Desafios do Processamento de Alto Desempenho
Resumo
O Processamento de Alto Desempenho, High Performance Computing - HPC, vem crescendo de importância nos últimos anos com a necessidade de grande poder de processamento para gerenciar sistemas Big Data, assim como para treinamento e uso de algoritmos para Inteligência Artificial, entre outras demandas. Neste artigo é feita uma análise dos principais desafios na evolução destes sistemas para os próximos anos, quanto a futuras arquiteturas dos processadores e máquinas, a heterogeneidade, a computação quântica, além das necessidades de redução do consumo de energia e localidade dos dados e o avanço de soluções HPC na nuvem.
Palavras-chave:
Processamento de Alto Desempenho, Arquiteturas Heterogêneas, Consumo de Energia, Machine Learning, Big Data
Referências
Aurora (2021). Argonne Leadership Computing Facility. https://www.alcf.anl.gov/aurora [Acesso em: 10 Abr. 2021].
Barney, B. (2009). POSIX threads programming. National Laboratory. https://computing.llnl.gov/tutorials/pthreads [Acesso em: 4 Mai. 2021].
Chandra, R., Dagum, L., Kohr, D., Menon, R., Maydan, D., & McDonald, J. (2001). Parallel programming in OpenMP. Morgan kaufmann.
Cook, S. (2012). CUDA programming: a developer's guide to parallel computing with GPUs. Newnes.
Cox M., Ellsworth D. (1997) “Managing Big Data for Scientific Visualization” Conference on Visualization ’97. VIS ’97.
Cruz E., Diener M., Pilla L., Navaux P. (2021) “Online Thread and Data Mapping Using a Sharing-Aware Memory Management Unit” ACM Transactions on Modeling and Performance Evaluation of Computing Systems January 2021, Vol. 5 No. 4 Article.
Davila G. P. , Oliveira D. A. G. , Navaux P. O, A, , Rech P. : Identifying the Most Reliable Collaborative Workload Distribution in Heterogeneous Devices. DATE 2019: 1325-1330
Desjardins J. (2019). How much data is generated each day? https://www.visualcapitalist.com/how-much-data-is-generated-each-day/. [Acesso em: 12 Mar. 2021].
Diaz, J., Munoz-Caro, C., & Nino, A. (2012). A survey of parallel programming models and tools in the multi and many-core era. IEEE Transactions on parallel and distributed systems, 23(8), 1369-1386.
Dongarra J., H. M. and Strohmaier, E. (2020). Top500 supercomputer: November 2020. https://www.top500.org/lists/top500/2020/11/. [Acesso em: 10 Mar. 2021].
Farber, R. (2016). Parallel programming with OpenACC. Newnes.
Frontier (2021). ORNL Exascale Supercomputer. https://www.olcf.ornl.gov/frontier/ [Acesso em: 10 Abr. 2021].
Fujitsu (2021). Supercomputer Fugaku. https://www.fujitsu.com/. [Acesso em: 10 Abr. 2021].
Gabriel, E., Fagg, G. E., Bosilca, G., Angskun, T., Dongarra, J. J., Squyres, J. M., ... & Woodall, T. S. (2004, September). Open MPI: Goals, concept, and design of a next generation MPI implementation. In European Parallel Virtual Machine/Message Passing Interface Users’ Group Meeting (pp. 97-104). Springer, Berlin, Heidelberg.
Hendrickx N., Lawrie W., Russ M., Riggelen F., Snoo S., Schouten R., Sammak A., Scappucci G., Veldhorst M. (2021) “A four-qubit germanium quantum processor”. Nature, 2021; 591 (7851): 580 DOI: 10.1038/s41586-021-03332-6.
Kooge P. & All (2008) “ExaScale Computing Study: Technology Challenges in Achieving Exascale Systems” Defense Advanced Research Projects Agency Information Processing Techniques Office, Tech. Rep.
Munshi, A., Gaster, B., Mattson, T. G., & Ginsburg, D. (2011). OpenCL programming guide. Pearson Education.
Padoin E. L., Diener M., Navaux P. O. A. , Méhaut J. F. : Managing Power Demand and Load Imbalance to Save Energy on Systems with Heterogeneous CPU Speeds. SBAC-PAD 2019: 72-79
Schardl, T. B., Lee, I. T. A., & Leiserson, C. E. (2018, July). Brief announcement: Open cilk. In Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures (pp. 351-353).
Serpa, M. S., Moreira, F. B., Navaux, P. O., Cruz, E. H., Diener, M., Griebler, D., & Fernandes, L. G. (2019). Memory Performance and Bottlenecks in Multicore and GPU Architectures. In 2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) (pp. 233-236). IEEE.
Stevens R., Nichols J., Yelick K., Helland B., Leads C. (2019) “AI for Science” Report on the Department of Energy (DOE).
Verbraeken, J., Wolting, M., Katzy, J., Kloppenburg, J., Verbelen, T., & Rellermeyer, J. S. (2020). A survey on distributed machine learning. ACM Computing Surveys (CSUR), 53(2), 1-33.
Vetter J. and all (2018) “Extreme Heterogeneity 2018: Productive Computational Science in the Era of Extreme Heterogeneity” Report for DOE ASCR Basic Research Needs Workshop on Extreme Heterogeneity.
Barney, B. (2009). POSIX threads programming. National Laboratory. https://computing.llnl.gov/tutorials/pthreads [Acesso em: 4 Mai. 2021].
Chandra, R., Dagum, L., Kohr, D., Menon, R., Maydan, D., & McDonald, J. (2001). Parallel programming in OpenMP. Morgan kaufmann.
Cook, S. (2012). CUDA programming: a developer's guide to parallel computing with GPUs. Newnes.
Cox M., Ellsworth D. (1997) “Managing Big Data for Scientific Visualization” Conference on Visualization ’97. VIS ’97.
Cruz E., Diener M., Pilla L., Navaux P. (2021) “Online Thread and Data Mapping Using a Sharing-Aware Memory Management Unit” ACM Transactions on Modeling and Performance Evaluation of Computing Systems January 2021, Vol. 5 No. 4 Article.
Davila G. P. , Oliveira D. A. G. , Navaux P. O, A, , Rech P. : Identifying the Most Reliable Collaborative Workload Distribution in Heterogeneous Devices. DATE 2019: 1325-1330
Desjardins J. (2019). How much data is generated each day? https://www.visualcapitalist.com/how-much-data-is-generated-each-day/. [Acesso em: 12 Mar. 2021].
Diaz, J., Munoz-Caro, C., & Nino, A. (2012). A survey of parallel programming models and tools in the multi and many-core era. IEEE Transactions on parallel and distributed systems, 23(8), 1369-1386.
Dongarra J., H. M. and Strohmaier, E. (2020). Top500 supercomputer: November 2020. https://www.top500.org/lists/top500/2020/11/. [Acesso em: 10 Mar. 2021].
Farber, R. (2016). Parallel programming with OpenACC. Newnes.
Frontier (2021). ORNL Exascale Supercomputer. https://www.olcf.ornl.gov/frontier/ [Acesso em: 10 Abr. 2021].
Fujitsu (2021). Supercomputer Fugaku. https://www.fujitsu.com/. [Acesso em: 10 Abr. 2021].
Gabriel, E., Fagg, G. E., Bosilca, G., Angskun, T., Dongarra, J. J., Squyres, J. M., ... & Woodall, T. S. (2004, September). Open MPI: Goals, concept, and design of a next generation MPI implementation. In European Parallel Virtual Machine/Message Passing Interface Users’ Group Meeting (pp. 97-104). Springer, Berlin, Heidelberg.
Hendrickx N., Lawrie W., Russ M., Riggelen F., Snoo S., Schouten R., Sammak A., Scappucci G., Veldhorst M. (2021) “A four-qubit germanium quantum processor”. Nature, 2021; 591 (7851): 580 DOI: 10.1038/s41586-021-03332-6.
Kooge P. & All (2008) “ExaScale Computing Study: Technology Challenges in Achieving Exascale Systems” Defense Advanced Research Projects Agency Information Processing Techniques Office, Tech. Rep.
Munshi, A., Gaster, B., Mattson, T. G., & Ginsburg, D. (2011). OpenCL programming guide. Pearson Education.
Padoin E. L., Diener M., Navaux P. O. A. , Méhaut J. F. : Managing Power Demand and Load Imbalance to Save Energy on Systems with Heterogeneous CPU Speeds. SBAC-PAD 2019: 72-79
Schardl, T. B., Lee, I. T. A., & Leiserson, C. E. (2018, July). Brief announcement: Open cilk. In Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures (pp. 351-353).
Serpa, M. S., Moreira, F. B., Navaux, P. O., Cruz, E. H., Diener, M., Griebler, D., & Fernandes, L. G. (2019). Memory Performance and Bottlenecks in Multicore and GPU Architectures. In 2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) (pp. 233-236). IEEE.
Stevens R., Nichols J., Yelick K., Helland B., Leads C. (2019) “AI for Science” Report on the Department of Energy (DOE).
Verbraeken, J., Wolting, M., Katzy, J., Kloppenburg, J., Verbelen, T., & Rellermeyer, J. S. (2020). A survey on distributed machine learning. ACM Computing Surveys (CSUR), 53(2), 1-33.
Vetter J. and all (2018) “Extreme Heterogeneity 2018: Productive Computational Science in the Era of Extreme Heterogeneity” Report for DOE ASCR Basic Research Needs Workshop on Extreme Heterogeneity.
Publicado
18/07/2021
Como Citar
NAVAUX, Philippe Olivier Alexandre; SERPA, Matheus da Silva.
Desafios do Processamento de Alto Desempenho. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 48. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 39-49.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2021.15805.
