The STAR-100 was a vector supercomputer designed, manufactured, and marketed by Control Data Corporation (CDC). It was one of the first machines to use a vector processor to improve performance on appropriate scientific applications.
The name STAR was a construct of the words STrings and ARrays. The 100 came from 100 million floating point operations per second (MFLOPS), the speed at which the machine was designed to operate. The computer was announced very early during the 1970s and was supposed to be several times faster than the CDC 7600, which was then the world's fastest supercomputer with a peak performance of 36 MFLOPS. On August 17, 1971, CDC announced that General Motors had placed the first commercial order for a STAR-100.
A number of basic design features of the machine meant that its real world performance was much lower than expected when first used commercially in 1974, and was one of the primary reasons CDC was pushed from its former dominance in the supercomputer market when the Cray-1 was announced in 1975.
In general organization, the STAR was similar to CDC's earlier supercomputers, where a simple CPU was supported by a number of peripheral processors that offloaded housekeeping tasks and allowed the CPU to crunch numbers as quickly as possible. In the STAR, both the CPU and peripheral processors were deliberately further simplified, to lower the cost and complexity of implementation. The STAR also differed from the earlier designs by being based on a 64-bit architecture instead of 60-bit, a side effect of the increasing use of 8-bit ASCII processing. Also unlike previous machines, the STAR made heavy use of microcode and also supported a virtual memory capability.
The main innovation in the STAR was the inclusion of instructions for vector processing. These new and more complex instructions approximated what was available to users of the APL programming language and operated on huge vectors that were stored in consecutive locations in the main memory. The CPU was designed to use these instructions to set up additional hardware that fed in data from the main memory as quickly as possible. For instance, a program could use single instruction with a few parameters to add all the elements in two vectors that could be as long as 65,535 elements. The CPU only had to decode a single instruction, set up the memory hardware, and start feeding the data into the math units. As with instruction pipelines in general, the time needed to complete any one instruction was no better than it was before, but since the CPU was working on a number of instructions at once (or in this case, data points) the overall performance dramatically improves due to the assembly line nature of the task.
The main memory had a capacity of 65,536 superwords (SWORDs), which are 512-bit words. The main memory was 32-way interleaved to pipeline memory accesses. It was constructed from core memory with an access time of 1.28 μs. The main memory was accessed via a 512-bit bus, controlled by the storage access controller (SAC), which handled requests from the stream unit. The stream unit accesses the main memory through the SAC via three 128-bit data buses, two for reads, and one for writes. Additionally, there is a 128-bit data bus for instruction fetch, I/O, and control vector access. The stream unit serves as the control unit, fetching and decoding instructions, initiating memory accesses on the behalf of the pipelined functional units, and controlling instruction execution, among other tasks. It also contains two read buffers and one write buffer for streaming data to the execution units.
The STAR-100 has two pipelines where arithmetic is performed. The first pipeline contains a floating point adder and multiplier, whereas the second pipeline is multifunctional, capable of executing all scalar instructions. It also contains a floating point adder, multiplier, and divider. Both pipelines are 64-bit for floating point operations and are controlled by microcode. The STAR-100 can split its floating point pipelines into four 32-bit pipelines, doubling the peak performance of the system to 100 MFLOPS at the expense of half the precision.
The STAR-100 uses I/O processors to offload I/O from the CPU. Each I/O processor is a 16-bit minicomputer with its own main memory of 65,536 words of 16 bits each, which is implemented with core memory. The I/O processors all share a 128-bit data bus to the SAC.
Real world performance, users and impact
The STAR-100's architecture meant that its real world performance was a fraction of its peak performance. This was due to a number of reasons. Firstly, the vector instructions, being memory-to-memory, had a relatively long startup time, since the pipeline from the memory to the functional units was very long. In contrast to the register-based pipelined functional units in the 7600, the STAR pipelines were much deeper. The problem was compounded by the fact that the STAR had a slower cycle time than the 7600 (40 ns vs 27.5 ns). So the vector length needed for the STAR to run faster than the 7600 occurred at about 50 elements; if the loops were working on data sets with fewer elements, the cost of setting up the vector pipeline was higher than the savings provided by the vector instruction(s).
When the machine was released in 1974, it quickly became apparent that the general performance was nowhere near what people expected. Very few programs can be effectively vectorized into a series of single instructions; nearly all calculations will rely on the results of some earlier instruction, yet the results had to clear the pipelines before they could be fed back in. This forced most programs to hit the high setup cost of the vector units, and generally the ones that did "work" were extreme examples. Making matters worse was that the basic scalar performance was sacrificed in order to improve vector performance. Any time that the program had to run scalar instructions, the overall performance of the machine dropped dramatically. (See Amdahl's Law.)
Two STAR-100 systems were eventually delivered to the Lawrence Livermore National Laboratory and one to NASA Langley Research Center. In preparation for the STAR deliveries, LLNL programmers developed a library of subroutines, called STACKLIB, on the 7600 to emulate the vector operations of the STAR. In the process of developing STACKLIB, they found that programs converted to use it ran faster than they had before, even on the 7600. This placed further pressures on the performance of the STAR.
The STAR-100 was a disappointment to everyone involved, and Jim Thornton, the chief designer, left CDC to form Network Systems Corporation. An updated version was later released in 1979 as the Cyber 203, followed by the Cyber 205 in 1980, but by this point systems from Cray Research with considerably higher performance were on the market. The failure of the STAR led to CDC being pushed from its former dominance in the supercomputer market, something they tried to address with the formation of ETA Systems in September 1983.
- P.M. Kogge, The Architecture of Pipelined Computers, Taylor & Francis, 1981, pp. 162–164.
- R.W. Hockney and C.R. Jesshope, Parallel Computers 2: Architecture, Programming and Algorithms, Adam Hilger, 1988, p. 21.
- R.G. Hintz and D.P. Tate, "Control Data STAR-100 processor design," Proc. Compcon, 1972, pp. 1–4.
- P.B. Schneck, Supercomputer Architecture, Kluwer Academic, 1987, pp. 99–118.
- Neil R. Lincoln with 18 Control Data Corporation (CDC) engineers on computer architecture and design, Charles Babbage Institute, University of Minnesota. Engineers include Robert Moe, Wayne Specker, Dennis Grinna, Tom Rowan, Maurice Hutson, Curt Alexander, Don Pagelkopf, Maris Bergmanis, Dolan Toth, Chuck Hawley, Larry Krueger, Mike Pavlov, Dave Resnick, Howard Krohn, Bill Bhend, Kent Steiner, Raymon Kort, and Neil R. Lincoln. Discussion topics include CDC 1604, CDC 6600, CDC 7600, CDC 8600, CDC STAR-100 and Seymour Cray.