IBM Future Systems project

From Wikipedia, the free encyclopedia

In the late 1960s and early 1970s, IBM considered a radical redesign of their computing environment to take advantage of the much lower cost of computer circuitry expected in the 1980s. In September 1971, the IBM Future Systems project (FS) was officially started as a merger of several other research projects in various IBM locations. IBM had been making most of their profit on the hardware, bundling support software along with their systems. They recognized that the cost of developing software was growing phenomenally, and they hoped that a new architecture that took advantage of the cheaper hardware would simplify software development and would make a major reduction in total costs both for IBM and for their customers.

One design principle of FS was a "single-level store" which extended the idea of virtual memory to cover persistent data. Working memory, files, and databases were all accessed in a uniform way by an abstraction of the notion of address. Therefore, programmers would not have to be concerned whether the object they were trying to access was in memory or on the disk. This and other planned enhancements were expected to make programming easier and thereby reduce the cost of developing software.

Another principle was the use of very high-level complex instructions to be implemented in microcode. As an example, one of the instructions, CreateEncapsulatedModule, was a complete linkage editor. Other instructions were designed to support the internal data structures and operations of programming languages such as FORTRAN, COBOL, and PL/I. In effect, FS was designed to be the ultimate complex instruction set computer (CISC). Meanwhile, John Cocke, one of the chief designers of early IBM computers, began a research project to design the first reduced instruction set computer (RISC). In the long run, the RISC architecture, which eventually evolved into IBM's Power and Power PC architecture, proved to be much faster and vastly cheaper to implement.

Three implementations of the FS archtecture were planned: the top-of-line model was being designed in Poughkeepsie, NY, where IBM's largest and fastest computers were built; the middle model was being designed in Endicott, NY, which had responsibility for the mid-range computers; and the smallest model was being designed in Rochester, MN, which had the responsibility for IBM's small business computers.

The FS project was killed in 1975, primarily because of the poor performance of its largest implementation, but it was also marred by protracted internal arguments about various technical aspects, including internal IBM debates about the merits of RISC vs. CISC designs. The complexity of the instruction set was another obstacle, which was considered "incomprehensible" by IBM's own engineers. The FS project was finally terminated when simulations showed that the execution of native FS instructions on the high-end machine was slower than the System/370 emulator on the same machine.

Although the FS project as a whole was killed, a slightly simplified version of the architecture continued to be developed in Rochester for the smallest of the three machines. It was finally released as the IBM System/38, which proved to be a good design for ease of programming, but it was woefully underpowered. The AS/400 inherited the same architecture, but with performance improvements. Ironically, the current version of the AS/400 runs as a purely software implementation on top of the same Power chip that evolved from John Cocke's RISC machine. The only difference between the CPU used for IBM's Unix systems (which run the AIX or Linux operating systems) and the CPU used for the AS/400 is one bit per 64-bit word to flag memory locations that contain the special addresses.

Besides System/38 and the AS/400, which inherited almost all of the FS architecture, bits and pieces of Future Systems technology were incorporated in the following parts of IBM's product line:

  • the 3081 mainframe computer, which was essentially the System/370 emulator designed in Poughkeepsie, but with the FS microcode removed
  • the 3800 laser printer, and some machines that would lead to the 3279 terminal and GDDM
  • the 3850 automatic magnetic library
  • the 8100 mid-range computer, which was based on a CPU called the Universal Controller, which had been intended for FS input/output processing
  • the notion of automatic file migration without loss of identity would be used by various systems, including the Macintosh HFS
  • network enhancements concerning VTAM and NCP

[edit] Sources

[edit] External links

Tight security prevents a potential thief from stealing a system design. But good communication is necessary to design a system that is worth stealing. The recent version of the RIPON architecture has been issued in 15 separate, registered confidential documents. A programmer who gets authorization to learn about the addressing structure has to demonstrate a separate need to know to learn the instruction set. The avowed aim of all this red tape is to prevent anyone from understanding the whole system; this goal has certainly been achieved.

Retrieved from "http://en.wikipedia.org../../../i/b/m/IBM_Future_Systems_project_550b.html"
In other languages