A fast algorithm for particle simulations
Journal of Computational Physics
Parallel hierarchical N-body methods
Parallel hierarchical N-body methods
Astrophysical N-body simulations using hierarchical tree data structures
Proceedings of the 1992 ACM/IEEE conference on Supercomputing
An atomic model for message-passing
SPAA '93 Proceedings of the fifth annual ACM symposium on Parallel algorithms and architectures
Parallel hierarchical N-body methods and their implications for multiprocessors
Parallel hierarchical N-body methods and their implications for multiprocessors
A parallel hashed Oct-Tree N-body algorithm
Proceedings of the 1993 ACM/IEEE conference on Supercomputing
Experiences with parallel N-body simulation
SPAA '94 Proceedings of the sixth annual ACM symposium on Parallel algorithms and architectures
Fast algorithms for N-body simulations
Fast algorithms for N-body simulations
Experiences with Parallel N-Body Simulation
IEEE Transactions on Parallel and Distributed Systems
Solving irregularly structured problems based on distributed object model
Parallel Computing - Special issue: Parallel and distributed scientific and engineering computing
Hi-index | 0.00 |
This paper describes an implementation of a platform-independent parallel C++ N-body framework that can support various scientific simulations that involve tree structures, such as astrophysics, semiconductor device simulation, molecular dynamics, plasma physics, and fluid mechanics. Within the framework the users will be able to concentrate on the computation kernels that differentiate different N-body problems, and let the framework take care of the tedious and error-prone details that are common among N-body applications. %In addition, we will use MPI to implement the communication routines so %that the framework will be portable across many parallel platforms, %including massively parallel processors and workstation clusters. This framework was developed based on the techniques we learned from previous CM-5 C implementations, which have been rigorously justified both experimentally and mathematically. This gives us confidence that our framework will allow fast prototyping of different N-body applications, to run on different parallel platforms, and to deliver good performance as well.