Avaliação de arquiteturas manycore e do uso da virtualização de GPUs
Resumo
Atualmente a virtualização encontra-se presente desde nas diversas estratégias para a consolidação de recursos em Datacenters, até no suporte às pesquisas em Nuvens Computacionais. Ao mesmo tempo em que novos modelos de infraestruturas de HPC combinam arquiteturas de processamento multicore e manycore (aceleradores), ainda há uma grande expectativa de resultados tratando-se em como a camada de virtualização afeta o acesso a estes dispositivos. Este trabalho busca estabelecer uma avaliação de desempenho dos diferentes hipervisores, quando associados ao uso destas arquiteturas multi-core e manycore. Além disto, é estabelecido um comparativo entre as diferentes arquiteturas disponívies no mercado atual de HPC.Referências
Amazon (2013). Amazon EC2 Instances. hpc-applications/. [Online; accessado em 19-Janeiro-2013]. http://aws.amazon.com/
Asanovic, K., Bodik, R., Catanzaro, B. C., Gebis, J. J., Husbands, P., Keutzer, K., Patterson, D. A., Plishker, W. L., Shalf, J., Williams, S. W., and Yelick, K. A. (2006). The landscape of parallel computing research: A view from berkeley. Technical Report UCB/EECS-2006-183, EECS Department, University of California, Berkeley.
Cao, C., Dongarra, J., Du, P., Gates, M., Luszczek, P., and Tomov, S. (2013). clMAGMA: High Performance Dense Linear Algebra with OpenCL. Technical Report UT-CS-13- 706, University of Tennessee.
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 IISWC, pages 44–54.
Colella, P. (2004). Dening software requirements for scientic computing. DARPA HPCS presentation.
ComCiDis (2013). ComCiDis, Computação Cientíca Distribuída. http://comcidis.lncc.br/. [Online; accessado em 19-Janeiro-2013].
Dolbeau, R., Bodin, F., and de Verdiere, G. (2013). One OpenCL to rule them all? In Multi-/Many-core Computing Systems (MuCoCoS), 2013 IEEE 6th International Workshop on, pages 1–6.
Dongarra, J., Meuer, H., and Strohmaier, E. (1999). Top500 Supercomputer Sites (13th edition). Technical Report UT-CS-99-425.
Engen, V., Papay, J., Phillips, S. C., and Boniface, M. (2012). Predicting application performance for multi-vendor clouds using dwarf benchmarks. In Proceedings of the 13th international conference on Web Information Systems Engineering, WISE'12, pages 659–665, Berlin, Heidelberg. Springer-Verlag.
Hoopoe (2013). HOOPOE CLOUD. http://www.cass-hpc.com/solutions/hoopoe. [Online; accessado em 18-Janeiro-2013].
Matsunaga, A. and Fortes, J. A. B. (2010). On the Use of Machine Learning to Predict the Time and Resources Consumed by Applications. In Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, CCGRID '10, pages 495–504, Washington, DC, USA. IEEE Computer Society.
Muraleedharan, V. (2012). Hawk-i HPC Cloud Benchmark Tool. Msc in high performance computing, University of Edinburgh, Edinburgh.
Nimbix (2013). NIMBIX Accelerated Compute Cloud HPC Workloads in the Cloud. www.nimbix.net. [Online; accessado em 19-Agosto-2013].
Phillips, S. C., Engen, V., and Papay, J. (2011). Snow White Clouds and the Seven Dwarfs. In Proceedings of the 2011 IEEE Third International Conference on Cloud Computing Technology and Science, CLOUDCOM '11, pages 738–745, Washington, DC, USA. IEEE Computer Society.
Springer, P. (2011). Berkeley's Dwarfs on CUDA. Technical report, RWTH Aachen University. Seminar Project.
Stratton, J. A., Rodrigrues, C., Sung, I.-J., Obeid, N., Chang, L., Liu, G., and Hwu, W.- M. W. (2012). Parboil: A Revised Benchmark Suite for Scientic and Commercial Throughput Computing. Technical Report IMPACT-12-01, University of Illinois at Urbana-Champaign, Urbana.
Asanovic, K., Bodik, R., Catanzaro, B. C., Gebis, J. J., Husbands, P., Keutzer, K., Patterson, D. A., Plishker, W. L., Shalf, J., Williams, S. W., and Yelick, K. A. (2006). The landscape of parallel computing research: A view from berkeley. Technical Report UCB/EECS-2006-183, EECS Department, University of California, Berkeley.
Cao, C., Dongarra, J., Du, P., Gates, M., Luszczek, P., and Tomov, S. (2013). clMAGMA: High Performance Dense Linear Algebra with OpenCL. Technical Report UT-CS-13- 706, University of Tennessee.
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 IISWC, pages 44–54.
Colella, P. (2004). Dening software requirements for scientic computing. DARPA HPCS presentation.
ComCiDis (2013). ComCiDis, Computação Cientíca Distribuída. http://comcidis.lncc.br/. [Online; accessado em 19-Janeiro-2013].
Dolbeau, R., Bodin, F., and de Verdiere, G. (2013). One OpenCL to rule them all? In Multi-/Many-core Computing Systems (MuCoCoS), 2013 IEEE 6th International Workshop on, pages 1–6.
Dongarra, J., Meuer, H., and Strohmaier, E. (1999). Top500 Supercomputer Sites (13th edition). Technical Report UT-CS-99-425.
Engen, V., Papay, J., Phillips, S. C., and Boniface, M. (2012). Predicting application performance for multi-vendor clouds using dwarf benchmarks. In Proceedings of the 13th international conference on Web Information Systems Engineering, WISE'12, pages 659–665, Berlin, Heidelberg. Springer-Verlag.
Hoopoe (2013). HOOPOE CLOUD. http://www.cass-hpc.com/solutions/hoopoe. [Online; accessado em 18-Janeiro-2013].
Matsunaga, A. and Fortes, J. A. B. (2010). On the Use of Machine Learning to Predict the Time and Resources Consumed by Applications. In Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, CCGRID '10, pages 495–504, Washington, DC, USA. IEEE Computer Society.
Muraleedharan, V. (2012). Hawk-i HPC Cloud Benchmark Tool. Msc in high performance computing, University of Edinburgh, Edinburgh.
Nimbix (2013). NIMBIX Accelerated Compute Cloud HPC Workloads in the Cloud. www.nimbix.net. [Online; accessado em 19-Agosto-2013].
Phillips, S. C., Engen, V., and Papay, J. (2011). Snow White Clouds and the Seven Dwarfs. In Proceedings of the 2011 IEEE Third International Conference on Cloud Computing Technology and Science, CLOUDCOM '11, pages 738–745, Washington, DC, USA. IEEE Computer Society.
Springer, P. (2011). Berkeley's Dwarfs on CUDA. Technical report, RWTH Aachen University. Seminar Project.
Stratton, J. A., Rodrigrues, C., Sung, I.-J., Obeid, N., Chang, L., Liu, G., and Hwu, W.- M. W. (2012). Parboil: A Revised Benchmark Suite for Scientic and Commercial Throughput Computing. Technical Report IMPACT-12-01, University of Illinois at Urbana-Champaign, Urbana.
Publicado
28/07/2014
Como Citar
MANFROI, Laion; SCHULZE, Bruno; PINTO, Raquel; MURY, Antonio; FERRO, Mariza.
Avaliação de arquiteturas manycore e do uso da virtualização de GPUs. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 13. , 2014, Brasília.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2014
.
p. 26-39.
ISSN 2595-6167.
