Showing papers on "Overhead (computing) published in 1982"

Vehicle frame measurement device

Abstract: A vehicle frame measuring and aligning apparatus comprises parallel rails with transverse reference members moveable along the longitudinal axis of the rails slideable vertical locating members are mounted on the rails. The apparatus also comprises an overhead measuring and alignment device which is slideably attached to the rails, with a vertically adjustable overhead bar to which referencing and measuring members attach. Clamping devices are used to secure the vehicle in place.

An adaptive, ordered, graph search technique for dynamic time warping for isolated word recognition

Abstract: The technique of dynamic time warping (DTW) is relied on heavily in isolated word recognition systems. The advantage of using DTW is that reliable time alignment between reference and test patterns is obtained. The disadvantage of using DTW is the heavy computational burden required to find the optimal time alignment path. Several alternative procedures have been proposed for reducing the computation of DTW algorithms. However, these alternative methods generally suffer from a loss of optimality or precision in defining points along the alignment path. In this paper we propose another alternative procedure for implementing a DTW algorithm. The procedure is based on the well-known class of techniques for a directed search through a grid to find the "shortest" path. An adaptive version of a directed search procedure is defined and shown to be capable of obtaining the exact DTW solution with reduced computation of distances but with increased overhead. It is shown that for machines where the time for distance computation is significantly larger than the time for combinatorics and overhead, a potential gain in speed of up to 3 : 1 can be realized with the directed search algorithm. Formal comparison of the directed search algorithm with a standard DTW method, in an isolated word recognition test, showed essentially no loss in recognition accuracy when the parameters of the directed search were selected to realize the 3:1 reduction in distance computation.

A multi-version concurrency scheme with no rollbacks

Abstract: The multi-version data item concept is a method for increasing concurrency in a database system. All previously proposed schemes utilizing this concept relied on transaction rollback as a means for preserving consistency. These rollbacks require a considerable amount of overhead which degrades performance. In this paper we develop a new scheme that utilizes the multi-version data item concept. Our proposed scheme ensures consistency without the use of rollbacks. It is based upon the non-two phase tree locking protocol previously proposed by Silberschatz and Kedem.

Error-correction technique for random-access memories

Abstract: On-chip error correction for random-access memories is not very popular because of the high overhead necessary. This paper presents a technique that performs a single-bit correction and a double-bit detection on clocked memories where all column data is internally available, with an area penalty of less than 20 percent. The timing overhead for on-chip implementation is less than the time required to generate a parity bit. The detection and correction operation is transparent to the user and does not require different cycle times for the detection and the correction.

Dynamic time warping for isolated word recognition based on ordered graph searching techniques

Abstract: The technique of dynamic time warping (DTW) is relied on heavily in isolated word recognition systems. The advantage of using DTW is that reliable time alignment between reference and test patterns is obtained. The disadvantage of using DTW is the heavy computational burden required to find the optimal time alignment path. Several alternative procedures have been proposed for reducing the computation of DTW algorithms. However these alternative methods generally suffer from a loss of optimality or precision in defining points along the alignment path. In this paper we propose another alternative procedure for implementing a DTW algorithm. The procedure is based on the well known class of techniques for a directed search through a grid to find the "shortest' path. An adaptive version of a directed search procedure is defined and shown to be capable of obtaining the exact DTW solution with reduced computation of distances but with increased overhead. It is shown that for machines where the time for distance computation is significantly larger than the time for combinatorics and overhead, a potential gain in speed of up to 3 to 1 can be realized with the directed search algorithm. Formal comparison of the directed search algorithm with a standard DTW method, in an isolated word recognition test, showed essentially no loss in recognition accuracy when the parameters of the directed search were selected to realize the 3 to 1 reduction in distance computation.

Performance analysis of software for an MIMD computer

Abstract: This paper presents a technique for modeling and analyzing the performance of software for an MIMD (Multiple Instruction Multiple Data) computer. The models can be used as an alternative to experimentation for the evaluation of various algorithms and different degrees of parallelism. They can also be used to study the tradeoffs involved in increasing the amount of parallel computation at the expense of increased overhead for synchronization and communication. The detection and alleviation of performance bottlenecks is facilitated.

Rollback propagation detection and performance evaluation of FTMR2M—a fault-tolerant multiprocessor

Abstract: In this paper we consider the rollback propagation and the performance of a fault-tolerant multiprocessor with a rollback recovery mechanism (FTMR2M)[1], which was designed to be tolerant of hardware failure with minimum time overhead. Rollback propagation between cooperating processes is usually required to ensure correct recovery from failure. To minimize the waste of processor time and storage overhead required for handling sophisticated rollback propagations, the FTMR2M always keeps one recoverable state. Approaches for evaluating the recovery overhead and analyzing the performance of FTMR2M are presented. Two methods for detecting rollback propagations and multi-step rollbacks between cooperating processes are also proposed.

Zero-sequence representation of overhead lines

Abstract: The zero sequence components of electrical quantities of overhead lines appearing at unsymmetrical ground faults are analysed, taking into account the mutual coupling among line phase circuits and earth wires as well as the conducting effects of line towers. The line model, developed using the Z-Transform, enables an accurate analysis of ground fault current distribution and magnitudes. As an illustration, the line model is applied for evaluation of various earthing system parameters of an EHV line connecting two substations. Analytical expressions for some of these parameters are also given.

Apparatus and method for temperature estimation of overhead conductors

Abstract: An overhead conductor monitoring device includes a simulation conductor designed to have thermal characteristics similar to those of the overhead conductor. The simulation conductor is placed in the same ambient atmosphere as the overhead conductor and is selectively heated by a coil embedded within the simulation conductor. The power supply to the coil is computed by a microcomputer to be the same as the power of the overhead conductor. Temperature sensors are placed in or on the simulation conductor to monitor the temperature thereof. As the temperature of the simulation conductor increases, the power of the overhead conductor is recomputed to reflect changes in the characteristics of the overhead conductor. An alarm signal is generated if the temperature of the simulation conductor exceeds a predetermined temperature and theoretical values of overhead conductor power can be supplied microprocessor to determine the effects on the temperature of the overhead conductor.

TDM Communication system

Abstract: A time division multiplex digital data communication system with reduced band width. The system operates on independent digital signals so they can be multiplexed by encoding the time of transition of the digital data on each channel and transmitting serially the encoded times along with a bit for indicating the direction of transition or state after the transition plus bits for synchronization and/or overhead, as necessary.

Data transfer system

Abstract: PURPOSE:To reduce the input/output overhead for transfer of data, by referring to a storage region where the presence or absence is stored for alteration of data of a main storage device to control the transfer of information from the main storage device to an auxiliary storage device. CONSTITUTION:In the contents of an auxiliary storage cache 14 includes the contents of a main storage device 11, a CPU10 refers to a main storage data alteration information storing device 12. Then only an address is transferred via an auxiliary storage control circuit 13 if the data of the device 11 has no alteration. While both the address and data are transferred via the CPU10 to the cache 14 like a case where the cache 14 includes no data of the CPU10 if the data has an alteration. The data is written to an auxiliary storage device 17 from the chache 14 in the same way by referring to an information storage device 16 which stores the presence or absence of data of the CPU10. The input/output overhead is reduced for transfer of data, and the processing speed is increased with above-mentioned minimum necessary information transfer system.

Movable load bar with automatic hooks

Abstract: A load bar is movably supported from overhead support equipment and has grabbing hooks thereon which are adaptable to support loads having a wide variety of shapes and/or sizes.

High Performance Storage Reclamation in an Object-Based Memory System

Abstract: Measurements of the Smalltalk Virtual Machine indicate that 20%-30% of the time is spent reclaiming disused storage. Following the work of Deutsch, Bobrow, and Snyder [Deutsch and Bobrow 76] [Deutsch 82a] [Deutsch 82b] [Snyder 79] we introduce a strategy that reduces the overhead of storage reclamation by more than 80%. We discuss the design of hardware to support this strategy, and compare the hardware to a traditional software implementation. We conclude by suggesting directions for future research.

Disk common mutual communication system

Abstract: A disc intercommunication system is disclosed for use in a data processing system and provides a communication path (218) which interconnects all the programmable disc devices (212-214) in a multi- processor system. The disc devices (212-214) use their self-contained processor (220) and memory (221) to interpret data transfer commands and thereby determine which disc devices are to be involved in the data file transfer. The disc devices (212-214) communicate among themselves directly via the communication path (218) to accomplish the data file transfer thereby saving considerable overhead in the host processors.

Data communicating system

Abstract: PURPOSE:To raise utilizing efficiency of a channel and to prevent an overhead time due to acquisition and release of the channel, by always monitoring a utilizing state of common transmission line, and executing the acquisition and release of the channel in accordance with its state. CONSTITUTION:In case whan a utilization factor of a channel is comparatively low, the number of channels is sufficient, therefore, as soon as a link is set, acquisition of a channel is executed, and until the link is released, the channel is not released. In this way, the overhead is reduced and the response is improved. Subsequently, when a utilizing state of the channel becomes considerably dense, each communication node device acquires the channel only when transmitting a data, in order to use in common the channel effectively, and releases the chennel in other time. In this way, the transmission line throughput is improved, and the response time is improved.

Device for cutting off silage blocks

Abstract: A vertically adjustable cutting-off device is attached to the rails of an overhead conveyor so as to be displaceable. Silage blocks put down in a feeding passage near a feeding point are cut off from above in the direction of the feeding point by a revolving cutting band of the cutting-off device.

Input-output control system

Abstract: PURPOSE:To reduce the overhead for both software and hardware, by accepting a start request at a data channel (CH) to retain it there when the CH receiving a start request is busy or retaining a CH interruption. CONSTITUTION:A start reporting part 41 of data CH decides whether a transfer part 42 is busy or not when it receives a start request from a CPU1 and then checks a subchannel (SBCH) 44 corresponding to an I/O of a start request when it knows that the CH is busy. A BUSY report is given to the CPU1 if the I/O is busy. When the I/O is idle, no BUSY report is given. And the start request is retained. When the CH becomes available by the CH end report given from the I/O or the nipping of retaining of the CH interruption given from the CPU, the I/O is started as long as the next start is retained within the part 41. In such way, the overhead can be reduced for both software and hardware.