| Issue |
2014
SNA + MC 2013 - Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo
|
|
|---|---|---|
| Article Number | 04212 | |
| Number of page(s) | 10 | |
| Section | 4. Advanced Parallelism and HPC Strategies: b. Monte Carlo Methods, Parallelism and HPC | |
| DOI | https://doi.org/10.1051/snamc/201404212 | |
| Published online | 06 June 2014 | |
SNA + MC 2013, 04212 (2014)
Optimization of Monte Carlo Algorithms and Ray Tracing on GPUs
Nuclear Engineering Department, UC Berkeley, Berkeley, CA 94703-1730
* Corresponding Author, e-mail: rmb@berkeley.edu
To take advantage of the computational power of GPUs, algorithms that work well on CPUs must be modified to conform to the GPU execution model. In this study, typical task-parallel Monte Carlo algorithms have been reformulated in a data-parallel way, and the benefits of doing so are examined. In-progress 3D ray tracing work is also touched upon as a milestone in developing a full-featured neutron transport code. Possible solutions to problems are examined.
Key words: GPU / ray tracing / neutron transport / reactor simulation / data parallel / remapping
© Owned by the authors, published by EDP Sciences, 2014