Results 1  10
of
10
Multiphase Mesh Partitioning
 APPL. MATH. MODELLING
, 1999
"... We consider the loadbalancing problems which arise from parallel scientific codes containing multiple computational phases, or loops over subsets of the data, which are separated by global synchronisation points. We motivate, derive and describe the implementation of an approach which we refer to ..."
Abstract

Cited by 25 (9 self)
 Add to MetaCart
We consider the loadbalancing problems which arise from parallel scientific codes containing multiple computational phases, or loops over subsets of the data, which are separated by global synchronisation points. We motivate, derive and describe the implementation of an approach which we refer to as the multiphase mesh partitioning strategy to address such issues. The technique is tested on several examples of meshes, both real and artificial, containing multiple computational phases and it is demonstrated that our method can achieve high quality partitions where a standard mesh partitioning approach fails.
Partitioning Mapping of Unstructured Meshes to Parallel Machine Topologies
 Proc. Irregular '95: Parallel Algorithms for Irregularly Structured Problems, volume 980 of LNCS
, 1995
"... We give an overview of some strategies for mapping unstructured meshes onto processor grids. Sample results show that the mapping can make a considerable difference to the communication overhead in the parallel solution time, particularly as the number of processors increase. ..."
Abstract

Cited by 24 (7 self)
 Add to MetaCart
(Show Context)
We give an overview of some strategies for mapping unstructured meshes onto processor grids. Sample results show that the mapping can make a considerable difference to the communication overhead in the parallel solution time, particularly as the number of processors increase.
JOSTLE: Partitioning of Unstructured Meshes for Massively Parallel Machines
 Parallel Computational Fluid Dynamics: New Algorithms and Applications
, 1995
"... this paper we discuss the mesh partitioning problem in the light of the coming generation of massively parallel machines and the resulting implications for such algorithms ..."
Abstract

Cited by 21 (2 self)
 Add to MetaCart
(Show Context)
this paper we discuss the mesh partitioning problem in the light of the coming generation of massively parallel machines and the resulting implications for such algorithms
Dynamic Mesh Partitioning: A Unified Optimisation and LoadBalancing Algorithm
, 1995
"... A parallel method for dynamic partitioning of unstructured meshes is described. The method employs a new unified iterative optimisation technique which both balances the workload and attempts to minimise the interprocessor communications overhead. Experiments on a series of adaptively refined meshes ..."
Abstract

Cited by 14 (5 self)
 Add to MetaCart
A parallel method for dynamic partitioning of unstructured meshes is described. The method employs a new unified iterative optimisation technique which both balances the workload and attempts to minimise the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent quality to static partitioners (which do not reuse the existing partition) and much more quickly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners. Key words. graphpartitioning, unstructured meshes, dynamic loadbalancing. 1 Introduction The use of unstructured mesh codes on parallel machines can be one of the most efficient ways to solve large Computational Fluid Dynamics (CFD) and Computational Mechanics (CM) problems. Completely general geometries and complex behaviour can be readily modelled and, in principle, the inherent sparsit...
A Parallelisable Algorithm for Optimising Unstructured Mesh Partitions
 Math. Res. Rep., Univ. of
, 1995
"... A new method is described for optimising graph partitions which arise in mapping unstructured mesh calculations to parallel computers. The method employs a combination of iterative techniques to both evenly balance the workload and minimise the number and volume of interprocessor communications. I ..."
Abstract

Cited by 12 (4 self)
 Add to MetaCart
(Show Context)
A new method is described for optimising graph partitions which arise in mapping unstructured mesh calculations to parallel computers. The method employs a combination of iterative techniques to both evenly balance the workload and minimise the number and volume of interprocessor communications. It is designed to work efficiently in parallel as well as sequentially and can be applied directly to dynamically refined meshes. In addition, when combined with a fast direct partitioning technique (such as the Greedy algorithm) to give an initial partition, the resulting twostage process proves itself to be both a powerful and flexible solution to the static graphpartitioning problem. A clustering technique can also be employed to speed up the whole process. Experiments, on graphs with up to a million nodes, indicate that the resulting code is up to an order of magnitude faster than existing stateoftheart techniques such as Multilevel Recursive Spectral Bisection, whilst providing partitions of equivalent quality.
Evaluation of the JOSTLE mesh partitioning code for practical multiphysics applications
, 1996
"... this paper we present results obtained by the JOSTLE procedure for parallel multiphysics applications on unstructured meshes. ..."
Abstract

Cited by 9 (9 self)
 Add to MetaCart
this paper we present results obtained by the JOSTLE procedure for parallel multiphysics applications on unstructured meshes.
A Scalable Strategy for the Parallelization of Multiphysics Unstructured MeshIterative Codes on DistributedMemory Systems
 Int. J. High Perform. Comput. Appl
, 2000
"... This paper describes the parallelization strategy pursued to deliver highefficiency parallel operation for multiphysics codes, involving fluids interacting with solids and using iterative procedures over an unstructured mesh ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
(Show Context)
This paper describes the parallelization strategy pursued to deliver highefficiency parallel operation for multiphysics codes, involving fluids interacting with solids and using iterative procedures over an unstructured mesh
MESHITERATIVE CODES ON DISTRIBUTEDMEMORY SYSTEMS
"... Realizing scalable performance on high performance computing systems is not straightforward for singlephenomenon codes (such as computational fluid dynamics [CFD]). This task is magnified considerably when the target software involves the interactions of a range of phenomena that have distinctive s ..."
Abstract
 Add to MetaCart
(Show Context)
Realizing scalable performance on high performance computing systems is not straightforward for singlephenomenon codes (such as computational fluid dynamics [CFD]). This task is magnified considerably when the target software involves the interactions of a range of phenomena that have distinctive solution procedures involving different discretization methods. The problems of addressing the key issues of retaining data integrity and the ordering of the calculation procedures are significant. A strategy for parallelizing this multiphysics family of codes is described for software exploiting finitevolume discretization methods on unstructured meshes using iterative solution procedures. A mesh partitioningbased SPMD approach is used. However, since different variables use distinct discretization schemes, this means that
Communication Latency Hiding in a Parallel Conjugate Gradient Method
"... Introduction The diagonally preconditioned Conjugate Gradient Method (CGM) is commonly used in a range of applications for the iterative solution of Ax = b. The method lends itself to parallelisation by Domain Decomposition (DD) using a Single Program MultiData (SPMD) mapping onto Distributed Memo ..."
Abstract
 Add to MetaCart
Introduction The diagonally preconditioned Conjugate Gradient Method (CGM) is commonly used in a range of applications for the iterative solution of Ax = b. The method lends itself to parallelisation by Domain Decomposition (DD) using a Single Program MultiData (SPMD) mapping onto Distributed Memory (DM) parallel platforms. While it is possible to achieve good parallel performance it is often the case that performance is limited by the communication performance of the parallel system. Performance of the parallel CGM method can be improved by reducing the impact of communication startup latency and finite interprocessor communication bandwidth without modification of the algorithm. This invites an examination of the factors affecting parallel performance. Unstructured mesh applications using Finite Element or Finite Volume techniques to solve differential equations with iterative solution procedures are commonly parallelised using overlapping