Article Scalable parallel geometric algorithms for coarse grained multicomputers Share on Authors: Frank Dehne View Profile , Andreas Fabri Andrew Rau-Chaplin Authors Info & Claims SCG '93: Proceedings of the ninth annual symposium Computational geometryJuly 1993 Pages 298–307https://doi.org/10.1145/160985.161154Online:01 July 1993Publication History 115citation444DownloadsMetricsTotal Citations115Total Downloads444Last 12 Months2Last 6 weeks0 Get Citation AlertsNew Alert added!This alert...

We study scalable parallel computational geometry algorithms for the coarse grained multicomputer model: p processors solving a problem on n data items, were each processor has O(n/p)≫O(1) local memory and all are connected via some arbitrary interconnection network (e.g. mesh, hypercube, fat tree). present O(T sequential /p+T s (n, p)) time several problems. T p) refers to of global sort operation. Our results independent multicomputer’s network. Their complexities become optimal when /p...

The subtree prune and regraft distance ( d SPR ) between phylogenetic trees is important both as a general means of comparing tree topologies well measure lateral gene transfer (LGT). Although there has been extensive study on the computation similar metrics rooted trees, much less known about distances for unrooted which often arise in practice when root unresolved. We show that NP-Hard verify techniques from related work can cannot be applied. then present an efficient heuristic algorithm...

This paper presents a general methodology for the efficient parallelization of existing data cube construction algorithms. We describe two different partitioning strategies, one top-down and bottom-up Both strategies assign subcubes to individual processors in such way that loads assigned are balanced. Our methods reduce inter processor communication overhead by load advance instead computing each group-by parallel. create small number coarse tasks. allows sharing prefixes sort orders...

At the heart of analytical pipeline a modern quantitative insurance/reinsurance company is stochastic simulation technique for portfolio risk analysis and pricing process referred to as Aggregate Analysis. Support computation measures including Probable Maximum Loss (PML) Tail Value at Risk (TVAR) variety types complex property catastrophe insurance contracts Cat eXcess (XL), or Per-Occurrence XL, that combine these obtained in In this paper, we explore parallel methods aggregate analysis. A...

A project is described that has two goals: to explore the use of expert systems techniques for developing advanced operation support and build a useful tool assist operators Canadian National Datapac network cope with rapid growth evolution. Progress in evaluating an prototype system, DAD (Datapac Advisor), reported. The prototype's environment each its functional components are described. knowledge based design used highlighted, testing methodology results technical trial Key findings...

Skyline queries have received considerable attention in the database community. The goal is to retrieve all records a that property no other record better according of given set criteria. While this problem has been well studied computational geometry literature, solution context requires techniques designed particularly handle large amounts data. In paper, we show parallel computing an effective method speed up answering skyline on data sets. We also propose preprocess points quickly answer...

This paper addresses the query performance issue for Relational OLAP (ROLAP) datacubes. We present a distributed multi-dimensional ROLAP indexing scheme which is practical to implement, requires only small communication volume, and fully adapted disks. Our solution efficient spatial searches in high dimensions scalable terms of data sizes, dimensions, number processors. method also incrementally maintainable. Using "surrogate" group-bys, it allows processing arbitrary queries on partial...

In contrast to queries for on-line transaction processing (OLTP) systems that typically access only a small portion of database, OLAP may need aggregate large portions database which often leads performance issues. this paper we introduce CR-OLAP, Cloud based Real-time system on new distributed index structure OLAP, the PDCR tree, utilizes cloud infrastructure consisting (m + 1) multi-core processors. With increasing size, CR-OLAP dynamically increases m maintain performance. Our tree data...

Describes the parallel, cluster-based implementation of an algorithm for computation a database operator known as datacube. Though number efficient sequential algorithms have recently been proposed this problem, very little research effort has expended upon cost-effective parallelization techniques. Our approach builds directly existing proposals and is designed to be both load-balanced communication-efficient. We also provide experimental results that demonstrate viability our technique...

The operation of modern distributed enterprises, be they commercial, scientific, or health related, generate massive quantities data. Decision makers increasingly utilize On- Line Analytical Processing (OLAP) tools to glean from this rich data resource nuggets information which can used better run their enterprises. A typical approach OLAP is construct a single centralized repository by copying all the raw sites where it generated cental location, integrated, and then route queries that...

Space-filling curves, particularly Hilbert have proven to be a powerful paradigm for maintaining spatial groupings of multi-dimensional data in variety application areas including database systems,data structures and distributed information systems. One significant limitation the standard definition curves is requirement that grid size (i.e. cardinality) each dimension same. In real world, not all dimensions are equal work-around padding largest wastes memory disk space, while increasing...