In 1974, the outlook for computational capability beyond NCAR's Control Data Corporation (CDC) 7600 was not good. The CDC STAR, the Texas Instruments ASC, and the ILLIAC IV all seemed unsuitable in the NCAR environment. In 1974, two SCD staff members made a trip to Cray Research, Inc. (which had been founded two years by Seymour Cray when he left Control Data Corporation) to see what Cray was up to.
As computer architect at Cray Research, Cray provided the technical vision of a CRAY-1 computer that was twice as fast as the CDC 7600 and demonstrated balanced scalar and vector performance. The computer was also innovative in its use of reciprocal approximation for division. Although the CRAY-1A was still only partially built, the design reflected a simplicity not found in the other computers. SCD felt that although many technical and financial objections had to be overcome, the CRAY-1A would be a viable upgrade to the CDC 7600.
By 1975, NCAR's 7600 was straining under a severe overload. SCD was oversubscribed; turnaround time had become intolerable. A request for proposal (RFP) was issued, resulting in an order for a CRAY-1A. While serial number 1 of the CRAY-1 computer system had been shipped to the Los Alamos National Laboratory in 1976 for a six-month trial period, NCAR was Cray Research's first official customer.
On July 11, 1977, the CRAY-1A, serial number 3, was delivered to NCAR. The system cost was $8.86 million ($7.9 million plus $1 million for the disks).
The supercomputer weighed 5-1/2 tons, arrived in two refrigerated electronic vans, and needed more than 30 construction workers, engineers, and helpers to move it into the computer room. NCAR accepted the CRAY-1A in December. It was the first CRAY-1A to go into production, and upon its acceptance, Cray Research became a profitable company.
The CRAY-1A was very stable compared to the CDC 7600, representing a significant improvement in mean-time-to-failure rates. In good times, the 7600 hardware or software had failed at least once a day, often four to five or more times, wheras the CRAY would run for several days and most often failed only because of disk problems.
The CDC 7600 was used as a front end to the CRAY-1A. Incoming work flowed through the 7600, which also retrieved necessary archival files for use on the Cray from the TBM mass storage system. Users migrated their jobs to the Cray rather slowly at first, and continued to use the 7600 for data handling chores.
The CRAY-1A had a 12.5-nanosecond clock, 64 vector registers, and 1 million 64-bit words of high-speed memory. It could execute over 80 megaflops, but higher rates were possible with programs taking advantage of the vector features of the computer. Overall, its throughput was estimated at about 4.5 times the CDC 7600.
In 1978, the first standard software package consisting of the Cray Operating System (COS), the first automatically vectorizing Fortran compiler (CFT), and the Cray Assembler Language (CAL) were introduced.
The CRAY-1A was particularly adapted to the needs of the scientific community, permitting advances in modeling climate and severe storms.
This CRAY-1A was decommissioned on 27 Janury 1989 and powered off on February 1 after 12 years of service.