Cray the man, Cray the computer
May 21 2019: As Cray the independent supercomputer entity fades away into history after its acquisition by HP Enterprises, we recall the Man and the Machine -- both icons of computing.
SEYMOUR CRAY (1925-1996)
Seymour Cray, recognized as the "father of supercomputing," built the iconic Cray-1 and led the supercomputing industry for decades.
Recognized as “the father of supercomputing” and credited with single-handedly creating and leading the high performance computing industry for decades, Seymour R. Cray was a dedicated and focused computer engineer, regarded by some as a true maverick and “serial” pioneer. Jokingly, he would refer to himself as “an overpaid plumber.”
The beginnings
Born Sept. 28, 1925, in Chippewa Falls, Wisconsin, Seymour had a fascination with electronics and electrical devices from boyhood. In high school the young Cray preferred to be in the electrical engineering laboratory as much as possible. “I was one of those nerds before the name was popular,” he told a Smithsonian Institution interviewer. “I spent all my time in the electrical engineering laboratory and not enough time socializing.”
Following graduation from high school in 1943, he joined the U.S. Army, serving in an infantry communications platoon. He arrived in Europe the day after D-Day and saw action in the Battle of the Bulge campaign. Later he served in the Pacific theater in the Philippine Islands.
After returning from the war, Seymour earned a bachelor of science degree in electrical engineering from the University of Minnesota, followed by a master’s degree in applied mathematics. Shortly thereafter, he joined a new company called Engineering Research Associates (ERA). Housed in an old glider factory in St. Paul, Minnesota, ERA built specialized cryptographic equipment for the U.S. Navy. Seymour worked the gamut of computer technologies, ranging from vacuum tubes and magnetic amplifiers to transistors. It was also here that he had the opportunity to design his first computer, the 1103.
Seymour’s passion for building scientific computers led him to help start Control Data Corporation (CDC) in 1957. There he realized his goal of building the fastest scientific computer ever, the CDC 1604. It was the first fully transistorized commercial computer — he had eliminated vacuum tubes. Release of the CDC 6600, which was considered the world’s first actual supercomputer, followed in 1963. The CDC 6600 was capable of 9 megaflops (million floating-point operations per second) of processing power and was cooled by Freon. The CDC 7600 was next. Running at 40 megaflops, it in turn became the world’s fastest supercomputer.
In 1968 Seymour began work on the CDC 8600, designed for greater parallelism. It employed four processors, all sharing one memory. In 1968, he was awarded the W.W. McDowell Award by the American Foundation of Information Processing Societies for his work in the computer field.Seymour served as a director of CDC from 1957 to 1965 and was senior vice president at the time of his departure in 1972, when CDC decided to phase out development of large-scale scientific computers. That year he founded Cray Research Inc. in Chippewa Falls, Wisconsin.
Vector processing is born
The signature Cray-1 vector supercomputer established a world standard in supercomputing when it was unveiled in 1976. Integrated circuits replaced transistors, and the Cray-1 delivered 170 megaflops of processing speed.
In the years following CDC's founding, Seymour relinquished the company's management reins to devote more time to computer development. From 1972 to 1977 he served as director, chief executive officer and president of the company. In October 1977, he left the presidency of Cray Research, but remained chief executive officer and became chairman of the board. In 1980, he resigned as chief executive officer, and in 1981, Cray stepped aside as chairman of the board. As a full-time independent contractor, he devoted himself to the Cray-2 project.
In 1985 the Cray-2 computer system moved supercomputing forward yet again, breaking the gigaflops (1,000 megaflops) barrier. With the Cray-3, Seymour turned his attention to the possibilities of gallium arsenide processing chips and reduced packaging. But after experimenting with gallium arsenide as an ultrafast semiconductor material, Seymour returned to the use of silicon chips and introduced Flourinert, an inert fluorocarbon liquid, as a coolant.
In 1989 Seymour left Cray Research to form Cray Computer Corporation (CCC), based in Colorado Springs, Colorado. Here he began work on the Cray-4. CCC closed its doors in 1995 due to financial pressures.|
In 1996 Seymour started SRC Computers, Inc., and started the design of his own massively parallel supercomputer, concentrating on the communications and memory performance. Tragically, on Oct. 5, 1996, at the age of 71, Seymour Cray passed away in Colorado Springs from injuries suffered in a car accident two weeks earlier.
Cray, the supercomputer
Acquired by HPE: May 17 2019 marks a significant milestone in Crfay history, as the company signed a definitive agreement to be acquired by Hewlett Packard Enterprise (HPE).
Since the founding of Cray Research in 1972 Cray has focused on building some of the fastest supercomputers on the planet so that leading visionaries can keep asking questions that challenge the limits of possibility. From the first Cray-1 in 1976, to the Cray T3E in 1996, to the Cray XC series currently deployed at over 100 organizations around the world, Cray has been a leader in the supercomputing industry for over four decades. Today, Cray supercomputers power over 80% of the world’s global weather centres ( India uses 2 Cray SC 40 computers for weather prediction) , perform vital upstream exploration in the energy industry, design, test and perform safety analysis on cars (from a Formula 1 race car to your family sedan) and help research centers around the world achieve breakthroughs that change our world.
Exascale Era
Today the industry is at the threshold of a new era in the industry – the Exascale era. The promise of Exascale is more than a single gigantic supercomputer or a performance milestone. It is the ability to take advantage of the explosion of disparate data with increasingly complex modeling, simulation, analytics and artificial intelligence to drive new discovery, innovation and insights. This combination of data and compute-intensive workloads operating at extreme scale, and often in real-time, exceeds the capabilities of today’s datacenter infrastructure. Exascale computing systems and technologies will allow scientists and engineers to overcome these barriers and produce the world’s next breakthroughs.
Shasta and Slingshot
Cray began developing the Shasta supercomputer and Slingshot interconnect several years ago. The Shasta supercomputing architecture is an entirely new design, built from the ground up to address the needs of the Exascale era. It enables a diversity of processor technologies, supports converged, heterogeneous workloads, eliminates the distinction between supercomputers and clusters, and fuses the performance and scale of a supercomputer with the productivity of the cloud. Slingshot is different than any interconnect Cray or anyone else, has ever built. In addition to high speed and low latency, Slingshot incorporates intelligent features that enable diverse workloads to run simultaneously across the system. It includes novel adaptive routing, quality-of-service and congestion management capabilities while providing full Ethernet compatibility. Shasta and Slingshot are the basis of three recent seminal wins at the U.S. Department of Energy, powering a pre-Exascale supercomputer as well as the first two Exascale systems in the United States. Shasta hasn’t even started shipping yet and is quickly approaching $1B in new wins!
( source: Cray blog and website collaterals)