Scientific and artistic investigation of multi-dimensional fractals on the AT & T pixel machine

The pipelined architecture and parallel organization of the AT&T Pixel Machine image computer are described and demonstrated with applications for the visualization of multidimensional fractals, particularly linear fractals and quaternion/ stacked Julia sets. Techniques for pushing the Pixel Machine to its peak abilities are described and apply to more recent parallel image computers as well.     

Presupposition failure — A comedy of errors

Presuppositions of utterances are the pieces of information you convey with an utterance no matter whether your utterance is true or not. We first study presupposition in a very simple framework of updating propositional information, with examples of how presuppositions of complex propositional updates can be calculated. Next we move on to presuppositions and quantification, in the context of a dynamic version of predicate logic, suitably modified to allow for presupposition failure. In both the propositional and the quantificational case, presupposition failure can be viewed as error abortion of procedures. Thus, a dynamic assertion logic which describes the preconditions for error abortion is the suitable tool for analysing presupposition.     

Function materialization in object bases: design, realization, andevaluation

View materialization is a well-known optimization technique of relational database systems. We present a similar, yet more powerful, optimization concept for object-oriented data models: function materialization. Exploiting the object-oriented paradigm-namely, classification, object identity, and encapsulation-facilitates a rather easy incorporation of function materialization into (existing) object-oriented systems. Only those types (classes) whose instances are involved in some materialization are appropriately modified and recompiled, thus leaving the remainder of the object system invariant. Furthermore, the exploitation of encapsulation (information hiding) and object identity provides for additional performance tuning measures that drastically decrease the invalidation and rematerialization overhead incurred by updates in the object base. First, it allows us to cleanly separate the object instances that are irrelevant for the materialized functions from those that are involved in the materialization of some function result, and this to penalize only those involved objects upon update. Second, the principle of information hiding facilitates fine-grained control over the invalidation of precomputed results. Based on specifications given by the data type implementor, the system can exploit operational semantics to better distinguish between update operations that invalidate a materialized result and those that require no rematerialization. The paper concludes with a quantitative analysis of function materialization based on two sample performance benchmarks obtained from our experimental object base system GOM     

RAPS: a rule-based language for specifying resource allocation andtime-tabling problems

A general language for specifying resource allocation and time-tabling problems is presented. The language is based on an expert system paradigm that was developed previously by the authors and that enables the solution of resource allocation problems by using experts' knowledge and heuristics. The language enables the specification of a problem in terms of resources, activities, allocation rules, and constraints, and thus provides a convenient knowledge acquisition tool. The language syntax is powerful and allows the specification of rules and constraints that are very difficult to formulate with traditional approaches, and it also supports the specification of various control and backtracking strategies. We constructed a generalized inference engine that runs compiled resource allocation problem specification language (RAPS) programs and provides all necessary control structures. This engine acts as an expert system shell and is called expert system for resource allocation (ESRA). The performance of RAPS combined with ESRA is demonstrated by analyzing its solution of a typical resource allocation problem     

Sort vs. hash revisited

Efficient algorithms for processing large volumes of data are very important both for relational and new object-oriented database systems. Many query-processing operations can be implemented using sort- or hash-based algorithms, e.g. intersections, joins, and duplicate elimination. In the early relational database systems, only sort-based algorithms were employed. In the last decade, hash-based algorithms have gained acceptance and popularity, and are often considered generally superior to sort-based algorithms such as merge-join. In this article, we compare the concepts behind sort- and hash-based query-processing algorithms and conclude that (1) many dualities exist between the two types of algorithms, (2) their costs differ mostly by percentages rather than by factors, (3) several special cases exist that favor one or the other choice, and (4) there is a strong reason why both hash- and sort-based algorithms should be available in a query-processing system. Our conclusions are supported by experiments performed using the Volcano query execution engine     

Partitioned encoding schemes for algorithm-based fault tolerance inmassively parallel systems

Considers the applicability of algorithm based fault tolerance (ABET) to massively parallel scientific computation. Existing ABET schemes can provide effective fault tolerance at a low cost For computation on matrices of moderate size; however, the methods do not scale well to floating-point operations on large systems. This short note proposes the use of a partitioned linear encoding scheme to provide scalability. Matrix algorithms employing this scheme are presented and compared to current ABET schemes. It is shown that the partitioned scheme provides scalable linear codes with improved numerical properties with only a small increase in hardware and time overhead     

Massively parallel algorithms for trace-driven cache simulations

Considers the use of massively parallel architectures to execute a trace-driven simulation of a single cache set. A method is presented for the least-recently-used (LRU) policy, which, regardless of the set size C, runs in time O(log N) using N processors on the EREW (exclusive read, exclusive write) parallel model. A simpler LRU simulation algorithm is given that runs in O(C log N) time using N/log N processors. We present timings of this algorithm's implementation on the MasPar MP-1, a machine with 16384 processors. A broad class of reference-based line replacement policies are considered, which includes LRU as well as the least-frequently-used (LFU) and random replacement policies. A simulation method is presented for any such policy that, on any trace of length N directed to a C line set, runs in O(C log N) time with high probability using N processors on the EREW model. The algorithms are simple, have very little space overhead, and are well suited for SIMD implementation     

Unicast-based multicast communication in wormhole-routed networks

Multicast communication, in which the same message is delivered from a source node to an arbitrary number of destination nodes, is being increasingly demanded in parallel computing. System supported multicast services can potentially offer improved performance, increased functionality, and simplified programming, and may in turn be used to support various higher-level operations for data movement and global process control. This paper presents efficient algorithms to implement multicast communication in wormhole-routed direct networks, in the absence of hardware multicast support, by exploiting the properties of the switching technology. Minimum-time multicast algorithms are presented for n-dimensional meshes and hypercubes that use deterministic, dimension-ordered routing of unicast messages. Both algorithms can deliver a multicast message to m-1 destinations in [log ₂ m] message passing steps, while avoiding contention among the constituent unicast messages. Performance results of implementations on a 64-node nCUBE-2 hypercube and a 168-node Symult 2010 2-D mesh are given     

Weight smoothing to improve network generalization

A weight smoothing algorithm is proposed in this paper to improve a neural network's generalization capability. The algorithm can be used when the data patterns to be classified are presented on an n-dimensional grid (n>/=1) and there exists some correlations among neighboring data points within a pattern. For a fully-interconnected feedforward net, no such correlation information is embedded into the architecture. Consequently, the correlations can only be extracted through sufficient amount of network training. With the proposed algorithm, a smoothing constraint is incorporated into the objective function of backpropagation to reflect the neighborhood correlations and to seek those solutions that have smooth connection weights. Experiments were performed on problems of waveform classification, multifont alphanumeric character recognition, and handwritten numeral recognition. The results indicate that (1) networks trained with the algorithm do have smooth connection weights, and (2) they generalize better.