Abstract
Current Monte Carlo neutron transport applications use continuous energy cross section data to provide the statistical foundation for particle trajectories. This “classical” algorithm requires storage and random access of very large data structures. Recently, Forget et al. [1] reported on a fundamentally new approach, based on multipole expansions, that distills cross section data down to a more abstract mathematical format. Their formulation greatly reduces memory storage and improves data locality at the cost of also increasing floating point computation. In the present study, we abstract the multipole representation into a “proxy application”, which we then use to determine the hardware performance parameters of the algorithm relative to the classical continuous energy algorithm. This study is done to determine the viability of both algorithms on current and next-generation high performance computing platforms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We estimate that for a robust depletion calculation, in excess of 100 GB of cross section data would be required [15].
- 2.
The 16-core Xeon node used in our testing features hardware threading, supporting up to 32 threads per node.
References
Forget, B., Xu, S., Smith, K.: Direct Doppler broadening in Monte Carlo simulations using the multipole representation. Ann. Nucl. Energy 64(C), 78–85 (2014)
Romano, P.K., Forget, B.: The OpenMC Monte Carlo particle transport code. Ann. Nucl. Energy 51, 274–281 (2013)
Romano, P.K., Forget, B., Brown, F.B.: Towards scalable parallelism in Monte Carlo particle transport codes using remote memory access, pp. 17–21 (2010)
Siegel, A.R., Smith, K., Romano, P.K., Forget, B., Felker, K.G.: Multi-core performance studies of a Monte Carlo neutron transport code. Int. J. High Perform. Comput. Appl. 28(1), 87–96 (2013)
Tramm, J., Siegel, A.R.: Memory bottlenecks and memory contention in multi-core Monte Carlo transport codes. In: Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo, Paris, October 2013. Argonne National Laboratory (2013)
Tramm, J.R., Siegel, A.R., Islam, T., Schulz, M.: XSBench - the development and verification of a performance abstraction for Monte Carlo reactor analysis. Presented at the PHYSOR 2014 - the role of reactor physics toward a sustainable future, Kyoto
Dosanjh, S., Barrett, R., Doerfler, D., Hammond, S., Hemmert, K., Heroux, M., Lin, P., Pedretti, K., Rodrigues, A., Trucano, T., Luitjens, J.: Exascale design space exploration and co-design. Future Gener. Comput. Syst. 30, 46–58 (2013)
Attig, N., Gibbon, P., Lippert, T.: Trends in supercomputing: the European path to exascale. Comput. Phys. Commun. 182(9), 2041–2046 (2011)
Rajovic, N., Vilanova, L., Villavieja, C., Puzovic, N., Ramirez, A.: The low power architecture approach towards exascale computing. J. Comput. Sci. 4, 439–443 (2013)
Engelmann, C.: Scaling to a million cores and beyond: using light-weight simulation to understand the challenges ahead on the road to exascale. Future Gener. Comput. Syst. 30, 59–65 (2013)
Romano, P.: OpenMC Monte Carlo code, January 2014. https://github.com/mit-crpg/openmc
Tramm, J.: XSBench: the Monte Carlo macroscopic cross section lookup benchmark, January 2014. https://github.com/jtramm/XSBench
Tramm, J.: RSBench: a mini-app to represent the multipole resonance representation lookup cross section algorithm, January 2014. https://github.com/jtramm/RSBench
Hoogenboom, J.E., Martin, W.R., Petrovic, B.: Monte Carlo performance benchmark for detailed power density calculation in a full size reactor core benchmark specifications. Ann. Arbor. 1001, 42104–48109 (2010)
Romano, P.K., Siegel, A.R., Forget, B., Smith, K.: Data decomposition of Monte Carlo particle transport simulations via tally servers. J. Comput. Phys. 252(C), 20–36 (2013)
Leppänen, J.: Two practical methods for unionized energy grid construction in continuous-energy Monte Carlo neutron transport calculation. Ann. Nucl. Energy 36(7), 878–885 (2009)
ICL: PAPI - performance application programming interface, September 2013. http://icl.cs.utk.edu/papi/index.html
Intel: Xeon processor e5–2650 cpu specifications, September 2013. http://ark.intel.com/products/64590/
McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. In: IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, December 1995, pp. 19–25 (1995)
Acknowledgments
This work was supported by the Office of Advanced Scientific Computing Research, Office of Science, U.S. Department of Energy, under Contract DE-AC02-06CH11357. The submitted manuscript has been created by the University of Chicago as Operator of Argonne National Laboratory (“Argonne”) under Contract DE-AC02-06CH11357 with the U.S. Department of Energy. The U.S. Government retains for itself, and others acting on its behalf, a paid-up, nonexclusive, irrevocable worldwide license in said article to reproduce, prepare derivative works, distribute copies to the public, and perform publicly and display publicly, by or on behalf of the Government.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Tramm, J.R., Siegel, A.R., Forget, B., Josey, C. (2015). Performance Analysis of a Reduced Data Movement Algorithm for Neutron Cross Section Data in Monte Carlo Simulations. In: Markidis, S., Laure, E. (eds) Solving Software Challenges for Exascale. EASC 2014. Lecture Notes in Computer Science(), vol 8759. Springer, Cham. https://doi.org/10.1007/978-3-319-15976-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-15976-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-15975-1
Online ISBN: 978-3-319-15976-8
eBook Packages: Computer ScienceComputer Science (R0)