Algorithm for the replica redistribution in the implementation of parallel annealing method on the hybrid supercomputer architecture
arXiv:2006.00561 · doi:10.1016/j.cpc.2020.107786
Abstract
The parallel annealing method is one of the promising approaches for large scale simulations as potentially scalable on any parallel architecture. We present an implementation of the algorithm on the hybrid program architecture combining CUDA and MPI. The problem is to keep all general-purpose graphics processing unit devices as busy as possible redistributing replicas and to do that efficiently. We provide details of the testing on Intel Skylake/Nvidia V100 based hardware running in parallel more than two million replicas of the Ising model sample. The results are quite optimistic because the acceleration grows toward the perfect line with the growing complexity of the simulated system.
arXiv comment9 pages, 5 figures
References in corpus (10)
- Population Annealing with Weighted Averages: A Monte Carlo Method for Rough Free Energy Landscapes
- GPU accelerated population annealing algorithm
- PRAND: GPU accelerated parallel random number generation library: Using most reliable algorithms and applying parallelism of modern GPUs and CPUs
- Optimization of population annealing Monte Carlo for large-scale spin-glass simulations
- Monte Carlo Methods for Rough Free Energy Landscapes: Population Annealing and Parallel Tempering
- RNGSSELIB: Program library for random number generation, SSE2 realization
- Accelerating molecular dynamics simulations with population annealing
- Population Annealing Simulations of a Binary Hard Sphere Mixture
- Exploring first-order phase transitions with population annealing
- RNGSSELIB: Program library for random number generation. More generators, parallel streams of random numbers and Fortran compatibility