Showing papers on "Systems architecture published in 1971"
11 Nov 1971
TL;DR: It is very difficult to find a decomposition of a DBS which can be used to describe the architectural requirements of all these objectives, so the term "DBS architecture" should always specify very carefully his viewpoint (i.e.,the decomposition he has chosen and his goals in choosing it).
Abstract: The term "architecture" in the title suggests that a data base system (DBS),like any other system,can be decomposed into parts having generally different tasks and being interrelated according to a certain structure! it is just this structure or organization of parts which is usually meant by "architecture". The first problem which arises when studying the architecture of a system is the one of deciding how to decompose the system (which may be existing in the real world or still at the design stage)! this decision depends on the particular viewpoints and goals of the people who make it. This is also the case of a DBSs if we consider,for instance,the basic objectives of a DBS according to the Joint GUIDE-SHARE Report on "Data Base Management System Requirements", which are data independence,data relatability, data non-redundancy,data integrity,security,performance and compatibility, we can easily see that it is very difficult to find a decomposition of a DBS which can be used to describe the architectural requirements of all these objectives. Therefore,when using the term "DBS architecture" one should always specify very carefully his viewpoint (i.e.,the decomposition he has chosen and his goals in choosing it). As an example,we will dry to study the influence of the independence objective on the architecture of a DBS. Instead of decomposing an existing system,we will start from a non-independent,rudimentary DBS,and see what parts or features have to be added to it in order to make it independent. The two basic ingredients of a DBS are the data to be stored (the "data base" itself) and a data storing and processing systu (the "hardware").
3 citations
TL;DR: The MULTIPAC is a central data system developed for deep-space probes with the distinctive feature that it may be repaired during flight via command and telemetry links by reprogramming around the failed unit.
Abstract: The MULTIPAC is a central data system developed for deep-space probes with the distinctive feature that it may be repaired during flight via command and telemetry links by reprogramming around the failed unit. The computer organization uses pools of identical modules which the program organizes into one or more computers called processors. The interaction of these modules is dynamically controlled by the program rather than hardware. In the event of a failure, new programs are entered which reorganize the central data system with a somewhat reduced total processing capability aboard the spacecraft. As an example of one MULTIPAC configuration, a 16-watt system with 12 288 words of memory would have extensive data processing capability for variable data formatting, data sampling, converting analog information from experiments, and performing data reduction on experimental data to improve information transfer on a limited capacity telemetry channel. Emphasis is placedon the evolution of the system architecture and the final overall system design rather than the specific logic design.
1 citations
TL;DR: A new flight control system architecture is emerging in which the computer and the inertial system play major roles and some potential improvements in Air Traffic Control stemming from the utilization of inertial data are discussed.
Abstract: Significant improvements in inertial system performance coupled with reductions in cost are anticipated during this decade as a result of low-cost, automated, precision-production techniques. This trend is also apparent in airborne digital computer technology. As a result, a new flight control system architecture is emerging in which the computer and the inertial system play major roles. This paper describes the emerging system architecture and discusses some potential improvements in Air Traffic Control stemming from the utilization of inertial data.
16 Nov 1971
TL;DR: The direct impact of Large Scale Integration on minicomputer system architecture has been and will continue to be evolutionary and incremental, not revolutionary.
Abstract: The direct impact of Large Scale Integration (LSI) on minicomputer system architecture has been and will continue to be evolutionary and incremental, not revolutionary.