Comparação de Paralelismo com DO CONCURRENT, OpenMP e MPI em Algoritmos do NAS Parallel Benchmark
Resumo
Este trabalho compara o paralelismo nativo do Fortran, via DO CONCURRENT, com OpenMP e MPI em três algoritmos do NAS Parallel Benchmark (Conjugate Gradient, Multi-Grid e Fas-Fourier Transform). Os resultados mostram que DO CONCURRENT alcança desempenho competitivo em cenários com acesso regular à memória, como CG e MG, mas é menos eficiente em FFT, que exige comunicação global intensiva. A contribuição principal é evidenciar a viabilidade prática do DO CONCURRENT em CPU, oferecendo código mais legível e de fácil manutenção sem perder eficiência significativa.
Referências
Ayguade, E., Copty, N., Duran, A., Hoeflinger, J., Lin, Y., Massaioli, F., Teruel, X., Unnikrishnan, P., and Zhang, G. (2009). The Design of OpenMP Tasks. IEEE Transactions on Parallel and Distributed Systems, 20(3):404–418.
Chandrasekaran, S. and Juckeland, G. (2017). OpenACC for Programmers: Concepts and Strategies. Addison-Wesley Professional, 1st edition.
Chapman, B., Mehrotra, P., and Zima, H. (1998). Enhancing OpenMP with features for locality contro. In Proc. ECWMF Workshop: Towards Teracomputing-The Use of Parallel Processors in Meteorology, Austria. PSU.
Dagum, L. and Menon, R. (1998). OpenMP: An Industry-Standard API for Shared-Memory Programming. IEEE Computational Science & Engineering, 5(1):46–55.
Gropp, W., Lusk, E., and Skjellum, A. (1996). Using MPI: Portable Parallel Programming with the Message Passing Interface. MIT Press, 1st edition.
Hammond, J. R., Deakin, T., Cownie, J., and McIntosh-Smith, S. (2022). Benchmarking Fortran DO CONCURRENT on CPUs and GPUs Using BabelStream. In 2022 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pages 82–99.
Löff, J., Griebler, D., Mencagli, G., Araujo, G., Torquati, M., Danelutto, M., and Fernandes, L. G. (2021). The NAS Parallel Benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures. Future Generation Computer Systems, 125:743–757.
Maqbool, S. and Lee, B.-J. (2025). High performance additive manufacturing phase field simulation: Fortran do concurrent vs openmp. Computational Materials Science, 252:113788.
Reid, J. (2018). The New Features of Fortran 2018. SIGPLAN Fortran Forum, 37(1):5–43.
Stulajter, J. and Smith, A. (2022). Advances in Parallel Programming Techniques for Modern HPC Systems. Journal of Parallel and Distributed Computing, 160:1–15.
Stulajter, M. M., Caplan, R. M., and Linker, J. A. (2021). Can Fortran’s ’do concurrent’ replace directives for accelerated computing?
Tremarin, G., Marciano, A., Schepke, C., and Vogel, A. (2024). Fortran DO CONCURRENT Evaluation in Multi-core for NAS-PB Conjugate Gradient and a Porous Media Application. In Anais do XXV Simpósio em Sistemas Computacionais de Alto Desempenho, pages 133–143, Porto Alegre, RS, Brasil. SBC.
Chandrasekaran, S. and Juckeland, G. (2017). OpenACC for Programmers: Concepts and Strategies. Addison-Wesley Professional, 1st edition.
Chapman, B., Mehrotra, P., and Zima, H. (1998). Enhancing OpenMP with features for locality contro. In Proc. ECWMF Workshop: Towards Teracomputing-The Use of Parallel Processors in Meteorology, Austria. PSU.
Dagum, L. and Menon, R. (1998). OpenMP: An Industry-Standard API for Shared-Memory Programming. IEEE Computational Science & Engineering, 5(1):46–55.
Gropp, W., Lusk, E., and Skjellum, A. (1996). Using MPI: Portable Parallel Programming with the Message Passing Interface. MIT Press, 1st edition.
Hammond, J. R., Deakin, T., Cownie, J., and McIntosh-Smith, S. (2022). Benchmarking Fortran DO CONCURRENT on CPUs and GPUs Using BabelStream. In 2022 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pages 82–99.
Löff, J., Griebler, D., Mencagli, G., Araujo, G., Torquati, M., Danelutto, M., and Fernandes, L. G. (2021). The NAS Parallel Benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures. Future Generation Computer Systems, 125:743–757.
Maqbool, S. and Lee, B.-J. (2025). High performance additive manufacturing phase field simulation: Fortran do concurrent vs openmp. Computational Materials Science, 252:113788.
Reid, J. (2018). The New Features of Fortran 2018. SIGPLAN Fortran Forum, 37(1):5–43.
Stulajter, J. and Smith, A. (2022). Advances in Parallel Programming Techniques for Modern HPC Systems. Journal of Parallel and Distributed Computing, 160:1–15.
Stulajter, M. M., Caplan, R. M., and Linker, J. A. (2021). Can Fortran’s ’do concurrent’ replace directives for accelerated computing?
Tremarin, G., Marciano, A., Schepke, C., and Vogel, A. (2024). Fortran DO CONCURRENT Evaluation in Multi-core for NAS-PB Conjugate Gradient and a Porous Media Application. In Anais do XXV Simpósio em Sistemas Computacionais de Alto Desempenho, pages 133–143, Porto Alegre, RS, Brasil. SBC.
Publicado
28/10/2025
Como Citar
MARCIANO, Anna V. G.; ANTUNES, Artur dos Santos; SCHEPKE, Claudio.
Comparação de Paralelismo com DO CONCURRENT, OpenMP e MPI em Algoritmos do NAS Parallel Benchmark. In: WORKSHOP DE INICIAÇÃO CIENTÍFICA - SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 26. , 2025, Bonito/MS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 97-104.
DOI: https://doi.org/10.5753/sscad_estendido.2025.16753.
