This paper presents the BaLinda model, based on last in/first out threads that interact via a shared tuplespace, and discusses the idea of using function based objects as the basic unit of parallel execution, and the ...
详细信息
This paper presents the BaLinda model, based on last in/first out threads that interact via a shared tuplespace, and discusses the idea of using function based objects as the basic unit of parallel execution, and the hierarchical structure to partition tuplespaces. It is argued that the two-level parallel execution, both within and between objects, are well suited to scalable parallel platforms with shared memory nodes connected by high speed networks.
The proceedings contain 23 papers. The special focus in this conference is on Discrete algorithms, programming Environments and Implementations. The topics include: parallel mesh generation;efficient massively paralle...
ISBN:
(纸本)3540631380
The proceedings contain 23 papers. The special focus in this conference is on Discrete algorithms, programming Environments and Implementations. The topics include: parallel mesh generation;efficient massively parallel quicksort;practical parallel list ranking;on computing all maximal cliques distributedly;a probabilistic model for best-first search BandB algorithms;programming irregular parallel applications in cilk;a variant of the biconjugate gradient method suitable for massively parallel computing;efficient implementation of the improved quasi-minimal residual method on massively distributed memory computers;programming with shared data abstractions;supporting run-time parallelization of DO-ACROSS loops on general networks of workstations;engineering diffusive load balancing algorithms using experiments;comparative study of static scheduling with task duplication for distributed systems;a new approximation algorithm for the register allocation problem;improving cache performance through tiling and data alignment;a support for non-uniform parallel loops and its application to a flame simulation code;performance otimization of combined variable-cost computations and I/O;parallel software caches;communication efficient parallel searching;parallel sparse cholesky factorization and unstructured graph partitioning for sparse linear system solving.
The proceedings contains 43 papers. Topics discussed include instruction level parallelism and wide buses, collective input-output performance, caches, scheduling and processor assignment, parallelarchitectures, obje...
详细信息
The proceedings contains 43 papers. Topics discussed include instruction level parallelism and wide buses, collective input-output performance, caches, scheduling and processor assignment, parallelarchitectures, object-oriented programming, routing, synchronization, performance, prefetching, communication and multicasts, tree-based and semi-structured algorithms, distributed shared memory, compilers, hardware features, data placement and transformation and performance prediction and coding.
The proceedings contain 7 papers. The topics discussed include: high level architecture for simulation;DEVS formalism as a framework for advanced distributed simulation;simulation of fine-grained parallel algorithms w...
ISBN:
(纸本)0818677732
The proceedings contain 7 papers. The topics discussed include: high level architecture for simulation;DEVS formalism as a framework for advanced distributed simulation;simulation of fine-grained parallel algorithms with the ALT (animating language tools) system;event synchronization in multi-user virtual reality environments;feedback control in time warp synchronized parallel simulators;COVERS 3.0 - an object-oriented environment for modeling, simulation, and analysis of real-time concurrent systems;design and simulations of cellular neural-like associative memory;and design of high-speed parallel arithmetic algorithms and architectures.
Vector computers have been extensively used for years in matrix algebra to treat with large dense matrix problems. However, if matrices are sparse and we use special storage schemes for them, vectorization provides a ...
详细信息
Vector computers have been extensively used for years in matrix algebra to treat with large dense matrix problems. However, if matrices are sparse and we use special storage schemes for them, vectorization provides a poor performance due to the great amount of indirections in the code. An alternative option is the utilization of a multiprocessor (or a cluster of workstations);in this case, a data parallelprogramming model also fails because of the reason pointed out for vector computers. Therefore, the best choice is to parallelize the corresponding algorithms using message passing routines. In order to discuss these features, we will focus on solving sparse linear least squares problems, which appear in several scientific areas such as structural analysis, geodetic survey, molecular structure and many others. Experimental results are obtained for vector and parallel computer architectures.
Cilk is a parallelprogramming language that allows programmers to write multithreaded parallel programs that use computational resources predictably and efficiently. The Cilk language allows programmers to specify th...
详细信息
The proceedings contains 80 papers from the Fourth international Conference on High Performance Computing. Topics discussed include: database management systems (DBMS);data migration and caching;algorithms;programming...
详细信息
The proceedings contains 80 papers from the Fourth international Conference on High Performance Computing. Topics discussed include: database management systems (DBMS);data migration and caching;algorithms;programming and languages;load balancing and scheduling;reconfigurable custom computing;routing;instruction level parallelism (ILP) architectures and compiler issues;parallel input/output and multithreaded systems;virtual channels;and image processing.
In this paper we describe algorithms for the ordering and numerical factorization step in parallel sparse Cholesky factorization. Direct methods for solving sparse positive definite systems play an important role in m...
详细信息
ISBN:
(纸本)3540631380
In this paper we describe algorithms for the ordering and numerical factorization step in parallel sparse Cholesky factorization. Direct methods for solving sparse positive definite systems play an important role in many scientific applications such as linear programming and structural engineering. The importance of direct methods is mainly due to their generality and robustness. The paper describes minimum degree and nested dissection based ordering methods and presents a scalable parallel algorithm for the factorization of sparse matrices. The interested reader will find many references to the relevant literature.
Koller and Megiddo introduced the paradigm of constructing compact distributions that satisfy a given set of constraints and showed how it can be used to efficiently derandomize certain types of algorithms, In this pa...
详细信息
Koller and Megiddo introduced the paradigm of constructing compact distributions that satisfy a given set of constraints and showed how it can be used to efficiently derandomize certain types of algorithms, In this paper, we significantly extend their results in two ways. First, we show how their approach can be applied to deal with more general expectation constraints. More importantly, we provide the first parallel (NC) algorithm for constructing a compact distribution that satisfies the constraints up to a small relative error. This algorithm deals with constraints over any event that can be verified by finite automata, including all independence constraints as well as constraints over events relating to the parity or sum of a certain set of variables. Our construction relies on a new and independently interesting parallel algorithm for converting a solution to a linear system into an almost basic approximate solution to the same system, We use these techniques in the first NC derandomization of an algorithm for constructing large independent sets in d-uniform hypergraphs for arbitrary d. We also show how the linear programming perspective suggests new proof techniques which might be useful in general probabilistic analysis. (C) 1997 Academic Press.
The proceedings contain 168 papers. The topics discussed include: static and dynamic data management in networks;iterative algorithms on high performance architectures;on correcting the intrusion of tracing non-determ...
ISBN:
(纸本)9783540634409
The proceedings contain 168 papers. The topics discussed include: static and dynamic data management in networks;iterative algorithms on high performance architectures;on correcting the intrusion of tracing non-deterministic programs by software;client server computing on message passing systems: experiences with PVM-RPC;minimal routing in the triangular grid and in a family of related tori;optimal gossip in store-and-forward noncombining 2-D tori;embedding and emulation results for static multichannel mesh of optical buses;finding a pair on a mesh with multiple broadcasting is hard;synchronising asynchronous communications;functional parallelprogramming with explicit processes: beyond SPMD;an efficient compilation framework for languages based on a concurrent process calculus;integrating an entry consistency memory model and concurrent object-oriented programming;and shared vs. snoop: evaluation of cache structure for single-chip multiprocessors.
暂无评论