Exploração do Espaço de Projetos de Sistemas GPGPUs ciente de Dark-Silicon
Resumo
Este trabalho apresenta extensão da ferramenta MultiExplorer para a exploração do espaço de projetos GPGPUs. Para tal, foi realizada a integração de novos simuladores e estimadores ao fluxo da ferramenta, a caracterização de desempenho, área e consumo de seis modelos de GPUs executando aplicações CUDA e Rodinia, a modelagem de um banco de núcleos alternativos necessários para a exploração arquitetural e a extensão da interface adaptada ao novo domínio.
Referências
Amorim, E. R., Santos, R., and Duenha, L. (2023). A tool for teaching and learning of design space exploration on processor architectures. In 2023 IEEE Frontiers in Education Conference (FIE), pages 1–9. IEEE.
Arigoni, D., Santos, R., and Garanhani, L. (2022). Design space exploration of heterogeneous systems applied to the cloud resource allocation problem. In Anais do XXIII Simpósio em Sistemas Computacionais de Alto Desempenho, pages 169–180, Porto Alegre, RS, Brasil. SBC.
BAGHSORKHI, S., DELAHAYE, M., PATEL, S., GROPP, W., and HWU, W. (2010). An adaptive performance modeling tool for gpu architectures. In Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming, pages 105–114. Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming.
Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J. W., Lee, S.-H., and Skadron, K. (2009). Rodinia: A benchmark suite for heterogeneous computing. In 2009 IEEE International Symposium on Workload Characterization (IISWC), pages 44–54. IEEE.
HONG, S. and KIM, H. (2009). An analytical model for a gpu architecture with memory-level and thread-level parallelism awareness. In Proceedings of the 36th annual international symposium on Computer architecture, pages 152–163. Proceedings of the 36th annual international symposium on Computer architecture.
Khairy, M., Shen, Z., Aamodt, T. M., and Rogers, T. G. (2020). Accel-sim: an extensible simulation framework for validated gpu modeling. In Proceedings of the ACM/IEEE 47th Annual International Symposium on Computer Architecture, ISCA ’20, page 473–486. IEEE Press.
Leng, J., Hetherington, T., ElTantawy, A., Gilani, S., Kim, N. S., Aamodt, T. M., and Reddi, V. J. (2013). Gpuwattch: enabling energy optimizations in gpgpus. ACM SIGARCH Computer Architecture News, 41(3):487–498.
LI, S., AHN, J., STRONG, R., BROCKMAN, J., TULLSEN, D., and JOUPPI, N. (2013). The McPAT framework for multicore and manycore architectures: Simultaneously modeling power, area, and timing. ACM Transactions on Architecture and Code Optimization (TACO), 10(1):5.
MOORE, G. (1998). Cramming more components onto integrated circuits. Proceedings of the IEEE, 86(1):82–85.
NVIDIA (2021). CUDA Toolkit Documentation. [link].
SANTOS, R., DUENHA, L., SILVA, A., SOUSA, M., TEDESCO, L., MELGAREJO, J., SANTOS, T., AZEVEDO, R., and MORENO, E. (2018). Dark-silicon aware design space exploration. Journal of Parallel and Distributed Computing, 120:295–306.
Sonohata, R., Arigoni, D. C. A., Fernandes, E. R., Ribeiro dos Santos, R., and Dessandre Duenha, L. (2023). Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration. Concurrency and Computation: Practice and Experience, 35(17):e6877.
Arigoni, D., Santos, R., and Garanhani, L. (2022). Design space exploration of heterogeneous systems applied to the cloud resource allocation problem. In Anais do XXIII Simpósio em Sistemas Computacionais de Alto Desempenho, pages 169–180, Porto Alegre, RS, Brasil. SBC.
BAGHSORKHI, S., DELAHAYE, M., PATEL, S., GROPP, W., and HWU, W. (2010). An adaptive performance modeling tool for gpu architectures. In Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming, pages 105–114. Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming.
Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J. W., Lee, S.-H., and Skadron, K. (2009). Rodinia: A benchmark suite for heterogeneous computing. In 2009 IEEE International Symposium on Workload Characterization (IISWC), pages 44–54. IEEE.
HONG, S. and KIM, H. (2009). An analytical model for a gpu architecture with memory-level and thread-level parallelism awareness. In Proceedings of the 36th annual international symposium on Computer architecture, pages 152–163. Proceedings of the 36th annual international symposium on Computer architecture.
Khairy, M., Shen, Z., Aamodt, T. M., and Rogers, T. G. (2020). Accel-sim: an extensible simulation framework for validated gpu modeling. In Proceedings of the ACM/IEEE 47th Annual International Symposium on Computer Architecture, ISCA ’20, page 473–486. IEEE Press.
Leng, J., Hetherington, T., ElTantawy, A., Gilani, S., Kim, N. S., Aamodt, T. M., and Reddi, V. J. (2013). Gpuwattch: enabling energy optimizations in gpgpus. ACM SIGARCH Computer Architecture News, 41(3):487–498.
LI, S., AHN, J., STRONG, R., BROCKMAN, J., TULLSEN, D., and JOUPPI, N. (2013). The McPAT framework for multicore and manycore architectures: Simultaneously modeling power, area, and timing. ACM Transactions on Architecture and Code Optimization (TACO), 10(1):5.
MOORE, G. (1998). Cramming more components onto integrated circuits. Proceedings of the IEEE, 86(1):82–85.
NVIDIA (2021). CUDA Toolkit Documentation. [link].
SANTOS, R., DUENHA, L., SILVA, A., SOUSA, M., TEDESCO, L., MELGAREJO, J., SANTOS, T., AZEVEDO, R., and MORENO, E. (2018). Dark-silicon aware design space exploration. Journal of Parallel and Distributed Computing, 120:295–306.
Sonohata, R., Arigoni, D. C. A., Fernandes, E. R., Ribeiro dos Santos, R., and Dessandre Duenha, L. (2023). Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration. Concurrency and Computation: Practice and Experience, 35(17):e6877.
Publicado
23/10/2024
Como Citar
LUDGERO, Laura B.; DAMASCENO, Gislayne G.; RODRIGUES, Samuel S.; SANTOS, Ricardo R. dos; DUENHA, Liana D..
Exploração do Espaço de Projetos de Sistemas GPGPUs ciente de Dark-Silicon. In: WORKSHOP DE INICIAÇÃO CIENTÍFICA - SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 25. , 2024, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 25-32.
DOI: https://doi.org/10.5753/sscad_estendido.2024.244794.
