In order to exploit the latest advances in hardware technology, application developers need high-performance, easy-to-use cooperation tools that spun interconnections of standard hardware. Distributed shared memory has been proposed as such a cooperation tool, but performance problems have limited its usefulness. This paper argues that a new approach to distributed shared memory implementation can make it an effective tool in its own right and a foundation for other tools. It describes a prototype implementation that allows sharing of memory resources in workstation cluster. The prototype is based on an innovative, low-overhead messaging protocol which utilizes the high bandwidth of the underlying hardware, while adding very little latency overhead. Finally, the interface exported by this software is designed to function effectively as a substrate for a variety of cooperation tools.>

The authors examine the use of a new architecture for the design of system software. The architecture allows the construction of flexible system software components, and the resulting realizations can be tailored to the needs of various applications. The focus is on the application of that architecture to distributed shared memory (DSM). The system software architecture, called pi , defines elements of system software as generalized objects. These x objects have two interfaces: one for usage and one for additional control. pi enables system software components to evolve as computer hardware evolves and it addresses the demands emerging classes of applications like object-oriented databases and multimedia. The pi architecture and its use in a DSM subsystem for clustered workstations are discussed.>

The verification of identifying and pose hypotheses in model-based 3D object recognition systems can involve a time-consuming image rendering operation followed by pixel-level comparison of the input and rendered images. In situations where many such hypotheses need to be verified, exploitation of inherent data-parallelism between hypotheses and their corresponding object models can increase the efficiency of the object recognition system. The authors describe a prototype system for distribution of hypotheses and the accompanying rendering tasks to individual processors in a loosely-coupled computing environment, and demonstrate excellent performance improvements over a single-processor implementation.>

A programming model for developing distributed applications requiring closely coupled concurrent components is described. In integrates the features of remote procedure calls (RPCs) with those of shared variables into a familiar programming environment. While procedure calls are a well-known paradigm, classic RPCs do not enable fine-grained information sharing. Shared variables facilitate such sharing but have yet to be integrated into a familiar model for distributed applications. The new model, realized as ARCADE-Based C, or ABC, extends C to include the creation and invocation of remote functions; blocking/nonblocking function calls, and distributed shared variables.>

Variable length source coding schemes offer substantial improvements in data rate for a wide variety of data compression techniques. Unfortunately, practical considerations have limited their use. This paper describes several techniques which allow these powerful codes to be effectively applied. In particular, the problem of loss of code word synchronization due to channel errors is addressed. It is shown how self-synchronizing codes limit error propagation. Also, variable delay and the associated difficulties of buffer synchronization and buffer overflow are considered. The variable delay at the transmitter can be coupled with a variable delay at the receiver to give a fixed system delay. Buffer control then becomes the allocation of this delay between transmitter and receiver. Finally, a switching property of variable length codes to better match the bimodal operation of the source is presented.

A simplified combination speech codec (coder/ decoder) and filter structure is described. It uses adaptive delta modulation followed by digital processing to produce a filtered log-PCM representation of a speech signal. The simplification results from combining the delta modulation step-size expansion, integration and low-pass filtering into one operation. All multiplications are eliminated and replaced by one-bit shift-and-add operations. The resulting structure is amenable to a single chip implementation using conventional, all-digital technologies while satisfying established filter standards.

A speech coding algorithm for digital transmission of speech at a rate of 9600 bits per second which can be implemented on a speech processing system is described. The algorithm combines the following: a pitch extraction loop, a pitch compensating adaptive quantizer, a sequentially adaptive linear predictor, an adaptive source coding, and a multipath tree searching to generate very high quality speech output. Although each of these elements has been previously applied to speech coding, the combination of all five of these elements has not been discussed before. Preliminary simulation studies of the algorithm have yielded a signal-to-noise ratio which is indicative of very high quality speech.

A new adaptive quantizer for speech digitization has been derived. It is similar to known adaptive quantizers in that it adjusts its dynamic range to match that of the speech waveform. In addition, it further adjusts its range to compensate for the increased signal strength that follows a pitch pulse. The new quantizer bases its adaptation on its own output and no side information is required. When combined with a variable length source coding scheme, the new quantizer offers a significant improvement in signal-to-noise ratio and in subjective speech quality. The technique is applicable to a broad range of digitization methods including adaptive delta modulation and various forms of ADPCM.

A new scheme for enumerating the legal bidding sequences in bridge is developed for various constraints on the allowed bids. It is shown that such bidding sequences can be represented by fixed length strings from aD-ary alphabet and that all such strings represent bidding sequences.

An improved system for speech digitization using adaptive differential pulse-code modulation (ADPCM) is described. The system uses an adaptive predictor, an adaptive quantizer, and a variable length source coding scheme to achieve a 4-5 dB increase in signal-to-noise ratio over previous ADPCM. The increase can be used to improve speech quality at moderate data rates on the order of 16 kbits/s or to retain the same quality and reduce the data rate to 9.6 kbits/s. The latter alternative permits the use of narrow-band channels. The implementation complexity is on the same order as other ADPCM systems.

In this correspondence, it is shown that an adaptive quantizer with a one word memory can be viewed as one that estimates the variance of its input and normalizes the input by the square root of the estimate. It is shown that, even though the estimate is an exponential average, the effect of transmission errors does not die out. Finally, a method of combating the effect of such errors is described.

Bounds on the capacity of a class of digital communication channels are derived. Equating the bounds on capacity to rate-distortion functions of (typical) sources in turn produces bounds on the performance of a class of digital communication systems. For ratios of squared quantization level to noise variance much !ess than one, the power requirements for this class of digital communication systems are shown to be within approximately 3 dB of the theoretical optimum.

This paper describes the application of selected block and convolutional coding techniques to digital transmission over an HF radio channel. Performance results are presented for interleaved binary Bose-Chaudhuri-Hocquenghem (BCH) codes, interleaved two-stage concatenated codes, and diffuse convolutional codes. The performance results are based upon raw error data recorded in transmission over a 640-km HF path, with various data runs representing the typical effects of frequency-selective and non-selective fading, atmospheric impulse noise, and interference from other users of the HF band. The performance of binary BCH codes with bit interleaving is presented and the selection of a code to meet a specified performance criterion is described. The sensitivity of specific codes to changing channel conditions is presented, along with the cost, in terms of interleaving, of designing for one set of channel conditions rather than others. Concatenated codes are discussed as a means of effective error control on channels with clustered errors. Performance data are presented for selected two-stage codes used with inner-stage word interleaving and the effects of varying certain of the code parameters are shown. Emphasis is placed on code designs that use the inner-stage code only for error detection and the outer-stage code mainly for erasure filling with only a small amount of symbol error correction. The impact of error clustering on the performance of concatenated codes is discussed. Two diffuse convolutional codes are evaluated with the use of recorded error data in computer simulations of their threshold-decoding algorithms. Performance of various configurations of these convolutional codes is given and a comparison is made with that of a simple block coding scheme having the same decoder storage requirements. The various coding techniques studied are compared on the basis of achievable performance as well as certain factors affecting the feasibility of implementation.