the proceedings contain 79 papers. the special focus in this conference is on Fundamentals of Computation theory. the topics include: Simulation-based comparison of hash functions for emulated shared memory;task manag...
ISBN:
(纸本)9783540568919
the proceedings contain 79 papers. the special focus in this conference is on Fundamentals of Computation theory. the topics include: Simulation-based comparison of hash functions for emulated shared memory;task management, virtual shared memory, and multithreading in a distributed memory implementation of sisal;simulating the data diffusion machine;an FP based programming language for efficient parallel programming of multiprocessor networks;the data-parallel categorical abstract machinedata parallel implementation of extensible sparse functional arrays;embeddings of tree-related networks in incomplete hypercubes;optimal mappings of m dimensional FFT communication to k dimensional mesh for arbitrary m and k;the united functions and objects approach;detection of recurrences in sequential programs with loops;parallel programming using skeleton functions;data-parallel portable software platform: principles and implementation;a compositional approach for fault-tolerance using specification transformation;concurrent metatem — a language for modelling reactive systems;trace-based compositional reasoning about fault tolerant systems;a kahn principle for networks of nonmonotonic real-time processes;adaptive multicast wormhole routing in 2D mesh multicomputer;the impact of packetization in wormhole-routed networks;a high-performance flat concurrent logic programming system;exploiting recursion-parallelism in prolog;why and how in the elipsys or-parallel CLP system;skewed-associative caches;trace-splitting for the parallel simulation of cache memory;locality and false sharing in coherent-cache parallel graph reduction;SLiD — a cost-effective and scalable limited-directory scheme for cache coherence and formal development of actor programs using structured algebraic petri nets.
the proceedings contain 107 papers. the topics discussed include: consistency management for software design information repository;an entity-relationship approach to schema evolution;evaluating partitioning technique...
ISBN:
(纸本)0818642122
the proceedings contain 107 papers. the topics discussed include: consistency management for software design information repository;an entity-relationship approach to schema evolution;evaluating partitioning techniques for main memory database: horizontal and single vertical;modeling and storage allocation strategies for homogeneous parallel access storage devices in real time multimedia information processing;towards a methodology for developing a federated database system;multimedia databases modeling;eliminating unnecessary array bounds checks in nests of loops;on driving and monitoring smalltalk-80 applications using UNIX spreadsheets;optimal operations on red-black trees;preprocessing first-class functions for Ada;AI-based classification and retrieval of reusable software components;and a neural network model for documentary base self-organizing and querying.
the scheduling policy of a microkernel significantly affects the parallel execution of fine-grained programs. In this study several thread management alternatives were implemented on a shared memory system with 6 proc...
详细信息
Improvements in disk speed have not kept up with improvements in processor and memory speed. Conventional storage techniques, in the face of multimedia data, are inefficient and/or inadequate. An efficient multimedia ...
详细信息
We propose a parallel algorithm which reduces the problem of computing Hamiltonian cycles in tournaments to the problem of computing Hamiltonian paths. the running time of our algorithm is O(log n) using O(n2/log n) p...
详细信息
In this paper, we present algorithms for solving several basic geometric problems of size n in a network of p processors each with O(n/p) local memory. Our algorithms achieve the best possible (up to a constant factor...
详细信息
In this paper, we present algorithms for solving several basic geometric problems of size n in a network of p processors each with O(n/p) local memory. Our algorithms achieve the best possible (up to a constant factor) time bound in hypercubic parallelarchitectures such as hypercube, shuffle exchange and cube connected cycles, provided that n /spl les/ p/sup 1/+/spl epsi/ for some positive constant /spl epsi/. Our algorithms use only sorting and parallel prefixes that involve interprocessor communications, and can be easily implemented in commercially available parallel computers. Experimentation on nCUBE parallel computers show that our algorithms run efficiently.< >
Data-parallel ML is proposed for compilation to a distributed version (DPCAM) of Cousineau, Curien and Mauny’s Categorical Abstract Machine. the DPCAM is a static network of CAMs which dynamically restrict the MIMD e...
详细信息
the authors present a testability analysis and testing approach for local and global interconnection topologies for single and multiple faulty cells. Fault location can be obtained for single faulty cells, while for m...
详细信息
ISBN:
(纸本)0780308670
the authors present a testability analysis and testing approach for local and global interconnection topologies for single and multiple faulty cells. Fault location can be obtained for single faulty cells, while for multiple cells fault masking can be identified, and fault location can be obtained iteratively. the approach is based on the analysis of controllability and observability of the architecture given the cell function and the interconnection topology. the input output relationship of the generic cell is the cell function. A fault model is derived for multistage interconnection networks. the testing method can be applied to any architecture independently of its topology, and of the number of input and output lines of the generic cell contained in it.
Cost-effective multiprocessor designs may be obtained by combining processors of different speeds (heterogeneous architecture) in the same architecture. this way, the serial and critical portions of the application ma...
详细信息
this paper addresses the problem of constructing a work load balanced parallel multi-way merge. While a balanced multi-way merge provides an ideal component for multiprocessor sorting algorithms, the general problem c...
详细信息
暂无评论