Home  About us  Contact
 

Parallel Machines (parallel + machines)

Distribution by Scientific Domains
Engineering16%

Selected Abstracts

Micro-mechanical simulation of geotechnical problems using massively parallel computers

INTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS, Issue 14 2003
David W. Washington
Abstract This paper demonstrates that the architecture of a massively parallel computer can be adapted for micro-mechanical simulations of a Geotechnical problem. The Discrete Element Method was used on a massively parallel supercomputer to simulate Geotechnical boundary value problems. For the demonstration, a triaxial test was simulated using an algorithm titled ,TRUBAL for Parallel Machines (TPM)' based on the discrete element method (DEM). In this trial demonstration, the inherent parallelism within DEM algorithm is shown. Then a comparison is made between the parallel algorithm (TPM) and the serial algorithm (TRUBAL) to show the benefits of this research. TPM showed substantial improvement in performance with increasing number of processors when compared with TRUBAL using single processor. Copyright © 2003 John Wiley & Sons, Ltd. [source]

Parallelization and scalability of a spectral element channel flow solver for incompressible Navier,Stokes equations

CONCURRENCY AND COMPUTATION: PRACTICE & EXPERIENCE, Issue 10 2007
C. W. Hamman
Abstract Direct numerical simulation (DNS) of turbulent flows is widely recognized to demand fine spatial meshes, small timesteps, and very long runtimes to properly resolve the flow field. To overcome these limitations, most DNS is performed on supercomputing machines. With the rapid development of terascale (and, eventually, petascale) computing on thousands of processors, it has become imperative to consider the development of DNS algorithms and parallelization methods that are capable of fully exploiting these massively parallel machines. A highly parallelizable algorithm for the simulation of turbulent channel flow that allows for efficient scaling on several thousand processors is presented. A model that accurately predicts the performance of the algorithm is developed and compared with experimental data. The results demonstrate that the proposed numerical algorithm is capable of scaling well on petascale computing machines and thus will allow for the development and analysis of high Reynolds number channel flows. Copyright © 2007 John Wiley & Sons, Ltd. [source]

Parallel protein folding with STAPL

CONCURRENCY AND COMPUTATION: PRACTICE & EXPERIENCE, Issue 14 2005
Shawna Thomas
Abstract The protein-folding problem is a study of how a protein dynamically folds to its so-called native state,an energetically stable, three-dimensional conformation. Understanding this process is of great practical importance since some devastating diseases such as Alzheimer's and bovine spongiform encephalopathy (Mad Cow) are associated with the misfolding of proteins. We have developed a new computational technique for studying protein folding that is based on probabilistic roadmap methods for motion planning. Our technique yields an approximate map of a protein's potential energy landscape that contains thousands of feasible folding pathways. We have validated our method against known experimental results. Other simulation techniques, such as molecular dynamics or Monte Carlo methods, require many orders of magnitude more time to produce a single, partial trajectory. In this paper we report on our experiences parallelizing our method using STAPL (Standard Template Adaptive Parallel Library) that is being developed in the Parasol Lab at Texas A&M. An efficient parallel version will enable us to study larger proteins with increased accuracy. We demonstrate how STAPL enables portable efficiency across multiple platforms, ranging from small Linux clusters to massively parallel machines such as IBM's BlueGene/L, without user code modification. Copyright © 2005 John Wiley & Sons, Ltd. [source]

A parallel cell-based DSMC method on unstructured adaptive meshes

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, Issue 12 2004
Min Gyu Kim
Abstract A parallel DSMC method based on a cell-based data structure is developed for the efficient simulation of rarefied gas flows on PC-clusters. Parallel computation is made by decomposing the computational domain into several subdomains. Dynamic load balancing between processors is achieved based on the number of simulation particles and the number of cells allocated in each subdomain. Adjustment of cell size is also made through mesh adaptation for the improvement of solution accuracy and the efficient usage of meshes. Applications were made for a two-dimensional supersonic leading-edge flow, the axi-symmetric Rothe's nozzle, and the open hollow cylinder flare flow for validation. It was found that the present method is an efficient tool for the simulation of rarefied gas flows on PC-based parallel machines. Copyright © 2004 John Wiley & Sons, Ltd. [source]

Tight bounds for the identical parallel machine-scheduling problem: Part II

INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH, Issue 1 2008
Mohamed Haouari
Abstract A companion paper introduces new lower bounds and heuristics for the problem of minimizing makespan on identical parallel machines. The objective of this paper is threefold. First, we describe further enhancements of previously described lower bounds. Second, we propose a new heuristic that requires solving a sequence of 0,1 knapsack problems. Finally, we show that embedding these newly derived bounds in a branch-and-bound procedure yields a very effective exact algorithm. Moreover, this algorithm features a new symmetry-breaking branching strategy. We present the results of computational experiments that were carried out on a large set of instances and that attest to the efficacy of the proposed algorithm. In particular, we report proven optimal solutions for some benchmark problems that have been open for some time. [source]

Tight bounds for the identical parallel machine scheduling problem

INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH, Issue 6 2006
Mohamed Haouari
Abstract We address the problem of minimizing makespan on identical parallel machines. We propose new lower bounding strategies and heuristics for this fundamental scheduling problem. The lower bounds are based on the so-called lifting procedure. In addition, two optimization-based heuristics are proposed. These heuristics require iteratively solving a subset-sum problem. We present the results of computational experiments that provide strong evidence that the new proposed lower and upper bounds consistently outperform the best bounds from the literature. [source]

Capacitated lot-sizing and scheduling with parallel machines, back-orders, and setup carry-over

NAVAL RESEARCH LOGISTICS: AN INTERNATIONAL JOURNAL, Issue 4 2009
Daniel Quadt
Abstract We address the capacitated lot-sizing and scheduling problem with setup times, setup carry-over, back-orders, and parallel machines as it appears in a semiconductor assembly facility. The problem can be formulated as an extension of the capacitated lot-sizing problem with linked lot-sizes (CLSPL). We present a mixed integer (MIP) formulation of the problem and a new solution procedure. The solution procedure is based on a novel "aggregate model," which uses integer instead of binary variables. The model is embedded in a period-by-period heuristic and is solved to optimality or near-optimality in each iteration using standard procedures (CPLEX). A subsequent scheduling routine loads and sequences the products on the parallel machines. Six variants of the heuristic are presented and tested in an extensive computational study. © 2009 Wiley Periodicals, Inc. Naval Research Logistics 2009 [source]

Scheduling parallel machines with inclusive processing set restrictions

NAVAL RESEARCH LOGISTICS: AN INTERNATIONAL JOURNAL, Issue 4 2008
Jinwen Ou
Abstract We consider the problem of assigning a set of jobs to different parallel machines of the same processing speed, where each job is compatible to only a subset of those machines. The machines can be linearly ordered such that a higher-indexed machine can process all those jobs that a lower-indexed machine can process. The objective is to minimize the makespan of the schedule. This problem is motivated by industrial applications such as cargo handling by cranes with nonidentical weight capacities, computer processor scheduling with memory constraints, and grades of service provision by parallel servers. We develop an efficient algorithm for this problem with a worst-case performance ratio of + ,, where , is a positive constant which may be set arbitrarily close to zero. We also present a polynomial time approximation scheme for this problem, which answers an open question in the literature. © 2008 Wiley Periodicals, Inc. Naval Research Logistics, 2008 [source]

A branch-and-price algorithm for parallel machine scheduling with time windows and job priorities

NAVAL RESEARCH LOGISTICS: AN INTERNATIONAL JOURNAL, Issue 1 2006
Jonathan F. Bard
Abstract This paper presents a branch-and-price algorithm for scheduling n jobs on m nonhomogeneous parallel machines with multiple time windows. An additional feature of the problem is that each job falls into one of , priority classes and may require two operations. The objective is to maximize the weighted number of jobs scheduled, where a job in a higher priority class has "infinitely" more weight or value than a job in a lower priority class. The methodology makes use of a greedy randomized adaptive search procedure (GRASP) to find feasible solutions during implicit enumeration and a two-cycle elimination heuristic when solving the pricing subproblems. Extensive computational results are presented based on data from an application involving the use of communications relay satellites. Many 100-job instances that were believed to be beyond the capability of exact methods, were solved within minutes. © 2005 Wiley Periodicals, Inc. Naval Research Logistics, 2006 [source]

Multiple common due dates

NAVAL RESEARCH LOGISTICS: AN INTERNATIONAL JOURNAL, Issue 4 2001
Bernard Dickman
Abstract Common due date problems have been extensively discussed in the scheduling literature. Initially, these problems discussed finding a common due date for a set of jobs on a single machine. These single machine problems were later extended to finding the common due date on a set of parallel machines. This paper further extends the single machine problem to finding multiple common due dates on a single machine. For a basic and important class of penalty functions, we show that this problem is comparable to the parallel machine problem. © 2001 John Wiley & Sons, Inc. Naval Research Logistics 48: 293,298, 2001 [source]