Performance Evaluation of N-Body Simulations on AWS with StarPU, OpenMP and MPI Runtime Systems
Resumo
Cloud Computing provides a cost-effective option for High Performance Computing (HPC) workloads, but brings new challenges. This study evaluates StarPU, a task-based runtime for heterogeneous architectures, in cloud environments by running an N-Body simulation under different cluster configurations and comparing it with traditional HPC runtime systems (OpenMP and MPI). Results show that StarPU excels in single-node setups, especially with GPU acceleration, while scalability varies, struggling with CPU-intensive workloads but performing well in hybrid and GPU-only scenarios. These insights highlight the need for careful infrastructure selection and architectural strategies to ensure good performance in cloud-based HPC.
Referências
Augonnet, C., Thibault, S., Namyst, R., and Wacrenier, P.-A. (2011). StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurrency and Computation: Practice and Experience, 23(2):187–198.
Barnes, J. and Hut, P. (1986). A hierarchical o(n log n) force-calculation algorithm. Nature, 324(6096):446–449.
Bueno, J., Planas, J., Duran, A., Martorell, X., Ayguadé, E., Badia, R. M., and Labarta, J. (2012). Productive programming of gpu clusters with ompss. In Parallel and Distributed Processing Symposium (IPDPS).
Chandra, R. (2001). Parallel programming in OpenMP. Morgan kaufmann.
Dancheva, T., Alonso, U., and Barton, M. (2024). Cloud benchmarking and performance analysis of an HPC application in Amazon EC2. Cluster Computing, 27(2):2273–2290.
Graham, R. L., Woodall, T. S., and Squyres, J. M. (2006). Open mpi: A flexible high performance mpi. In Parallel Processing and Applied Mathematics: 6th International Conference, PPAM 2005, Poznań, Poland, September 11-14, 2005, Revised Selected Papers 6, pages 228–239. Springer.
Guidi, G., Ellis, M., Buluç, A., Yelick, K., and Culler, D. (2021). 10 years later: Cloud computing is closing the performance gap. In Companion of the ACM/SPEC International Conference on Performance Engineering, ICPE ’21, page 41–48, New York, NY, USA. Association for Computing Machinery.
Heggie, D. (2005). The classical gravitational n-body problem. Encyclopedia of Mathematical Physics.
Hoque, R., Hérault, T., Bosilca, G., and Dongarra, J. (2017). Dynamic task discovery in PaRSEC: a data-flow task-based runtime. In ScalA ’17: The 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems.
Liberman García, A. (2015). The evolution of the Cloud: the work, progress and outlook of cloud infrastructure. PhD thesis, Massachusetts Institute of Technology.
Munhoz, V. and Castro, M. (2024). Enabling the execution of hpc applications on public clouds with hpc@cloud toolkit. Concurrency and Computation: Practice and Experience, 36(8):e7976.
Netto, M. A. S., Calheiros, R. N., Rodrigues, E. R., Cunha, R. L. F., and Buyya, R. (2018). HPC cloud for scientific and business applications: Taxonomy, vision, and research challenges. ACM Comput. Surv., 51(1).
Nylons, L., Harris, M., and Prins, J. (2007). Fast n-body simulation with cuda. GPU gems, 3:62–66.
Pereira, R. (2023). Efficient Use of Task-based Parallelism in HPC Parallel Applications. Theses, Ecole normale supérieure de lyon - ENS LYON.
Teylo, L., Arantes, L., Sens, P., and Drummond, L. M. d. A. (2023). Scheduling Bag-of-Tasks in Clouds using Spot and Burstable Virtual Machines. IEEE Transactions on Cloud Computing, 11(1):984–996.
Wang, Q. (2021). A hybrid fast multipole method for cosmological n-body simulations. Research in Astronomy and Astrophysics, 21(1):003.
Wei, J., Chen, M., Wang, L., Ren, P., Lei, Y., Qu, Y., Jiang, Q., Dong, X., Wu, W., Wang, Q., Zhang, K., and Zhang, X. (2022). Status, challenges and trends of data-intensive supercomputing. CCF Transactions on High Performance Computing, 4(2):211–230.
Zhuang, J., Jacob, D. J., Lin, H., Lundgren, E. W., Yantosca, R. M., Gaya, J. F., Sulprizio, M. P., and Eastham, S. D. (2020). Enabling high-performance cloud computing for earth science modeling on over a thousand cores: Application to the geoschem atmospheric chemistry model. Journal of Advances in Modeling Earth Systems, 12(5):e2020MS002064. e2020MS002064 2020MS002064.
Zwart, S. F. P., Belleman, R. G., and Geldof, P. M. (2007). High-performance direct gravitational n-body simulations on graphics processing units. New Astronomy, 12(8):641–650.
Barnes, J. and Hut, P. (1986). A hierarchical o(n log n) force-calculation algorithm. Nature, 324(6096):446–449.
Bueno, J., Planas, J., Duran, A., Martorell, X., Ayguadé, E., Badia, R. M., and Labarta, J. (2012). Productive programming of gpu clusters with ompss. In Parallel and Distributed Processing Symposium (IPDPS).
Chandra, R. (2001). Parallel programming in OpenMP. Morgan kaufmann.
Dancheva, T., Alonso, U., and Barton, M. (2024). Cloud benchmarking and performance analysis of an HPC application in Amazon EC2. Cluster Computing, 27(2):2273–2290.
Graham, R. L., Woodall, T. S., and Squyres, J. M. (2006). Open mpi: A flexible high performance mpi. In Parallel Processing and Applied Mathematics: 6th International Conference, PPAM 2005, Poznań, Poland, September 11-14, 2005, Revised Selected Papers 6, pages 228–239. Springer.
Guidi, G., Ellis, M., Buluç, A., Yelick, K., and Culler, D. (2021). 10 years later: Cloud computing is closing the performance gap. In Companion of the ACM/SPEC International Conference on Performance Engineering, ICPE ’21, page 41–48, New York, NY, USA. Association for Computing Machinery.
Heggie, D. (2005). The classical gravitational n-body problem. Encyclopedia of Mathematical Physics.
Hoque, R., Hérault, T., Bosilca, G., and Dongarra, J. (2017). Dynamic task discovery in PaRSEC: a data-flow task-based runtime. In ScalA ’17: The 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems.
Liberman García, A. (2015). The evolution of the Cloud: the work, progress and outlook of cloud infrastructure. PhD thesis, Massachusetts Institute of Technology.
Munhoz, V. and Castro, M. (2024). Enabling the execution of hpc applications on public clouds with hpc@cloud toolkit. Concurrency and Computation: Practice and Experience, 36(8):e7976.
Netto, M. A. S., Calheiros, R. N., Rodrigues, E. R., Cunha, R. L. F., and Buyya, R. (2018). HPC cloud for scientific and business applications: Taxonomy, vision, and research challenges. ACM Comput. Surv., 51(1).
Nylons, L., Harris, M., and Prins, J. (2007). Fast n-body simulation with cuda. GPU gems, 3:62–66.
Pereira, R. (2023). Efficient Use of Task-based Parallelism in HPC Parallel Applications. Theses, Ecole normale supérieure de lyon - ENS LYON.
Teylo, L., Arantes, L., Sens, P., and Drummond, L. M. d. A. (2023). Scheduling Bag-of-Tasks in Clouds using Spot and Burstable Virtual Machines. IEEE Transactions on Cloud Computing, 11(1):984–996.
Wang, Q. (2021). A hybrid fast multipole method for cosmological n-body simulations. Research in Astronomy and Astrophysics, 21(1):003.
Wei, J., Chen, M., Wang, L., Ren, P., Lei, Y., Qu, Y., Jiang, Q., Dong, X., Wu, W., Wang, Q., Zhang, K., and Zhang, X. (2022). Status, challenges and trends of data-intensive supercomputing. CCF Transactions on High Performance Computing, 4(2):211–230.
Zhuang, J., Jacob, D. J., Lin, H., Lundgren, E. W., Yantosca, R. M., Gaya, J. F., Sulprizio, M. P., and Eastham, S. D. (2020). Enabling high-performance cloud computing for earth science modeling on over a thousand cores: Application to the geoschem atmospheric chemistry model. Journal of Advances in Modeling Earth Systems, 12(5):e2020MS002064. e2020MS002064 2020MS002064.
Zwart, S. F. P., Belleman, R. G., and Geldof, P. M. (2007). High-performance direct gravitational n-body simulations on graphics processing units. New Astronomy, 12(8):641–650.
Publicado
28/10/2025
Como Citar
VANZ, Nicolas; MUNHOZ, Vanderlei; CASTRO, Márcio.
Performance Evaluation of N-Body Simulations on AWS with StarPU, OpenMP and MPI Runtime Systems. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 26. , 2025, Bonito/MS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 61-72.
DOI: https://doi.org/10.5753/sscad.2025.15831.
