A Framework for Transparent Load Balancing in Parallel Numerical Simulation
نویسندگان
چکیده
Load imbalance is the most important factor that limits scalability of parallel applications in scientific computing. Dynamic load balancing at the application level usually is implemented in a proprietary manner. This paper presents a generic framework for application level dynamic load balancing. Our framework can be applied to any grid-based iterative numerical simulation. It defines a programming model that is tailored to the specific requirements of this class of applications and that provides a unique API for shared and distributed memory systems and combinations thereof. Load balancing can be implemented totally transparent to the application. The framework also provides an interface to application developers who wish to steer load balancing based on their specific knowledge of the computation. Third party repartitioning software can be integrated easily. We apply our framework to PAM-CRASH, an industrial crash simulation software marketed by ESI that is widely used in the automotive industry. Our project results are evaluated at BMW’s crash simulation department on a network of SGI cc-NUMA systems.
منابع مشابه
Large-scale Parallel Discrete Element Simulations of Granular Flow
We present large-scale parallel direct numerical simulations of granular flow using a novel, portable software program for Discrete Element Method (DEM) simulations. Since particle methods provide a unifying framework for both discrete and continuous systems, we base the program on the ppm library [1], which has already been demonstrated to provide transparent parallelization and state-of-thear...
متن کاملPLUM: Parallel Load Balancing for Adaptive Unstructured Meshes
Mesh adaption is a powerful tool for eecient unstructured-grid computations but causes load imbalance among processors on a parallel machine. We present a novel method called PLUM to dynamically balance the processor workloads with a global view. This paper describes the implementation and integration of all major components within our dynamic load balancing strategy for adaptive grid calculati...
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 کاملParleda: a Library for Parallel Processing in Computational Geometry Applications
ParLeda is a software library that provides the basic primitives needed for parallel implementation of computational geometry applications. It can also be used in implementing a parallel application that uses geometric data structures. The parallel model that we use is based on a new heterogeneous parallel model named HBSP, which is based on BSP and is introduced here. ParLeda uses two main lib...
متن کاملShape optimizing load balancing for MPI-parallel adaptive numerical simulations
Load balancing is important for the efficient execution of numerical simulations on parallel computers. In particular when the simulation domain changes over time, the mapping of computational tasks to processors needs to be modified accordingly. Most state-of-the-art libraries addressing this problem are based on graph repartitioning with a parallel variant of the Kernighan-Lin (KL) heuristic....
متن کامل