Showing papers in "Journal of Parallel and Distributed Computing in 1998"

TL;DR: This paper presents and study a class of graph partitioning algorithms that reduces the size of the graph by collapsing vertices and edges, they find ak-way partitioning of the smaller graph, and then they uncoarsen and refine it to construct ak- way partitioning for the original graph.

TL;DR: The quality of the produced partitions and orderings are comparable to those produced by the serial multilevel algorithm that has been shown to outperform both spectral partitioning and multiple minimum degree.

TL;DR: The results indicate that the nonblocking queue consistently outperforms the best known alternatives and that data-structure-specific nonblocking algorithms, which exist for queues, stacks, and counters, can work extremely well.

TL;DR: The implementation and integration of all major components within the dynamic load balancing strategy for adaptive grid calculations, which remains viable on a large number of processors, are described.

TL;DR: This work focuses on (partial) permutation, k-relation routing, routing to random destinations, dynamic routing, isotonic routing, fault tolerant routing, and related sorting results.

TL;DR: This data structure is the first to support multi-insertion and multi-decrease key in constant time, and can be implemented on the EREW PRAM and can perform any sequence of operations inO(n) time andO(mlogn) work, being the total number of keyes inserted and/or updated.

TL;DR: It is shown that KeLP's flexible communication model effectively manages elaborate data motion patterns arising in structured adaptive mesh refinement and achieves performance comparable to hand-coded message-passing on several structured numerical kernels.

TL;DR: Two novel processor allocation schemes that reduce physical fragmentation for the mesh-connected multicomputers are proposed to improve the performance of theMesh-connected computers by allowing jobs to be executed on a reduced size submesh adaptively.

TL;DR: A novel variation on sample sort which uses only two rounds of regular all-to-all personalized communication in a scheme that yields very good load balancing with virtually no overhead, and its performance is invariant over the set of input distributions unlike previous efficient algorithms.

TL;DR: This work presents simple randomized algorithms for parallel priority queues on distributed memory machines that improve over the best previously known algorithms for many interconnection networks and even matches the speed of the best known PRAM algorithms.

TL;DR: This paper proposes new multicast algorithms for a mesh network using wormholerouting with apath-based facility and these new algorithms generally perform faster than algorithms previously described in the literature under the same model.

TL;DR: The parallel watershed transformation used in gray-scale image segmentation is here augmented to perform with the aid of a priori supplied image cues called markers to calibrate a resilient algorithm to oversegmentation.

TL;DR: New parallel algorithms for smoothed particle hydrodynamics and contact detection are described which turn out to have several key features in common and how to join them with traditional parallel finite element techniques to create an integrated particle/mesh transient dynamics simulation is described.

TL;DR: It is shown that the size of the load plays an important role in determining the performance of the network and the optimal load partitioning depends critically on many network parameters and load characteristics.

TL;DR: Experiments with two automatically parallelized applications show these algorithms to be effective in reducing the lock overhead to negligible levels and that an overly aggressive lock coarsening algorithm may harm the overall parallel performance by serializing sections of the parallel computation.

TL;DR: The initial results indicate that wide-area parallel processing can lead to better performance even with Internet technology, but that current Internet bandwidth is a major bottleneck for file and binary transfer.

TL;DR: This work states that the complete binary tree can be embedded into the square grid of the same size with almost optimal dilation (up to a very small factor).

TL;DR: The basic properties of the hyperstar, a multiprocessor interconnection topology, based on the Cartesian product of star graphs, are discussed and proved and are shown to be a member of the Cayley class of symmetric graphs.

TL;DR: The current paper demonstrates the success in combining problem-specific knowledge for the quadratic assignment problem (QAP) with the raw computing power offered by contemporary parallel hardware by using the library of parallel search algorithms ZRAM.

TL;DR: Results indicate that graph partitioning can now be truly embedded in dynamically changing real-world applications.

TL;DR: This work proves a lower bound of ?

TL;DR: A data structure for searching in multi-dimensional point sets in distributed environments and its experimental evaluation also through a comparison with previous proposals, based on an extension ofk-d trees is presented.

TL;DR: A partitioning and scheduling mechanism that adapts to resource changes and optimizes resource utilization is proposed and the application of this mechanism for online information browsing is demonstrated.

TL;DR: This paper transforms DFT into a form expressed in discrete moments via a modular mapping and truncating Taylor series expansion and extends the use of the systolic array for fast computation of moments without any multiplications to one that computes DFT with only a few multiplications and without any evaluations of exponential functions.

TL;DR: The proposed scheme is the first synthesis scheme which can collectively synthesize Fortran 90 RESHAPE, EOSHIFT, MERGE, array reduction operations, and WHERE constructs and is based on the composition of access functions, which is analogous to a composition of mathematic functions.

TL;DR: Lower bounds for the performance ratio of dynamic tree embedding in bipartite static networks, including numerous important networks such as n-dimensional meshes,n-dimensional tori,k-aryn-cubes, cube-connected cycles, and butterflies are established.

TL;DR: The analysis and results indicate that when the size of the subnetwork assigned to processor is small enough so that the computation time is less than or equal to the communication time within an iteration, high frequency termination detection methods should be used.

TL;DR: A linear time algorithm is presented that constructs for every degreedproblem instance a communication schedule with total communication time at most d2, which is the maximum number of messages that each processor may send or receive.

TL;DR: This paper presents a technique to reduce overheads for applications that dynamically create and destroy processes and log event information with attached vector timestamps, at the expense of a more complicated timestamp comparison protocol and more sophisticated data structures for maintaining vector time.

TL;DR: In this article, a simple embedding algorithm is proposed that can embed ann-level binomial tree in ann-cube with up ton?1 faulty links in log(n?1) steps.