CRI Cray-1A S/N 14

Cray Research, Inc.
Clock Speed: 
Dates Used: 
Monday, May 2, 1983 to Wednesday, October 1, 1986
Microprocessor Peak Teraflops: 
Memory (terabytes): 
Number of Processors: 
Electrical Power Consumption: 
115.00 kW
Paired with: 

Because of growth in user demand, NCAR's aging Control Data Corporation (CDC) 7600 was replaced by low-cost (previously-owned) Cray Research, Inc. (CRI) Cray-1A, serial number 14, in May 1983.

SCD and the NCAR scientific community had engaged in a lengthy debate over whether it was appropriate to bring in a fast scalar processor (because of the heavy data processing component of the workload) or to get a second Cray-1A.  Proponents of the scalar processor felt that a fast scalar processor with good I/O could better handle tape I/O and mass store archive — i.e., it would be better suited for data processing, which was a significant percentage of the workload. Opponents felt that the Cray would provide more numerical computing, even though it might be inefficiently used for the data processing necessary to support the atmospheric sciences.  In the end, the scalar processor lost out to the second Cray-1A because both the price and its abilities in the modeling area were superior.

NCAR's Cray-1A, S/N 14, was configured the same as NCAR's first Cray-1A, S/N 3.  It had a 12.5-nanosecond clock, eight 64-element vector registers, 1 million 64-bit words (8 megabytes) of high-speed memory and sixteen DD-19 "high-speed" disk drives, each with a capacity of three-hundred megabytes and a transfer rate of 4.5 megabytes per second. The Cray-1A could chain floating-point vector add and mutliply instructions together to produce two floating point operations (FLOPs) per clock; thus the Cray-1A had a peak speed of 160 megaflops.

NCAR's second Cray-1A, S/N 14, was obtained with U.S. Department of Energy funding. It was placed into service in May 1983 and decommissioned October 1986 to make way for NCAR's first multi-processor supercomputer, the CRI Cray X-MP.