Name
Abstract | ||
|---|---|---|
We describe a highly optimized implementation of MPI domain decomposition in a GPU-enabled, general-purpose molecular dynamics code, HOOMD-blue (Anderson and Glotzer, 2013). Our approach is inspired by a traditional CPU-based code, LAMMPS (Plimpton, 1995), but is implemented within a code that was designed for execution on GPUs from the start (Anderson et al., 2008). The software supports short-ranged pair force and bond force fields and achieves optimal GPU performance using an autotuning algorithm. We are able to demonstrate equivalent or superior scaling on up to 3375 GPUs in Lennard-Jones and dissipative particle dynamics (DPD) simulations of up to 108 million particles. GPUDirect RDMA capabilities in recent GPU generations provide better performance in full double precision calculations. For a representative polymer physics application, HOOMD-blue 1.0 provides an effective GPU vs. CPU node speed-up of 12.5×. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.cpc.2015.02.028 | Computer Physics Communications |
Keywords | Field | DocType |
Multi-GPU,Molecular dynamics,MPI/CUDA,Strong scaling,Weak scaling,Domain decomposition,LAMMPS | Dissipative particle dynamics,Computer science,CUDA,Parallel computing,Double-precision floating-point format,Computational science,Software,Remote direct memory access,Code (cryptography),Scaling,Domain decomposition methods | Journal |
Volume | ISSN | Citations |
192 | 0010-4655 | 31 |
PageRank | References | Authors |
1.63 | 11 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jens Glaser | 1 | 31 | 1.63 |
| Trung Dac Nguyen | 2 | 46 | 3.70 |
| Joshua A. Anderson | 3 | 309 | 30.04 |
| Pak Lui | 4 | 67 | 4.65 |
| Filippo Spiga | 5 | 46 | 3.45 |
| Jaime A. Millan | 6 | 31 | 1.63 |
| David C. Morse | 7 | 31 | 1.63 |
| Sharon C. Glotzer | 8 | 104 | 14.69 |