Cluster Computing

, Volume 20, Issue 3, pp 2763–2777 | Cite as

Performance analysis and comparison of cellular automata GPU implementations

  • Emmanuel N. Millán
  • Nicolás Wolovick
  • María Fabiana Piccoli
  • Carlos García Garino
  • Eduardo M. Bringa


Cellular automata (CA) models are of interest to several scientific areas, and there is a growing interest in exploring large systems which would need high performance computing. In this work a CA implementation is presented which performs well in five different NVIDIA GPU architectures, from Tesla to Maxwell, simulating systems with up to a billion cells. Using the game of life (GoL) and a more complex variation of GoL as examples, a performance of 5.58e6 evaluated cells/s is achieved. The two optimizations most often used in previous studies are the use of shared memory and Multicell algorithms. Here, these optimizations do not improve performance in Fermi or newer architectures. The GoL CA code running in an NVIDIA Titan X obtained a speedup of up to \(\sim \)85 x and up to \(\sim \)230 x for a more complex CA, compared to an optimized serial CPU implementation. Finally, the efficiency of each GPU is analyzed in terms of cell performance/transistors and cell performance/bandwidth showing how the architectures improved for this particular problem.


Cellular automata Graphics processing unit Benchmarks Performance analysis 



The authors acknowledge support from CONICET, ANPCyT Grant PICT-2014-0696, and a SeCTyP UNCuyo Grant. This work used the clusters Mendieta from CCAD-UNC and ICB-ITIC from UNCuyo, which are part of the SNCAD network.


  1. 1.
    Aaby, B.G., Perumalla, K.S., Seal, S.K.: Efficient simulation of agent-based models on multi-GPU and multi-core clusters. In: Proceedings of the 3rd International ICST Conference on Simulation Tools and Techniques p. 29:1 (2010). doi: 10.4108/icst.simutools2010.8822
  2. 2.
    Balasalle, J., Lopez, M.A., Rutherford, M.J.: Optimizing memory access patterns for cellular. In: Hwu, W. (ed.) GPU Computing Gems Jade Edition, pp. 67–75. Morgan Kaufmann, Amsterdam (2011)Google Scholar
  3. 3.
    Bauer, M., Cook, H., Khailany, B.: Cudadma. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on—SC 11 p. 12 (2011). doi: 10.1145/2063384.2063400
  4. 4.
    Blecic, I., Cecchini, A., Trunfio, G.A.: Fast and accurate optimization of a GPU-accelerated ca urban model through cooperative coevolutionary particle swarms. Proc. Comput. Sci. 29, 1631–1643 (2014). doi: 10.1016/j.procs.2014.05.148 CrossRefGoogle Scholar
  5. 5.
    Brodtkorb, A.R., Dyken, C., Hagen, T.R., Hjelmervik, J.M., Storaasli, O.O.: State-of-the-art in heterogeneous computing. Sci. Program. 18(1), 1–33 (2010)Google Scholar
  6. 6.
    Brown, W.M., Wang, P., Plimpton, S.J., Tharrington, A.N.: Implementing molecular dynamics on hybrid high performance computers—short range forces. Comput. Phys. Commun. 182(4), 898–911 (2011). doi: 10.1016/j.cpc.2010.12.021
  7. 7.
    Browne, S., Dongarra, J., Garner, N., London, K., Mucci, P.: A scalable cross-platform infrastructure for application performance tuning using hardware counters. In: ACM/IEEE 2000 Conference on Supercomputing, p. 42. IEEE (2000)Google Scholar
  8. 8.
    Campos, R.S., Lobosco, M., dos Santos, R.W.: A GPU-based heart simulator with mass-spring systems and cellular automaton. J Supercomput 69(1), 1–8 (2014). doi: 10.1007/s11227-014-1199-5 CrossRefGoogle Scholar
  9. 9.
    Carozzani, T., Gandin, C.A., Digonnet, H.: Optimized parallel computing for cellular automaton finite element modeling of solidification grain structures. Modelling Simul. Mater. Sci. Eng. 22(1), 015,012 (2013). doi: 10.1088/0965-0393/22/1/015012 CrossRefGoogle Scholar
  10. 10.
    Caux, J., Hill David, R., Siregar, P.: Accelerating 3D Cellular automata computation with GP-GPU in the context of integrative biology. In: Cellular Automata—Innovative Modelling for Science and Engineering, pp. 411–426. InTech (2011).
  11. 11.
    Chen, S., Doolen, G.D.: Lattice Boltzmann method for fluid flows. Ann. Rev. Fluid Mech. 30(1), 329–364 (1998). doi: 10.1146/annurev.fluid.30.1.329 MathSciNetCrossRefGoogle Scholar
  12. 12.
    CUDA C Programming Guide, vol. 4.2. NVIDIA (2012).
  13. 13.
    CUDA C Programming Guide, vol. 7.0. NVIDIA (2015).
  14. 14.
    CUDA from NVIDIA.
  15. 15.
    Feichtinger, C., Habich, J., Kstler, H., Hager, G., Rde, U., Wellein, G.: A flexible patch-based lattice Boltzmann parallelization approach for heterogeneous GPU-CPU clusters. Parallal Comput. 37(9), 536–549 (2011). doi: 10.1016/j.parco.2011.03.005 MathSciNetCrossRefGoogle Scholar
  16. 16.
    Ferrero, E.E., De Francesco, J.P., Wolovick, N., Cannas, S.A.: q-state potts model metastability study using optimized GPU-based Monte Carlo algorithms. Comput. Phys. Commun. 183(8), 1578–1587 (2012). doi: 10.1016/j.cpc.2012.02.026 MathSciNetCrossRefGoogle Scholar
  17. 17.
    Ganguly, N., Sikdar, B.K., Deutsch, A., Canright, G., Chaudhuri, P.P.: A survey on cellular automata. Center for High Performance Computing, Dresden University of Technology (2003)., doi:
  18. 18.
    Gardner, M.: Mathematical games: the fantastic combinations of John Conway new solitaire game life. Sci. Am. 223(4), 120–123 (1970)CrossRefGoogle Scholar
  19. 19.
    Gibson, M.J., Keedwell, E.C., Savi, D.: Understanding the efficient parallelisation of cellular automata on CPU and GPGPU hardware. In: Proceeding of the Fifteenth Annual Conference Companion on Genetic and Evolutionary Computation Conference Companion—GECCO 13 Companion pp. 171–172 (2013). doi: 10.1145/2464576.2464660
  20. 20.
    Gibson, M.J., Keedwell, E.C., Savi, D.A.: An investigation of the efficient implementation of cellular automata on multi-core CPU and GPU hardware. J. Parallel Distrib. Comput. 77, 11–25 (2014). doi: 10.1016/j.jpdc.2014.10.011
  21. 21.
    Hawick, K.A., Johnson, M.G.: Bit-packed damaged lattice potts model simulations with cuda and gpus. In: Proceedings of International Conferences on Modelling, Simulation and Identification, pp. 371–378 (2011)Google Scholar
  22. 22.
    Hong, S., Kim, H.: An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. SIGARCH Comput. Archit. News 37(3), 152 (2009). doi: 10.1145/1555815.1555775 CrossRefGoogle Scholar
  23. 23.
    Kjolstad, F.B., Snir, M.: Ghost cell pattern. In: Proceedings of the 2010 Workshop on Parallel Programming Patterns, p. 4. ACM, New York (2010)Google Scholar
  24. 24.
    LAMMPS: Lennard Jones Liquid Benchmark.
  25. 25.
    Lee, C., Ro, W.W., Gaudiot, J.L.: Boosting CUDA applications with CPU-GPU hybrid computing. Int. J. Parallel Program. 42(2), 384–404 (2013). doi: 10.1007/s10766-013-0252-y CrossRefGoogle Scholar
  26. 26.
    Lindholm, E., Nickolls, J., Oberman, S., Montrym, J.: Nvidia tesla: a unified graphics and computing architecture. IEEE Micro 28(2), 39–55 (2008)CrossRefGoogle Scholar
  27. 27.
    Maruyama, N., Aoki, T.: Optimizing stencil computations for NVIDIA Kepler GPUs. In: Größlinger, A., Köstler, H. (eds.) Proceedings of the 1st International Workshop on High-Performance Stencil Computations, pp. 89–95. Austria, Vienna (2014)Google Scholar
  28. 28.
    Meng, J., Skadron, K.: Performance modeling and automatic ghost zone optimization for iterative stencil loops on GPUs. In: Proceedings of the 23rd International Conference on Conference on Supercomputing—ICS 09 pp. 256–265 (2009). doi: 10.1145/1542275.1542313
  29. 29.
    Millán, E.N., Bederian, C., Piccoli, M.F., García Garino, C., Bringa, E.M.: Performance analysis of cellular automata HPC implementations. Comput. Electr. Eng. 48, 12–24 (2015). doi: 10.1016/j.compeleceng.2015.09.015 CrossRefGoogle Scholar
  30. 30.
    Millán, E.N., Martínez, P.C., Gil Costa, G.V., Piccoli, M.F., Printista, A.M., Bederian, C., García Garino, C., Bringa, E.M.: Parallel implementation of a cellular automata in a hybrid CPU/GPU environment. In: A. De Giusti (ed.) XVIII Congreso Argentino de Ciencias de la Computación, pp. 184–193. Red de Universidades con Carreras en Informática RedUNCI (2013). ISBN 978-987-23963-1-2Google Scholar
  31. 31.
    Moore, N.: Kernel specialization for improved adaptability and performance on graphics processing units (gpus). Ph.D. thesis, Northeastern University Boston, MA (2012)Google Scholar
  32. 32.
    North, M.J., Collier, N.T., Ozik, J., Tatara, E.R., Macal, C.M., Bragen, M., Sydelko, P.: Complex adaptive systems modeling with repast simphony. Complex Adapt. Syst. Model. 1(1), 3 (2013). doi: 10.1186/2194-3206-1-3 CrossRefGoogle Scholar
  33. 33.
    NVIDIA: Whitepaper NVIDIA GeForce GTX 750 Ti, v1.1Google Scholar
  34. 34.
    NVIDIA: Whitepaper NVIDIA GeForce GTX 980, v1.1Google Scholar
  35. 35.
    NVIDIA: Whitepaper NVIDIAs Next Generation CUDA Compute Architecture: Fermi, v1.1Google Scholar
  36. 36.
    NVIDIA: Whitepaper NVIDIAs Next Generation CUDA Compute Architecture: Kepler GK110, v1.0Google Scholar
  37. 37.
    NVIDIA: Nvidia geforce 8800 gpu architecture overview. Technical brief, November 2006 (2006)Google Scholar
  38. 38.
    NVIDIA: Tuning Cuda Applications for Kepler, v7.0 (2015)Google Scholar
  39. 39.
    NVIDIA: Tuning Cuda Applications for Maxwell, v7.0 (2015)Google Scholar
  40. 40.
    NVIDIA: Nvidia geforce gtx 200 gpu architectural overview. Technical brief, May (2008)Google Scholar
  41. 41.
    Oxman, G., Weiss, S., Be’ery, Y.: Computational methods for conway’s game of life cellular automaton. J. Comput. Sci. 5(1), 24–31 (2014). doi: 10.1016/j.jocs.2013.07.005 MathSciNetCrossRefGoogle Scholar
  42. 42.
    Papadopoulou, M.M., Sadooghi-Alvandi, M., Wong, H.: Micro-benchmarking the GT200 GPU. Computer Group, ECE, University of Toronto, Technical Report (2009)Google Scholar
  43. 43.
    Perumalla, K.S., Aaby, B.G.: Data parallel execution challenges and runtime performance of agent simulations on gpus. In: Proceedings of the 2008 Spring Simulation Multiconference, SpringSim’08, pp. 116–123. Society for Computer Simulation International, San Diego, CA, USA (2008).
  44. 44.
    Pohl, T., Deserno, F., Thurey, N., Rude, U., Lammers, P., Wellein, G., Zeiser, T.: Performance evaluation of parallel large-scale lattice boltzmann applications on three supercomputing architectures. In: Proceedings of the ACM/IEEE SC2004 Conference p. 21 (2004). doi: 10.1109/sc.2004.37
  45. 45.
    Preis, T., Virnau, P., Paul, W., Schneider, J.J.: GPU accelerated Monte Carlo simulation of the 2D and 3D ising model. J. Comput. Phys. 228(12), 4468–4477 (2009). doi: 10.1016/ CrossRefzbMATHGoogle Scholar
  46. 46.
    RanjanNayak, D., Kumar Sahu, S., Mohammed, J.: A cellular automata based optimal edge detection technique using twenty-five neighborhood model. IJCA 84(10), 27–33 (2013). doi: 10.5120/14614-2869 CrossRefGoogle Scholar
  47. 47.
    Rapaport, D.: Enhanced molecular dynamics performance with a programmable graphics processor. Comput. Phys. Commun. 182(4), 926–934 (2011). doi: 10.1016/j.cpc.2010.12.029 CrossRefzbMATHGoogle Scholar
  48. 48.
    Rauch, L., Madej, L., Spytkowski, P., Golab, R.: Development of the cellular automata framework dedicated for metallic materials microstructure evolution models. Arch. Civil Mech. Eng. 15(1), 48–61 (2015). doi: 10.1016/j.acme.2014.06.006 CrossRefGoogle Scholar
  49. 49.
    Russo, L., Russo, P., Vakalis, D., Siettos, C.: Detecting weak points of wildland fire spread: a cellular automata model risk assessment simulation approach. Chem. Eng. 36, 253–258 (2014)Google Scholar
  50. 50.
    Rybacki, S., Himmelspach, J., Uhrmacher, A.M.: Experiments with single core, multi-core, and GPU based computation of cellular automata. In: First International Conference on Advances in System Simulation, 2009. SIMUL’09, pp. 62–67. IEEE (2009)Google Scholar
  51. 51.
    Ryoo, S., Rodrigues, C.I., Stone, S.S., Baghsorkhi, S.S., Ueng, S.Z., Stratton, J.A., Hwu, W.m.W.: Program optimization space pruning for a multithreaded gpu. In: Proceedings of the Sixth Annual IEEE/ACM International Symposium on Code Generation and Optimization—CGO 08 (2008). doi: 10.1145/1356058.1356084
  52. 52.
    Shimokawabe, T., Aoki, T., Takaki, T., Yamanaka, A., Nukada, A., Endo, T., Maruyama, N., Matsuoka, S.: Peta-scale phase-field simulation for dendritic solidification on the tsubame 2.0 supercomputer. In: 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1–11 (2011)Google Scholar
  53. 53.
    Smoller, J.: Shock waves and reaction-diffusion equations. In: Research Supported by the US Air Force and National Science Foundation, vol. 258. Springer, New York(Grundlehren der Mathematischen Wissenschaften, vol. 258), p. 600 (1983)Google Scholar
  54. 54.
    Topa, P.: Cellular automata model tuned for efficient computation on GPU with global memory cache. In: 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pp. 380–383 (2014). doi: 10.1109/pdp.2014.97
  55. 55.
    Topa, P., Młocek, P.: Using shared memory as a cache in cellular automata water flow simulations on gpus. Comput. Sci. 14, 3 (2013)Google Scholar
  56. 56.
    Top 500 supercomputers, list of june 2016.
  57. 57.
    Veerbeek, W., Pathirana, A., Ashley, R., Zevenbergen, C.: Enhancing the calibration of an urban growth model using a memetic algorithm. Comput. Environ. Urban Syst. 50, 53–65 (2015). doi: 10.1016/j.compenvurbsys.2014.11.003 CrossRefGoogle Scholar
  58. 58.
    Volkov, V.: Better performance at lower occupancy. In: Proceedings of the GPU Technology Conference, GTC, vol. 10 (2010)Google Scholar
  59. 59.
    Volkov, V., Demmel, J.: Benchmarking GPUs to tune dense linear algebra. 2008 SC—International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–11 (2008). doi: 10.1109/sc.2008.5214359
  60. 60.
    Wilensky, U.: Netlogo. Center for Connected Learning and Computer-Based Modeling, Northwestern University, Evanston, IL (1999).
  61. 61.
    Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65 (2009). doi: 10.1145/1498765.1498785 CrossRefGoogle Scholar
  62. 62.
    Zhao, Y.: GPU accelerated computation and real-time rendering of cellular automata model for spatial simulation. J. Inform. Comput. Sci. 11(12), 4453–4465 (2014). doi: 10.12733/jics20104445 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Emmanuel N. Millán
    • 1
  • Nicolás Wolovick
    • 2
  • María Fabiana Piccoli
    • 3
  • Carlos García Garino
    • 4
  • Eduardo M. Bringa
    • 1
  1. 1.CONICET and FCENUniversidad Nacional de CuyoMendozaArgentina
  2. 2.Universidad Nacional de CórdobaCórdobaArgentina
  3. 3.Universidad Nacional de San LuisSan LuisArgentina
  4. 4.ITIC and FINGUniversidad Nacional de CuyoMendozaArgentina

Personalised recommendations