检索结果-内蒙古大学图书馆

Computer architectures for Machine Perception, proceedings (CAMP) 2000年 131-135页

作者： Verdier, Francois Merigot, Alain Zavidovique, Bertrand Universite de Cergy-Pontoise Cergy-Pontoise France

This paper presents some results of programming efficient matching algorithms on a new asynchronous parallel programming model. Matching algorithms are widely used in Image Processing when considering high-level treatments. Pattern Analysis, Database Search, 2D and 3D reconstruction all need matching algorithms to perform. Experiments we done were mainly oriented towards a particular matching problem: the Stable Marriage algorithm. Different implementations of this algorithm have been done on a massively parallel asynchronous model. This model relies on a network of asynchronously communicating processors leading to very fast SIMD treatments. The asynchronous model and implementations of the matching algorithm are presented. An example of Image Processing problem is also used for illustration purpose and supports the architectural discussion and results.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast stable matching algorithm using asynchronous parallel programming model

Fast stable matching algorithm using asynchronous parallel p...

引用

Computer architectures for Machine Perception (CAMP)

作者： F. Verdier A. Merigot B. Zavidovique ETIS-Equipe Traitement des Image et du Signal Université de Cergy Pontoise Cergy-Pontoise France Institut d'Electronique Fondamentale Université PARIS Sud Orsay France

This paper presents some results of programming efficient matching algorithms on a new asynchronous parallel programming model. Matching algorithms are widely used in image processing when considering high-level treatments. Pattern analysis, database search, 2D and 3D reconstruction all need matching algorithms to perform. Experiments we did were mainly oriented towards a particular matching problem: the stable marriage algorithm. Different implementations of this algorithm have been done on a massively parallel asynchronous model. This model relies on a network of asynchronously communicating processors leading to very fast SIMD treatments. The asynchronous model and implementations of the matching algorithm are presented. An example of image processing problem is also used for illustration purpose and supports the architectural discussion and results.

关键词： parallel programming Image processing Pattern matching Pattern analysis Image databases parallel machines Optimal matching Computer networks Asynchronous communication Arithmetic

来源：评论

学校读者我要写书评

暂无评论

A parallel spatial join framework using PMR-quadtrees

A parallel spatial join framework using PMR-quadtrees

引用

international workshop on Database and Expert Systems Applications

作者： A.A.B. Lima C. Esperanca M. Mattoso COPPE/UFRJ-Computer Science Department Federal University of Rio de Janeiro Rio de Janeiro Brazil

Spatial join is the most important and complex operation in spatial databases. Therefore, there is a lot of ongoing research presenting algorithms and data structures to efficiently process spatial joins. In this work we present a parallel solution for spatial join processing with a dynamic load balance strategy. We have implemented PMR-quadtrees (Samet, 1990) on top of persistent object structures using an object oriented database server.

关键词： Object oriented databases Spatial databases parallel processing Database systems Load management Computer science Data structures Memory architecture parallel architectures Scalability

来源：评论

学校读者我要写书评

暂无评论

parallel segmentation based on topology with the associative net model

Parallel segmentation based on topology with the associative...

引用

Computer architectures for Machine Perception (CAMP)

作者： D. Dulac S. Guezguez G. Bertrand A2SI ESIEE France University of Paris XI Orsay France

This paper presents an implementation of a topological segmentation on a SIMD massively parallel computer based on reconfigurability and asynchronism: Associative Mesh. This architecture provides powerful computational primitives that can apply an associative operator over the connex sets of a graph. So, basic primitives combine communications and computations. These primitives can be easily and efficiently realised in hardware by means of asynchronous operations and are adapted to a large number of image analysis primitives. We try to show the adequacy of Associative Mesh computing model with the different data movements that are generated by the several approaches of the image analysis. We are interested here with a new approach: image topology. We indicate how to get an homotopic kernel and a leveling kernel with parallel algorithms. Such kernels may be seen as "ultimate" topological simplifications of an image. This kind of image is similar to a very good split because it is based on topological information of image. We show one example of merge: we implement a method segmenting without the need of defining and tuning parameters.

关键词： Topology Kernel Image analysis Mesh generation Image segmentation Gray-scale Concurrent computing Computer architecture Hardware parallel machines

来源：评论

学校读者我要写书评

暂无评论

A choice of SM/DM parallel ANN implementation for embedded applications

A choice of SM/DM parallel ANN implementation for embedded a...

引用

international Conference and workshop on Engineering of Computer-Based Systems

作者： V. Dvorak R. Cejka Department of Computer Science Brno University of Technology Brno Czech Republic

This paper examines implementations of a multi-layer perceptron (MLP) on bus-based shared memory (SM) and on distributed memory (DM) multiprocessor systems. The goal has been to optimize HW and SW architectures in order to obtain the fastest response possible. Prototyping parallel MLP algorithms for up to 8 processing nodes with the DM as well as SM memory was done using CSP-based TRANSIM tool. The results of prototyping MLPs of different sizes on various number of processing nodes demonstrate the feasible speedups, efficiency and time responses for the given CPU speed, link speed or bus bandwidth.

关键词： Samarium Delta modulation

来源：评论

学校读者我要写书评

暂无评论

parallel segmentation based on topology with the Associative Net Model

Computer Architectures for Machine Perception, Proceedings (...

引用

Computer architectures for Machine Perception, proceedings (CAMP) 2000年 95-103页

作者： Dulac, Didier Guezguez, Saloua Bertrand, Gilles A2SI-ESIEE Noisy-Le-Grand France

This paper presents an implementation of a topological segmentation on a SIMD massively parallel computer based on reconfigurability and asynchronism: Associative Mesh. This architecture provides powerful computational primitives that can apply an associative operator over the connex sets of a graph. So, basic primitives combine communications and computations. These primitives can be easily and efficiently realized in hardware by means of asynchronous operations and are adapted to a large number of image analysis primitives. We try to show the adequacy of Associative Mesh computing model with the different data movements that are generated by the several approaches of the image analysis. We are interested here with a new approach: image topology. We indicate how to get an homotopic kernel and a leveling kernel with parallel algorithms. Such kernels may be seen as `ultimate' topological simplifications of an image. This kind of image is similar to a very good split because it is based on topological information of image. We show one example of merge: we implement a method segmenting without the need of defining and tuning parameters.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Examples of image processing to benefit from an asynchronous implementation

Examples of image processing to benefit from an asynchronous...

引用

Computer architectures for Machine Perception (CAMP)

作者： E. Senn B. Zavidovique L.E.S.T.E.R. Université de Bretagne Sud Lorient France Institut dElectronique Fondamentale Université Paris XI Orsay France

This paper describes how asynchronous techniques make easier timing in an image processing computer. It outlines an original machine architecture, and explains why it is asynchronous: the router circuit supports the asynchronism by itself. Its structure and behavior are sketched. Our method for self-timed design, its salient features and contributions to the typical asynchronous circuit design flow are introduced. The VLSI implementation and the cell set design, including full-custom self-timed asynchronous cells, are detailed. Measured circuit's performances are presented, as well as global processing and communication performances for different image processing algorithms. The gain from asynchronism is exhibited.

关键词： Image processing Communication system control Circuits Very large scale integration Robots Humans parallel machines Frequency synchronization Logic Clocks

来源：评论

学校读者我要写书评

暂无评论

An object-oriented framework for the parallel join operation

An object-oriented framework for the parallel join operation

引用

international workshop on Database and Expert Systems Applications

作者： S. Carvalho A. Lerner S. Lifschitz Departamento de Informática Pontificia Universidade Católica do Rio de Janeiro PUC Rio Rio de Janeiro Rio de Janeiro Brazil

We propose an object oriented framework for one of the most frequent and costly operations in parallel database systems: the parallel join. The framework independently captures a great variety of parameters, such as different load balancing procedures and different synchronization disciplines. The framework addresses DBMS flexibility, configuration and extensibility issues, via the instantiation of known algorithms and facilities for the introduction of new ones. The framework can also be used to compare algorithms and to determine the execution scenario an algorithm is best suited for. Related algorithms are grouped in families, suggesting a taxonomy.

关键词： Algorithm design and analysis Partitioning algorithms US Department of Transportation Electronic switching systems Taxonomy parallel processing Costs parallel architectures

来源：评论

学校读者我要写书评

暂无评论

proceedings of the 1st international workshop on Software and Performance, WOSP 1998

Proceedings of the 1st International Workshop on Software an...

引用

1st international workshop on Software and Performance, WOSP 1998

ISBN: (纸本)1581130600

The proceedings contain 27 papers. The topics discussed include: further experiences with software performance modelling;avoiding the software performance crisis;a wideband approach to integrating performance prediction into a software design environment;issues in cache management algorithms for commercial software systems;software performance engineering a digital signal processing application;on a language based method for software performance engineering of client/server systems;performance analysis of communication systems formally specified in SDL;modeling execution architecture of software system using colored Petri nets;experience in performance analysis of large real-time systems;performance modeling of layered network protocol software implemented with UNIX STREAMS facilities: application to a frame relay access device;applications optimization methodology-an approach;performance evaluation of software architectures;predicting memory use from a class diagram using dynamic information;development and validation of a hierarchical memory model incorporating CPU- and memory-operation overlap;performance of multi-level client-server systems with parallel service operations;managing performance requirements for information systems;and an approach to performance evaluation of software architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

4th international workshop on Applied parallel Computing Large Scale Scientific and Industrial Problems, PARA 1998

引用

4th international workshop on Applied parallel Computing, PARA 1998

ISBN: (纸本)3540654143

The proceedings contain papers 75. The special focus in this conference is on Applied parallel Computing Large Scale Scientific and Industrial Problems. The topics include: Communications Latency Hiding Techniques for a Reconfigurable Optical Interconnect;Multifrontal Solvers Within the PARASOL Environment;parallelization of a 3D FD-TD Code for the Maxwell Equations Using MPI;Advanced Calculations and Visualization of Enzymatic Reactions with the Combined Quantum Classical Molecular Dynamics Code;Memory Access Profiling Tools for Alpha-based architectures;parallelized Block-Structured Newton-Type Methods in Dynamic Process Simulation;Tuning the Performance of parallel Programs on NOWs Using Performance Analysis Tool;Numerical Simulation of 3D Fully Nonlinear Water Waves on parallel Computers;Fluctuations in the Defect Creation by Ion Beam Irradiation;parallelisation of an Industrial Hydrodynamics Application Using the PINEAPL Library;Hyper-Rectangle Selection Strategy for parallel Adaptive Numerical Integration;parallelising Fuzzy Queries for Spatial Data Modelling on a Cray T3D;Hyper-Systolic Implementation of BLAS-3 Routines on the APE100/Quadrics Machine;Resource Management for Ultra-scale Computational Grid Applications;A ScaLAPACK-Style Algorithm for Reducing a Regular Matrix Pair to Block Hessenberg-Triangular Form;parallel Tight-Binding Molecular Dynamics Code Based on Integration of HPF and Optimized parallel Libraries;parallel Computation of Multidimensional Scattering Wavefunctions for Helmholtz/Schroedinger Equations;New Serial and parallel Recursive QR Factorization algorithms for SMP Systems;Visualization of CFD Computations and Improving the Performance of Scientific parallel Applications in a Cluster of Workstations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：