Showing papers in "Distributed Computing in 1989"
IBM1
TL;DR: A probabilistic method is proposed for reading remote clocks in distributed systems subject to unbounded random communication delays and can achieve clock synchronization precisions superior to those attainable by previously published clock synchronization algorithms.
Abstract: A probabilistic method is proposed for reading remote clocks in distributed systems subject to unbounded random communication delays. The method can achieve clock synchronization precisions superior to those attainable by previously published clock synchronization algorithms. Its use is illustrated by presenting a time service which maintains externally (and hence, internally) synchronized clocks in the presence of process, communication and clock failures.
660 citations
121 citations
TL;DR: A technique for synthesizing systolic arrays which have non-uniform data flow governed by control signals is presented and it is shown how to derive the control signals in such arrays by applying similar pipelining transformations to theselinear conditional expressions.
Abstract: We present a technique for synthesizing systolic arrays which have non-uniform data flow governed by control signals. The starting point for the synthesis is anAffine Recurrence Equation—a generalization of the simple recurrences encountered in mathematics. A large class of programs, including most (single and multiple) nested-loop programs can be described by such recurrences. In this paper we extend our earlier work (Rajopadhye and Fujimoto 1986) in two principal directions. Firstly, we characterize a class of transformations calleddata pipelining and show that they yield recurrences that havelinear conditional expressions governing the computation. Secondly, we discuss the synthesis of systolic arrays that have non-uniform data flow governed by control signals. We show how to derive the control signals in such arrays by applying similar pipelining transformations to theselinear conditional expressions. The approach is illustrated by deriving the Guibas-Kung-Thompson architecture for computing the cost of optimal string parenthesization.
97 citations
TL;DR: In this paper, the principal sources of bottomhole assembly (BHA) bending vibration are drill-collar whirling and linear coupling between weight on bit and bending vibration of an initially curved BHA.
Abstract: Description of the principal sources of bottomhole assembly (BHA) bending vibration: drill-collar whirling and linear coupling between weight on bit and bending vibration of an initially curved BHA. Evolution of the consequences of bending vibrations in terms of drill-collar wear and connection fatigue. Downhole measurement of bending moment are used to detect and identify bending-vibration events.
89 citations
68 citations
TL;DR: This paper presents a model for message-logging based schemes to support fault-tolerant processes and develops conditions for proper message recovery in asynchronous systems and shows that requiring messages to be recovered in the same order as they were received before failure is a stricter requirement than necessary.
Abstract: A process is said to be fault tolerant if the system provides proper service despite the failure of the process. For supporting fault-tolerant processes, measures have to be provided to recover messages lost due to the failure. One approach for recovering messages is to use message-logging techniques. In this paper, we present a model for message-logging based schemes to support fault-tolerant processes and develop conditions for proper message recovery in asynchronous systems. We show that requiring messages to be recovered in the same order as they were received before failure is a stricter requirement than necessary. We then propose a distributed scheme to support fault-tolerant processes that can also handle multiple process failures.
38 citations
36 citations
30 citations
27 citations
27 citations
TL;DR: This work identifies the properties of naming systems, including under what conditions they support unique names, relative names, absolute names, and synonyms, and discusses how the basic elements of the model can be implemented by name servers.
Abstract: Naming in distributed systems is modelled as a string translation problem. Viewing names as strings and name resolution mechanisms as syntax directed translators provides a formal handle on the loosely understood concepts associated with naming: we give precise definitions for such informal terminology as name spaces, addresses, routes, source-routing, and implicit-routing; we identify the properties of naming systems, including under what conditions they support unique names, relative names, absolute names, and synonyms; and we discuss how the basic elements of the model can be implemented by name servers.
TL;DR: This paper formalizes the concept of message routing and shows a method by which a deadlock-free routing algorithm can be constructed out of a given routing algorithm.
Abstract: The execution of a concurrent computation by a network of processors requires a routing algorithm that is deadlock free. Many routing algorithms proposed for processor networks have the potential of deadlock due to the cyclic topology of the network. In this paper we first formalize the concept of message routing. Next, we show a method by which a deadlock-free routing algorithm can be constructed out of a given routing algorithm. Finally the method is illustrated by constructing deadlock-free routing algorithms for cartesian product processor networks.
TL;DR: In this article, the results of a 4-year study comparing liquid and dry cement additives are presented, and a pre-job quality-control checklist for use of liquid additives is presented and a dry-blending procedure is recommended.
Abstract: Presentation of the results of a 4-year study comparing liquid and dry cement additives. Cement-slurry thickening time, fluid loss, free water, and compressive strength are examined; and sensitivity to changes in slurry density is illustrated. Laboratory data demonstrate the liabilities of the liquid-additive system, and three case histories are discussed. A cost analysis shows that liquid-additive systems are more expensive. A prejob quality-control checklist for use of liquid additives is presented, and a dry-blending procedure is recommended.
TL;DR: Moran and Warmuth (1986) prove that anydeterministic algorithm that evaluatesf onR has communication complexity Ω (n logn) bits and construct a family of cyclic nonconstant boolean functions that can be evaluated inO(n l Cogn) bits by a deterministic algorithm.
Abstract: LetR be a unidirectional asynchronous ring ofn identical processors each with a single input bit. Letf be any cyclic nonconstant function ofn boolean variables. Moran and Warmuth (1986) prove that anydeterministic algorithm that evaluatesf onR has communication complexity Ω (n logn) bits. They also construct a family of cyclic nonconstant boolean functions that can be evaluated inO(n logn) bits by a deterministic algorithm. This contrasts with the following new results: