Showing papers on "Overhead (computing) published in 1981"

Local-Area Subnetworks: A Performance Comparison

Abstract: This paper provides a comparative evaluation of the performance of ring and bus systems constituting subnetworks of local-area networks. Performance is measured in terms of the delaythroughput characteristics. Systems investigated include token-controlled and slotted rings as well as random-access buses (CSMA with collision detection) and ordered-access buses. The investigation is based on analytic models which describe the various topologies and access mechanisms to a sufficient level of detail. The paper includes a comprehensive discussion of how the performance of the different networks is affected by system parameters like transmission rate, cable length, packet lengths, and control overhead.

IBM System/38 support for capability-based addressing

Abstract: The IBM System/38 provides capability-based addressing. This paper describes how support is divided among architectural definition, microcode, and hardware to minimize overhead for this function.

Mathematical verification of Dubanton's simplified calculation of overhead transmission line parameters and its physical interpretation

Abstract: For the calculation of overhead transmission line impedances with earth return Dubanton has given explicit formulae based on the assumption, that the earth return current is concentrated in a plane being in a fictitious complex depth. In this paper the authors give the mathematical basis started from Carson's formulae and the physical interpretation of this heuristic method.

Line protocol for communication system

Abstract: In a communication system, a line protocol format with a variable bit rate and low bit overhead provides for the high integrity, synchronous exchange of digital signal information between master and slave processing units, with master processing unit controlling the line protocol.

Program optimization based on a non-procedural specification

Abstract: : This dissertation deals with two related problems: development of a methodology for achieving memory and computation efficiency of computer programs, and the use of this methodology in very high-level programming and associated automatic program generators. Computer efficiency of programs has many aspects. Usually additional memory saves computation by avoiding the need to recompute certain variables. Our emphasis has been on reducing memory use by variables sharing memory space, without requiring recomputation. It will be shown that this also reduces computation overhead. The most significant savings are due to sharing memory in iterative steps. This is the focus of the reported research.

Dynamic rerouting tag schemes for the augmented data manipulator network

Abstract: The augmented data manipulator (ADM) is a multistage interconnection network designed for large-scale, parallel processing systems. This paper is an extension of an earlier work in which the use of the inverse ADM (IADM) network in an MIMD environment was investigated. Dynamically rerouting messages to avoid busy or faulty links is explored for both the ADM and IADM networks. Several schemes are presented. In some cases, there is no increase in tag overhead, but the switching elements are more complex. In other cases, the size of the routing tag is increased by one bit, but the switching elements are not as complex. A new broadcasting capability is developed that allows one processor to send a message to any number of other processors (with some restriction on the destination addresses). Finally, a scheme for dynamically rerouting a broadcast message is presented.

On the use of data-flow techniques in database machines

Abstract: The past decade has seen a number of design efforts in the area of database machines. Research has shown that all of the major designs suffer from some flaw leading to the inefficient execution of one or more operations. In this thesis we show that the lack of systematic study of the algorithms to be used by an architecture before a hardware design is picked is the reason for these flawed designs. We then consider a number of possible algorithms for all the relational algebra operators and introduce a new design based on a group of these. The proposed machine utilizes a local network communication mechanism and employs a data-flow strategy for query processing. Previous research has shown both advantages and disadvantages of using a data-flow query processing strategy. In particular, it was shown that data movement between the mass storage devices and processors is minimized at the expense of additional control messages. In this design we show how such a strategy can be employed without the large control overhead. We also consider the problem of associating logic with a disk for the implementation of certain operations "on the fly". Three design approaches are examined and compared. It is shown how an associative disk can be incorporated into a database that supports both on-the-disk-and off-the-disk processing.

Copying operands versus copying results: A solution to the problem of large operands in FFP'S

Abstract: In functional programming languages with reduction semantics, operators “use up” their operands to produce their results. This makes it difficult to execute efficiently certain computations, such as one in which several operators are applied—in succession or in parallel—to a large operand. The problem is that providing each operator with a separate copy of the large operand is a costly operation in most computer models.This paper proposes a solution to this problem in the context of a cellular computer that directly executes FFPs. The operators involved are applied in succession to the large operand, and only their results (with the exception of that of the last operator applied) need be moved. Providing each operator with a fresh copy of the large operand incurs no overhead in time. The proposed solution often allows one to avoid unproductive copying, and to suppress parallelism when it does not pay.The functional forms conditional, WHILE loop and construction are among the examples discussed. For example, when executing the conditional usually both the predicate and one of the “arms” of the conditional are applied to the operand. Since the result of the predicate computation is small, the overhead in the execution time of the conditional is negligible.A recursive matrix multiplication program described by Backus uses conditional and construction extensively. The proposed implementation technique reduces the execution time of this program on the cellular computer in question from O(n3) to O(n2).

Image Processing Unit Hardware Implementation

Abstract: Conventional digital computers are inefficient for even simple local image processing operations in terms of cost-effectiveness Image processing by serial computers requires a large amount of computing time Programs and data are stored in the same memory and all operations are serially executed in the so-called “von Neuman” architecture, even though image processing could usually be performed mostly in parallel Two-dimensional image data require a large amount of memory storage and usually exceed the main memory capacity This results in much overhead time transferring image data between the main memory and secondary storage, eg, magnetic disk Therefore, we have elected to implement cost-effective image processing by developing special hardware optimized to overcome the above problems

An Approach to a Calculation-minimized Hidden Line Algorithm.

Abstract: Hidden line algorithms based only on picture primitives, cannot recognize the areas of a picture which are completely visible or invisible. By testing each primitive of these areas they produce an overhead of calculation. Moreover, they waste time by first calculating the hidden lines explicitely and then displaying the remaining edges. This paper describes a method, which rather computes the visible parts of a picture, than excludes the invisible ones. Furthermore an approach to recognize complete visible areas instead of single visible edges is made. A comparison with other techniques will show the qualitatively better calculation rate of the new method.

Device for distinguishing aircraft flying overhead

Abstract: This device is used for distinguishing between aircraft flying overhead and rolling or starting aircraft. This is intended to prevent unwanted ignition of weapons, for example ground mines, in the case of aircraft flying overhead. The device has a sound pickup and bandpass filters which are tuned to characteristic frequency bands. To prevent false firings reliably in a simple manner, it is proposed that a sound pickup supplies input signals for two bandpass filters (2, 3), one of which is a high-pass and the other a low-pass filter. The bandpass filters form mean or RMS values (TP, HP) of the signal components and these values are first divided by one another in a device (6), a quotient Q APPROX HP DIVIDED TP being formed. It is then found whether the quotient Q is above a critical value in which case a signal preventing the triggering of the weapon is given.

Algorithm for the design of overhead transmission lines

Abstract: A dynamic programming algorithm which chooses types, heights and sites of towers along a given transmission line route is described. On the basis of estimated data for the ground strength along the line path, and the criterion of minimum construction costs, a set of consecutive cheapest solutions of the problem is determined (ie the optimal and the required number of suboptimal solutions). It is proposed to submit the obtained set of solutions for further analysis based on some additional criteria and a more accurate survey of ground strength in tower locations already known. The analysis may prove that one of the suboptimal solutions is most advantageous. Some specific features of the computer program and the results of experimental calculations are presented.

Data security and performance overhead in a distributed architecture system

Abstract: New updated! The latest book from a very famous author finally comes out. Book of data security and performance overhead in a distributed architecture system, as an amazing reference becomes what you need to get. What's for is this book? Are you still thinking for what the book is? Well, this is what you probably will get. You should have made proper choices for your better life. Book, as a source that may involve the facts, opinion, literature, religion, and many others are the great friends to join with.

Buffer invalidation system

Abstract: PURPOSE:To lessen an overhead by normally making the priority level of buffer invalidation BI processing lower and then by making it higher in a move-in CONSTITUTION:In the system having processors PC with respectively-characteristic buffer storages BS and a main memory unit, each PC is provided with BI storage part 10 stored temporarily with BI information, BI control part 11 and priority-level control part 12 that control a priority level by using BS3-1 When the contents of BS of other PC are rewritten, the BI command is stored in storage part 10 and the data entered in BS3-1 is invalidated by the command through control part 12 The priority level of a BI processing request is normally made lowest At this time, BI existence signal BIEMP or BI processing signal BIP has been input to OR circuit 13, but once move-in MVIN operation is performed, signal MVIN makes FF15 generate no output through AND circuit 14, so that control part 12 will give the top priority to the BI request processing from control part 11

Meeting a restricted consulting budget with part-time help

Abstract: At Northwestern University's Academic Computing Center, the first level of user consulting is provided by a carefully selected and trained group of 23 student consultants that report to User Services. These consultants are able to handle between 90 and 95 percent of all user problems without any further staff assistance. The total budget approximately equal to one full-time staff member without much of the overhead.

High crop overhead sprayer frame

Abstract: A sprayer frame is provided for use with a liquid spray system wherein an accurate and uniform application of liquid to a high crop situation is desired.

Performance Evaluation of the INFOPLEX Database Computer Using Operational Analysis.

Abstract: : The objective of this study is to assess the applicability of analytic techniques to the INFOPLEX database computer. This report builds on earlier work which has used simulation to evaluate the performance of the INFOPLEX data storage hierarchy. Simulation, though accurate, is not cost effective for exploring different design alternatives. Preliminary results from this study indicate that cost effective tools can be developed to analyze different architecture designs so that optimal design alternatives can be identified early in the design process. The model used in this report produces ceiling throughput to systems under investigation for overhead due to unbalanced flow is ignored. Tighter bounds can be obtained by including the unbalanced flow into analytic models. (Author)

Propagation of Disturbing Currents Along Overhead Lines

Abstract: In many problems on E lec tro m a g n et ic C o m p a t ib i l i t y , the propagation o f d i s t u r b in g s i g n a l s a long overhead l i n e s or the c o u p l in g between v a r io u s tr a n sm is s io n l i n e s s i t u a t e d above the ground has to be s t u d i e d . The d i s t u r b in g cu r re n t a t any p o in t a long th e l i n e i s o f t e n determined from the c h a r a c t e r i s t i c s o f the t r a n sm iss io n l i n e in frequency domain and then by a pp ly in g Fast F ourier Transform su b r o u t in e s . T h e r e fo r e , i t i s o f g r e a t importance to d e term ine , a t a g iv en freq u en cy , th e c urrent d i s t r i b u t i o n a lo ng a l i n e p a r a l l e l to the a ir -groun d i n t e r f a c e . We p o in t o u t in t h i s paper the l i m i t o f v a l i d i t y o f th e quasi TEM approxim ation. We g i v e v a lu e s o f the a t t e n u a t io n c o n s ta n ts and we show in what ca se th e cu r re n t does not de c re a se e x p o n e n t i a l ­ l y a long overhead l i n e s .