Name
Title | ||
|---|---|---|
Modeling Dynamic Load Balancing in Molecular Dynamics to Achieve Scalable Parallel Execution |
Abstract | ||
|---|---|---|
To achieve scalable parallel performance in Molecular Dynamics Simulation, we have modeled and implemented several dynamic spatial domain decomposition algorithms. The modeling is based upon Valiant's Bulk Syn- chronous Parallel architecture model (BSP), which describes supersteps of com- putation, communication, and synchronization. We have developed prototypes that estimate the differing costs of several spatial decomposition algorithms us- ing the BSP model. Our parallel MD implementation is not bound to the limitations of the BSP model, allowing us to extend the spatial decomposition algorithm. For an initial decom- position, we use one of the successful decomposition strategies from the BSP study, and then subsequently use performance data to adjust the decomposition, dynamically improving the load balance. We report our results here. |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1007/BFb0018552 | IRREGULAR |
Keywords | Field | DocType |
parallel execution,molecular dynamics,modeling dynamic load,achieve scalable,molecular dynamic,domain decomposition,load balance | Synchronization,Computer simulation,Computer science,Load balancing (computing),Parallel computing,Molecular dynamics,Bulk synchronous parallel,Domain decomposition methods,Computation,Distributed computing,Scalability | Conference |
ISBN | Citations | PageRank |
3-540-64809-7 | 5 | 0.44 |
References | Authors | |
6 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lars S. Nyland | 1 | 59 | 6.26 |
| Jan Prins | 2 | 252 | 56.10 |
| Ru Huai Yun | 3 | 15 | 2.70 |
| Jan Hermans | 4 | 6 | 1.51 |
| Hye-Chung Kum | 5 | 114 | 12.99 |
| Lei Wang | 6 | 333 | 76.40 |