Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SUNDIALS Time Integrators for Exascale Applications with Many Independent ODE Systems (2405.01713v1)

Published 2 May 2024 in math.NA, cs.DC, and cs.NA

Abstract: Many complex systems can be accurately modeled as a set of coupled time-dependent partial differential equations (PDEs). However, solving such equations can be prohibitively expensive, easily taxing the world's largest supercomputers. One pragmatic strategy for attacking such problems is to split the PDEs into components that can more easily be solved in isolation. This operator splitting approach is used ubiquitously across scientific domains, and in many cases leads to a set of ordinary differential equations (ODEs) that need to be solved as part of a larger "outer-loop" time-stepping approach. The SUNDIALS library provides a plethora of robust time integration algorithms for solving ODEs, and the U.S. Department of Energy Exascale Computing Project (ECP) has supported its extension to applications on exascale-capable computing hardware. In this paper, we highlight some SUNDIALS capabilities and its deployment in combustion and cosmology application codes (Pele and Nyx, respectively) where operator splitting gives rise to numerous, small ODE systems that must be solved concurrently.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. In: 2021 12th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA). IEEE, pp. 35–43.
  2. Astrophysical Journal 765(1): 39. 10.1088/0004-637X/765/1/39.
  3. ACM Transactions on Mathematical Software 48(1): 1–33. 10.1145/3480935.
  4. Parallel Computing 108: 102836.
  5. Monthly Notices of the Royal Astronomical Society 518(3): 3754–3776. 10.1093/mnras/stac3294.
  6. Colella P and Woodward P (1984) The piecewise parabolic method (ppm) for gas-dynamical simulations. Journal of Computational Physics 54(1): 174–201. 10.1016/0021-9991(84)90143-8.
  7. Journal of Open Source Software 8(90): 5450. 10.21105/joss.05450.
  8. Exascale Computing Project (2023) Exascale computing project. URL https://www.exascaleproject.org/. Last accessed 11-09-23.
  9. ACM Transactions on Mathematical Software (TOMS) 48(3): 1–24.
  10. Combust. Sci. Tech. 60: 167.
  11. The International Journal of High Performance Computing Applications 37(2): 115–131. 10.1177/10943420221121151.
  12. ACM Transactions on Mathematical Software (TOMS) 31(3): 363–396.
  13. Lapointe S, Mondal S and Whitesides RA (2020) Data-driven selection of stiff chemistry ODE solver in operator-splitting schemes. Combustion and Flame 220: 133–143.
  14. McLachlan RI and Quispel GRW (2002) Splitting methods. Acta Numerica 11: 341–434. 10.1017/S0962492902000053.
  15. NERSC (2023) NERSC documentation. URL https://docs.nersc.gov/systems/perlmutter/architecture/. Last accessed 11-09-23.
  16. Niemeyer K and Sung CJ (2014) Accelerating moderately stiff chemical kinetics in reactive-flow simuations using gpus. Journal of Computational Physics 256: 854–871. 10.1016/j.jcp.2013.09.025.
  17. NVIDIA (2024) cuSPARSE. URL https://developer.nvidia.com/cusparse. Last accessed 02-08-24.
  18. Nyx (2023) An adaptive mesh, n-body hydro cosmological simulation code. https://github.com/AMReX-Astro/Nyx.
  19. Oñorbe J, Hennawi JF and Lukić Z (2017) Self-consistent Modeling of Reionization in Cosmological Hydrodynamical Simulations. Astrophysical Journal 837(2): 106. 10.3847/1538-4357/aa6031.
  20. OLCF (2023a) Frontier User Guide. URL https://docs.olcf.ornl.gov/systems/frontier_user_guide.html#. Last accessed 11-09-23.
  21. OLCF (2023b) Summit User Guide. URL https://docs.olcf.ornl.gov/systems/summit_user_guide.html#. Last accessed 11-09-23.
  22. Pele (2023) Suite of tools for AMR simulation of reacting flows. https://github.com/amrex-combustion.
  23. ACM Transactions on Mathematical Software 49(2): 1–26.
  24. Saad Y (2003) Iterative methods for sparse linear systems. SIAM.
  25. Journal of Open Source Software 6(63): 3068. 10.21105/joss.03068.
  26. Stone C and Davis R (2013) Techniques for solving stiff chemical kinetics on gpus. In: 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. p. 369.
  27. Tomov S, Dongarra J and Baboulin M (2010) Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Computing 36(5-6): 232–240. 10.1016/j.parco.2009.12.005.
  28. TOP500 (2023) The 500 most powerful computer systems. https://www.top500.org.
  29. Fuel 191: 339–349.
  30. Journal of Open Source Software 4(37): 1370. 10.21105/joss.01370.
  31. The International Journal of High Performance Computing Applications 35(6): 508–526.
  32. Astrophysical Journal 886(2): 105. 10.3847/1538-4357/ab4e1d.
  33. Astrophysical Journal 936(1): 6. 10.3847/1538-4357/ac8478.
Citations (1)

Summary

We haven't generated a summary for this paper yet.