the company AVOS Systems, Inc. a ...
at Cray headquarters, and looked like it would give the Cray-2 a serious run for its money. In order to address this internal threat, as well as a series of newer Japanese Cray-1-like machines, the Cray-2 memory system was dramatically improved, both in size as well as the number of "pipes" into the processors. When the machine was eventually delivered in 1985, the delays had been so long that much of its performance benefits were due to the faster memory. Purchasing the machine really made sense only for users with huge data sets to process.
The first Cray-2 delivered possessed more physical memory (256 MWord) than all previously delivered Cray machines combined. Simulation moved from a 2-D realm or coarse 3-D to a finer 3-D realm because computation did not have to rely on slow virtual memory.
Uses and successors
The Cray-2 was predominantly developed for the
United States
The United States of America (U.S.A. or USA), commonly known as the United States (U.S. or US) or America, is a country primarily located in North America. It consists of 50 states, a federal district, five major unincorporated territorie ...
Departments of
Defense
Defense or defence may refer to:
Tactical, martial, and political acts or groups
* Defense (military), forces primarily intended for warfare
* Civil defense, the organizing of civilians to deal with emergencies or enemy attacks
* Defense industr ...
and
Energy
In physics, energy (from Ancient Greek: ἐνέργεια, ''enérgeia'', “activity”) is the quantitative property that is transferred to a body or to a physical system, recognizable in the performance of work and in the form of heat a ...
. Uses tended to be for
nuclear weapon
A nuclear weapon is an explosive device that derives its destructive force from nuclear reactions, either fission (fission bomb) or a combination of fission and fusion reactions ( thermonuclear bomb), producing a nuclear explosion. Both bom ...
s research or
oceanographic
Oceanography (), also known as oceanology and ocean science, is the scientific study of the oceans. It is an Earth science, which covers a wide range of topics, including ecosystem dynamics; ocean currents, waves, and geophysical fluid dynamics ...
(
sonar
Sonar (sound navigation and ranging or sonic navigation and ranging) is a technique that uses sound propagation (usually underwater, as in submarine navigation) to navigation, navigate, measure distances (ranging), communicate with or detect o ...
Lawrence Livermore National Laboratory
Lawrence Livermore National Laboratory (LLNL) is a federal research facility in Livermore, California, United States. The lab was originally established as the University of California Radiation Laboratory, Livermore Branch in 1952 in response ...
for unclassified energy research. It also found its way into civil agencies (such as
NASA Ames Research Center
The Ames Research Center (ARC), also known as NASA Ames, is a major NASA research center at Moffett Federal Airfield in California's Silicon Valley. It was founded in 1939 as the second National Advisory Committee for Aeronautics (NACA) laborat ...
), universities, and corporations worldwide. For example,
Ford
Ford commonly refers to:
* Ford Motor Company, an automobile manufacturer founded by Henry Ford
* Ford (crossing), a shallow crossing on a river
Ford may also refer to:
Ford Motor Company
* Henry Ford, founder of the Ford Motor Company
* Ford F ...
and
General Motors
The General Motors Company (GM) is an American Multinational corporation, multinational Automotive industry, automotive manufacturing company headquartered in Detroit, Michigan, United States. It is the largest automaker in the United States and ...
both used the Cray-2 for processing complex
Finite Element Analysis
The finite element method (FEM) is a popular method for numerically solving differential equations arising in engineering and mathematical modeling. Typical problem areas of interest include the traditional fields of structural analysis, heat ...
models of car bodyshells, and for performing virtual crash testing of bodyshell components prior to production.
The Cray-2 would have been superseded by the
Cray-3
The Cray-3 was a vector supercomputer, Seymour Cray's designated successor to the Cray-2. The system was one of the first major applications of gallium arsenide (GaAs) semiconductors in computing, using hundreds of custom built ICs packed into ...
, but due to development problems only a single Cray-3 was built and it was never paid for. The spiritual descendant of the Cray-2 is the
Cray X1
The Cray X1 is a non-uniform memory access, vector processor supercomputer manufactured and sold by Cray Inc. since 2003. The X1 is often described as the unification of the Cray T90, Cray SV1, and Cray T3E architectures into a single machine. The ...
, offered by
Cray
Cray Inc., a subsidiary of Hewlett Packard Enterprise, is an American supercomputer manufacturer headquartered in Seattle, Washington. It also manufactures systems for data storage and analytics. Several Cray supercomputer systems are listed ...
.
Comparison to later computers
In 2012, Piotr Luszczek (a former doctoral student of
Jack Dongarra
Jack Joseph Dongarra (born July 18, 1950) is an American computer scientist and mathematician. He is the American University Distinguished Professor of Computer Science in the Electrical Engineering and Computer Science Department at the Unive ...
), presented results showing that an
iPad 2
The iPad 2 is a tablet designed, developed and marketed by Apple Inc. Compared to the first iPad, as the second model in the iPad line, it gained a faster dual core A5 processor, a lighter build structure, and was the first iPad to feature ...
matched the historical performance of the Cray-2 on an embedded LINPACK benchmark.
Trivia
Due to the use of liquid cooling, the Cray-2 was given the nickname "Bubbles", and common jokes around the computer made reference to this unique system. Gags included "No Fishing" signs, cardboard depictions of the
Loch Ness Monster
The Loch Ness Monster ( gd, Uilebheist Loch Nis), affectionately known as Nessie, is a creature in Scottish folklore that is said to inhabit Loch Ness in the Scottish Highlands. It is often described as large, long-necked, and with one or mor ...
rising out of the heat exchanger tank, plastic fish inside the exchanger, etc. The power consumption of the Cray-2 was 150–200 kW. Research conducted at the Lawrence Livermore National Laboratory in the early 1990s indicated that to a limited extent the perfluorinated polyether used to cool Cray-2 circuits would break down to form the extremely toxic gas
perfluoroisobutylene
Perfluoroisobutene (PFIB) is the perfluorocarbon counterpart of the hydrocarbon isobutene and has the formula (CF3)2C=CF2. An alkene, it is a colorless gas that is notable as a highly toxic perfluoroalkene. Few simple alkenes are as toxic.
Safet ...
. At the time, Cray had created a poster showing the transparent "bubble chamber" that the cooling fluid was run through for visual effect, with a spill of the same material glistening on the floor—the joke was that if this actually occurred, the facility would have to be evacuated.Kelly, R. J., Personal Experience The manufacturer of the liquid developed a scrubber that could be placed in line with the pump that would catalytically degrade this toxic breakdown product.
Each vertical stack of logic modules sat above a stack of power modules which powered 5 volt
busbar
In electric power distribution, a busbar (also bus bar) is a metallic strip or bar, typically housed inside switchgear, panel boards, and busway enclosures for local high current power distribution. They are also used to connect high volt ...
s, each of which delivered about 2200 amps. The Cray-2 was powered by two motor-generators, which took in 480 V
three-phase
Three-phase electric power (abbreviated 3φ) is a common type of alternating current used in electricity generation, Electric power transmission, transmission, and Electric power distribution, distribution. It is a type of polyphase system empl ...
.
See also
*
History of supercomputing
The term supercomputing arose in the late 1920s in the United States in response to the IBM tabulators at Columbia University. The CDC 6600, released in 1964, is sometimes considered the first supercomputer. However, some earlier computers were c ...