Results 1 
7 of
7
Performance Evaluation of Load Distribution Strategies in Parallel Branch and Bound Computations
 in Parallel Branch and Bound Computations Proc. 7th Symposium on Parallel and Distributed Processing (SPDP'95
, 1995
"... Load distribution is essential for efficient use of processors in parallel branchandbound computations because the computation generates and consumes nonuniform subproblems at runtime. This paper presents six decentralized load distribution strategies. They are incorporated in a runtime support s ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
Load distribution is essential for efficient use of processors in parallel branchandbound computations because the computation generates and consumes nonuniform subproblems at runtime. This paper presents six decentralized load distribution strategies. They are incorporated in a runtime support system, and evaluated in the solution of set partitioning problems on two parallel computer systems. It is observed that local averaging strategies outperform the randomized allocation and the Acwn algorithm significantly in large scale system. They lead to an almost linear speedup in a PowerPCbased system with up to 32 nodes and to a speedup of 146.8 in a Transputerbased system with 256 nodes. It is also observed that the randomized allocation and the Acwn algorithm can be improved by 10% to 15% when the subproblem bound information is used in the decisionmaking. 1 Introduction Branchandbound is a wellknown technique for solving combinatorial search problems [4]. Its basic scheme is t...
Parallel Scalable Libraries and Algorithms for Computer Vision
, 1994
"... We describe a project that integrates applications requirements, parallel algorithm design, models of parallel computing, and software tools in order to improve the ability of applications researchers in the fields of computer vision and image processing (CVIP) to realize the performance potential o ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
We describe a project that integrates applications requirements, parallel algorithm design, models of parallel computing, and software tools in order to improve the ability of applications researchers in the fields of computer vision and image processing (CVIP) to realize the performance potential of high performance parallel computers. This objective is achieved by pursuing four directions of research: the development of efficient and practical scalable algorithms for fundamental CVIP problems; the implementation of realistic CVIP scenarios on high performance computers; the development of a scalable, architectureindependent parallel model and a metric for estimating the performance of an algorithm on an existing parallel machine; and the development of prototype software tools. In this paper we describe work in each of these areas. 1 Introduction The goal of this project is to develop both theory and tools to make scalable high performance parallel computing more readily available ...
A Case Study of Load Distribution in Parallel View Frustum Culling and Collision Detection
 Lecture Notes in Computer Science
, 2001
"... When parallelizing hierarchical view frustum culling and collision detection, the low computation cost per node and the fact that the traversal path through the tree structure is not known a priori make the classical loadbalance versus communication tradeo# very challenging. ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
When parallelizing hierarchical view frustum culling and collision detection, the low computation cost per node and the fact that the traversal path through the tree structure is not known a priori make the classical loadbalance versus communication tradeo# very challenging.
11 P2P B&B and GA for the FlowShop Scheduling Problem
"... Summary. Solving exactly Combinatorial Optimization Problems (COPs) using a BranchandBound algorithm (B&B) requires a huge amount of computational resources. The efficiency of such algorithm can be improved by its hybridization with metaheuristics such as Genetic Algorithms (GA) which proved thei ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Summary. Solving exactly Combinatorial Optimization Problems (COPs) using a BranchandBound algorithm (B&B) requires a huge amount of computational resources. The efficiency of such algorithm can be improved by its hybridization with metaheuristics such as Genetic Algorithms (GA) which proved their effectiveness, since they generate acceptable solutions in a reasonable time. Moreover, distributing at large scale the computation, using for instance PeertoPeer (P2P) Computing, provides an efficient way to reach high computing performance. In this chapter, we propose ParallelBB and ParallelGA, which are P2Pbased parallelization of the B&B and GA algorithms for the computational Grid. The two algorithms have been implemented using the ProActive distributed object Grid middleware. The algorithms have been applied to a monocriterion permutation flowshop scheduling problem and promisingly experimented on the Grid5000 computational Grid.
Parallel and Distributed BranchandBound/A* Algorithms
, 1994
"... In this report, we propose new concurrent data structures and load balancing strategies for BranchandBound (B&B)/A* algorithms in two models of parallel programming : shared and distributed memory. For the shared memory model (SMM), we present a general methodology which allows concurrent manipul ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
In this report, we propose new concurrent data structures and load balancing strategies for BranchandBound (B&B)/A* algorithms in two models of parallel programming : shared and distributed memory. For the shared memory model (SMM), we present a general methodology which allows concurrent manipulations for most tree data structures, and show its usefulness for implementation on multiprocessors with global shared memory. Some priority queues which are suited for basic operations performed by B&B algorithms are described : the Skewheaps, the funnels and the Splaytrees. We also detail a specific data structure, called treap and designed for A* algorithm. These data structures are implemented on a parallel machine with shared memory : KSR1. For the distributed memory model (DMM), we show that the use of partial cost in the B&B algorithms is not enough to balance nodes between the local queues. Thus, we introduce another notion of priority, called potentiality, between nodes that take...
Developing Scheduling Algorithms to Access the Critical Section in SharedMemory Parallel Computers
, 1997
"... ree of interactions among the concurrent processes. A sharedmemory multiprocessor machine consists of two main parts: a set of independent processors and a global shared memory. The global memory contains a set of modules connected to and shared by all processors through a shared highspeed bus. ..."
Abstract
 Add to MetaCart
ree of interactions among the concurrent processes. A sharedmemory multiprocessor machine consists of two main parts: a set of independent processors and a global shared memory. The global memory contains a set of modules connected to and shared by all processors through a shared highspeed bus. In sharedmemory multiprocessor computer, we face a critical resource constraint, namely, the shared memory. This resource constraint can inhibit the efficient cooperation of the parallel processors to exchange the partial results needed to solve a problem. In such environment, shared variables are used to facilitate communication between concurrent processes. But these shared variables must be protected from nondeterminism, which can result from concurrent access by more than one process at a time. These shared variables can be protected from nondeterminism by placing the code that uses them in a critical section that can be executed by only one process at a time. Unfortunately, accessing t
Reporting Computational Experiments . . .
 ORSA JOURNAL ON COMPUTING
, 1992
"... Accompanying the increasing availability of parallel computing technology is a corresponding growth of research into the development, implementation, and testing of parallel algorithms. This paper examines issues involved in reporting on the empirical testing of parallel mathematical programming alg ..."
Abstract
 Add to MetaCart
Accompanying the increasing availability of parallel computing technology is a corresponding growth of research into the development, implementation, and testing of parallel algorithms. This paper examines issues involved in reporting on the empirical testing of parallel mathematical programming algorithms, both optimizing and heuristic. We examine the appropriateness of various performance metrics and explore the effects of testing variability, machine influences, testing biases, and the effects of tuning parameters. Some of these difficulties were explored further in a survey sent to leading computational mathematical programming researchers for their reactions and suggestions. A summary of the survey and proposals for conscientious reporting are presented.