Exploração do Projeto de Sistemas Baseados em GPU ciente de Dark Silicon
Resumo
Este artigo propõe uma infraestrutura para realizar a exploração do espaço de projetos de sistemas computacionais com unidades de processamento gráfico (GPUs) em conjunto com núcleos para processamento de propósito geral, com o objetivo de reduzir dark silicon e aumentar o desempenho do sistema em tempo de projeto. A ferramenta GPGPUSim de simulação e estimativa fı́sica de projeto foi estendida para realizar estimativas de dark silicon das plataformas de GPUs e, em seguida, foi integrada ao framework MultiExplorer. Adicionalmente, foi desenvolvida uma estratégia para estimativa de desempenho das plataformas de GPU e a modelagem de bases de dados que passaram a utilizar tanto núcleos de GPU quanto de plataformas multicore (núcleos de propósito geral), possibilitando, assim, a exploração do espaço de projeto buscando arquiteturas heterogêneas GP-GPUs.
Referências
Bakhoda, A., Yuan, G. L., Fung, W. W., Wong, H., and Aamodt, T. M. (2009) Analyzing cuda workloads using a detailed gpu simulator. In Performance Analysis of Systems and Software, 2009. ISPASS 2009. IEEE International Symposium on, pages 163–174. IEEE.
Carlson, T. E., Heirman, W., and Eeckhout, L. (2011). Sniper: exploring the level of abstraction for scalable and accurate parallel multi-core simulation. In Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, page 52. ACM.
Dennard, R., Gaensslen, F., Yu, H.-N., Rideout, L., Bassous, E., and Leblanc, A. (1974). Design of ion-implanted mosfets with very small physical dimensions. IEEE Journal of Solid-Circuits, pages 256–267.
Dennard, R. H., Cai, J., and Kumar, A. (2007). A perspective on today’s scaling challenges and possible future directions. Solid-State Electronics, 51(4):518–525.
Duenha, L., Guedes, M., Almeida, H., Boy, M., and Azevedo, R. (2014). MPSoCBench: A toolset for MPSoC system level evaluation. In International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS XIV), pages 164–171. IEEE.
Fung, W. W., Sham, I., Yuan, G., and Aamodt, T. M. (2007). Dynamic warp formation and scheduling for efficient gpu control flow. In Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture, pages 407–420. IEEE Computer Society.
Hardavellas, N., Ferdman, M., Falsafi, B., and Ailamaki, A. (2011). Toward dark silicon in servers. IEEE Micro, 31(4):6–15.
Jia, W., Shaw, K. A., and Martonosi, M. (2012). Stargazer: Automated regressionbased gpu design space exploration. In Performance Analysis of Systems and Software (ISPASS), 2012 IEEE International Symposium on, pages 2–13. IEEE.
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. In ACM SIGARCH Computer Architecture News, volume 41, pages 487–498. ACM.
Li, S., Ahn, J., Strong, R., Brockman, J., Tullsen, D., and Jouppi, N. (2009). McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In 42nd Annual IEEE/ACM International Symposium on Microarchitecture, pages 469–480. IEEE.
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.
Mooney, C. Z. (1997). Monte carlo simulation, volume 116. Sage Publications.
Morris, G. W. and Aubury, M. (2007). Design space exploration of the european option benchmark using hyperstreams. In Field Programmable Logic and Applications, 2007. FPL 2007. International Conference on, pages 5–10. IEEE.
Nejatollahi, H. and Salehi, M. E. (2015). Voltage scaling and dark silicon in symmetric multicore processors. The Journal of Supercomputing, 71(10):3958–3973.
Raghunathan, B., Turakhia, Y., Garg, S., and Marculescu, D. (2013). Cherrypicking: exploiting process variations in dark-silicon homogeneous chip multiprocessors. In Proceedings of the DATE, pages 39–44. EDA Consortium.
Sanders, J. and Kandrot, E. (2010). CUDA by example: an introduction to generalpurpose GPU programming. Addison-Wesley Professional.
Santos, M. T., Oliveira, T., Sonohata, R., Krebs, C., Duenha, L., and Santos, R. (2018a). Modelo de predição de desempenho integrado à exploração do espaço de projetos. In Anais do Workshop de Computação Heterogênea (WCH), pages 630–641.
Santos, R., Duenha, L., Silva, A. C., Sousa, M., Tedesco, L. A., Melgarejo, J. C., Santos, T., Azevedo, R., and Moreno, E. (2018b). Dark-silicon aware design space exploration. Journal of Parallel and Distributed Computing, 120:295–306.
Santos, T., Silva, A., Duenha, L., Santos, R., Moreno, E., and Azevedo, R. (2016) On the dark silicon automatic evaluation on multicore processors. In Proceedings of the SBAC-PAD, pages 166–173. IEEE.
Schaller, R. (1997) 34(6):52–59. Moore’s law: Past, present and future. IEEE Spectrum,
Shafique, M., Garg, S., Henkel, J., and Marculescu, D. (2014). The eda challenges in the dark silicon era: Temperature, reliability, and variability perspectives. In Proceedings of the 51st Annual DAC, pages 1–6. ACM.
Turakhia, Y., Raghunathan, B., Garg, S., and Marculescu, D. (2013). Hades: Architectural synthesis for heterogeneous dark silicon chip multi-processors. In Proceedings of the 50th Annual DAC, page 173. ACM.
Ubal, R., Jang, B., Mistry, P., Schaa, D., and Kaeli, D. (2012). Multi2Sim: a simulation framework for CPU-GPU computing. In Proceedings of the 21st international conference on Parallel architectures and compilation techniques, pages 335–344. ACM.
Carlson, T. E., Heirman, W., and Eeckhout, L. (2011). Sniper: exploring the level of abstraction for scalable and accurate parallel multi-core simulation. In Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, page 52. ACM.
Dennard, R., Gaensslen, F., Yu, H.-N., Rideout, L., Bassous, E., and Leblanc, A. (1974). Design of ion-implanted mosfets with very small physical dimensions. IEEE Journal of Solid-Circuits, pages 256–267.
Dennard, R. H., Cai, J., and Kumar, A. (2007). A perspective on today’s scaling challenges and possible future directions. Solid-State Electronics, 51(4):518–525.
Duenha, L., Guedes, M., Almeida, H., Boy, M., and Azevedo, R. (2014). MPSoCBench: A toolset for MPSoC system level evaluation. In International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS XIV), pages 164–171. IEEE.
Fung, W. W., Sham, I., Yuan, G., and Aamodt, T. M. (2007). Dynamic warp formation and scheduling for efficient gpu control flow. In Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture, pages 407–420. IEEE Computer Society.
Hardavellas, N., Ferdman, M., Falsafi, B., and Ailamaki, A. (2011). Toward dark silicon in servers. IEEE Micro, 31(4):6–15.
Jia, W., Shaw, K. A., and Martonosi, M. (2012). Stargazer: Automated regressionbased gpu design space exploration. In Performance Analysis of Systems and Software (ISPASS), 2012 IEEE International Symposium on, pages 2–13. IEEE.
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. In ACM SIGARCH Computer Architecture News, volume 41, pages 487–498. ACM.
Li, S., Ahn, J., Strong, R., Brockman, J., Tullsen, D., and Jouppi, N. (2009). McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In 42nd Annual IEEE/ACM International Symposium on Microarchitecture, pages 469–480. IEEE.
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.
Mooney, C. Z. (1997). Monte carlo simulation, volume 116. Sage Publications.
Morris, G. W. and Aubury, M. (2007). Design space exploration of the european option benchmark using hyperstreams. In Field Programmable Logic and Applications, 2007. FPL 2007. International Conference on, pages 5–10. IEEE.
Nejatollahi, H. and Salehi, M. E. (2015). Voltage scaling and dark silicon in symmetric multicore processors. The Journal of Supercomputing, 71(10):3958–3973.
Raghunathan, B., Turakhia, Y., Garg, S., and Marculescu, D. (2013). Cherrypicking: exploiting process variations in dark-silicon homogeneous chip multiprocessors. In Proceedings of the DATE, pages 39–44. EDA Consortium.
Sanders, J. and Kandrot, E. (2010). CUDA by example: an introduction to generalpurpose GPU programming. Addison-Wesley Professional.
Santos, M. T., Oliveira, T., Sonohata, R., Krebs, C., Duenha, L., and Santos, R. (2018a). Modelo de predição de desempenho integrado à exploração do espaço de projetos. In Anais do Workshop de Computação Heterogênea (WCH), pages 630–641.
Santos, R., Duenha, L., Silva, A. C., Sousa, M., Tedesco, L. A., Melgarejo, J. C., Santos, T., Azevedo, R., and Moreno, E. (2018b). Dark-silicon aware design space exploration. Journal of Parallel and Distributed Computing, 120:295–306.
Santos, T., Silva, A., Duenha, L., Santos, R., Moreno, E., and Azevedo, R. (2016) On the dark silicon automatic evaluation on multicore processors. In Proceedings of the SBAC-PAD, pages 166–173. IEEE.
Schaller, R. (1997) 34(6):52–59. Moore’s law: Past, present and future. IEEE Spectrum,
Shafique, M., Garg, S., Henkel, J., and Marculescu, D. (2014). The eda challenges in the dark silicon era: Temperature, reliability, and variability perspectives. In Proceedings of the 51st Annual DAC, pages 1–6. ACM.
Turakhia, Y., Raghunathan, B., Garg, S., and Marculescu, D. (2013). Hades: Architectural synthesis for heterogeneous dark silicon chip multi-processors. In Proceedings of the 50th Annual DAC, page 173. ACM.
Ubal, R., Jang, B., Mistry, P., Schaa, D., and Kaeli, D. (2012). Multi2Sim: a simulation framework for CPU-GPU computing. In Proceedings of the 21st international conference on Parallel architectures and compilation techniques, pages 335–344. ACM.
Publicado
08/11/2019
Como Citar
SANTOS, Ricardo; SONOHATA, Rhayssa; KREBS, Casio; CATELAN, Daniela; DUENHA, Liana; SEGOVIA, Diego; SANTOS, Mateus Tostes.
Exploração do Projeto de Sistemas Baseados em GPU ciente de Dark Silicon. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 20. , 2019, Campo Grande.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 358-369.
DOI: https://doi.org/10.5753/wscad.2019.8682.
