Shared-Memory Implementation of an Irregular Particle Simulation Method
نویسندگان
چکیده
We investigate a parallel implementation of an irregular particle simulation algorithm. We concentrate on the issue which programming and system support is needed to yield an eecient implementation for a large number of processors. As execution platform we use the SB-PRAM, a shared memory machine with up to 4096 processors.
منابع مشابه
Implementation of D3Q19 Lattice Boltzmann Method with a Curved Wall Boundary Condition for Simulation of Practical Flow Problems
In this paper, implementation of an extended form of a no-slip wall boundary condition is presented for the three-dimensional (3-D) lattice Boltzmann method (LBM) for solving the incompressible fluid flows with complex geometries. The boundary condition is based on the off-lattice scheme with a polynomial interpolation which is used to reconstruct the curved or irregular wall boundary on the ne...
متن کاملA Shared - Memory Implementation of theHierarchical
The radiosity method is a simulation method from computer graphics to visualize the global illumination in scenes containing diiuse objects within an enclosure. A variety of realizations (including parallel approaches) were proposed to achieve a high eeciency while guaranteeing the same accuracy of the graphical representation. The hierarchical radiosity method reduces the computational costs c...
متن کاملMpi+openmp Implementation of Memory-saving Parallel Pic Applications on Hierarchical Distributed-shared Memory Architectures
The combination of inter-node and intra-node domaindecomposition strategies for the development of memorysaving parallel Particle-in-cell simulation codes, targeted to hierarchical distributed-shared memory architectures, is discussed in this paper, along with its MPI+OpenMP implementation. Particular emphasis is given to the devised dynamic workload balancing technique.
متن کاملcient Parallelization of Unstructured Reductions on Shared Memory Parallel Architectures ?
This paper presents a new parallelization method for an efcient implementation of unstructured array reductions on shared memory parallel machines with OpenMP. This method is strongly related to parallelization techniques for irregular reductions on distributed memory machines as employed in the context of High Performance Fortran. By exploiting data locality, synchronization is minimized witho...
متن کاملHierarchical MPI+OpenMP Implementation of Parallel PIC Applications on Clusters of Symmetric MultiProcessors
The hierarchical combination of decomposition strategies for the development of parallel Particle-in-cell simulation codes, targeted to hierarchical distributed-shared memory architectures, is discussed in this paper, along with its MPI+OpenMP implementation. Particular emphasis is given to the devised dynamic workload balancing technique.
متن کامل