Non-Algorithmic Load Imbalance Effects for Domain Decomposition Methods on a Hypercube
نویسندگان
چکیده
In this paper we discuss the effects of non-algorithmic load imbalance for three synchronization structures which appear in different algorithms using domain decomposition methods for solving PDE's on a hypercube machine. The synchronization structures are determined from the conditions related to the partitioning of a hypercube. To characterize the load imbalance effects we introduce a factor 'V defined as the ratio of the load imbalance costs to the total parallel execution time in absence of any load imbalance. We develop non-deterministic models for SPMD (Same Program Multiple Data) execution model and compute the 'V factor for the three structures, for different types of distributions of the execution time.
منابع مشابه
Weighted Decomposition in High-Performance Lattice-Boltzmann Simulations: Are Some Lattice Sites More Equal than Others?
Obtaining a good load balance is a significant challenge in scaling up lattice-Boltzmann simulations of realistic sparse problems to the exascale. Here we analyze the effect of weighted decomposition on the performance of the HemeLB lattice-Boltzmann simulation environment, when applied to sparse domains. Prior to domain decomposition, we assign wall and in/outlet sites with increased weights w...
متن کاملDynamic Domain Decomposition and Load Balancing in Parallel Simulation of Finite/discrete Elements
A dynamic domain decomposition strategy is proposed for the effective parallel implementation of combined finite/discrete element approaches. Attention is focused on the parallelised interaction detection between discrete objects. Issues including graph representation, initial partitioning and dynamic re-partitioning are discussed and a load imbalance detection and re-balancing scheme is also s...
متن کاملA Parallel DSMC Implementation on Unstructured
The direct simulation Monte Carlo (DSMC) method is versatile computational technique suitable for the simulation of a wide range of gas ows. It can deal with thermo-chemical non-equilibrium eeects with relative ease. However its computational cost has limited its application to rareeed or simple transitional ows. However DSMC is well suited to implementation on powerful multi-processor architec...
متن کاملBalancing Load versus Decreasing Communication: Parameterizing the Tradeoff
Domain decomposition is an important step for parallel scienti c applications, in particular nite element analyses. A good decomposition will minimize both the time spent on local computation and on interprocessor communication. It is often the case that these two goals cannot be satis ed simultaneously. In this paper, we use analytical and experimental results to illustrate the importance of c...
متن کامل