Grupo de Modelagem de Aplicações Paralelas

@inproceedings{ARAUJO:stream:ERAD:19,
title = {Avaliando o Paralelismo de Stream com Pthreads, OpenMP e SPar em Aplicações de Vídeo},
author = {Gabriell A. de Araujo and Dalvan Griebler and Luiz G. Fernandes},
url = {https://gmap.pucrs.br/dalvan/papers/2019/CR_ERAD_IC_Araujo_2019.pdf},
year = {2019},
date = {2019-04-01},
booktitle = {Escola Regional de Alto Desempenho (ERAD/RS)},
pages = {4},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Três de Maio, BR},
abstract = {isando estender os estudos de avaliação daSPar, efetuamos umaanálise comparativa entre SPar,Pthreadse OpenMP em aplicações destream. Os resultados revelam que o desempenho do código paralelo geradopela SPar se equipara com as implementações robustas nas consolidadas bibliotecas Pthreads e OpenMP. Não obstante, também encontramos pontos depossíveis melhorias na SPar.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{ARAUJO:gpu:ERAD:19,
title = {Revisando a Programação Paralela com CUDA nos Benchmarks EP e FT},
author = {Gabriell A. de Araujo and Dalvan Griebler and Luiz G. Fernandes},
url = {https://gmap.pucrs.br/dalvan/papers/2019/CR_ERAD_IC_Gabriell_2019.pdf},
year = {2019},
date = {2019-04-01},
booktitle = {Escola Regional de Alto Desempenho (ERAD/RS)},
pages = {4},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Três de Maio, BR},
abstract = {Este trabalho visa estender os estudos sobre o NAS Parallel Ben-chmarks (NPB), os quais possuem lacunas relevantes no contexto de GPUs.Os principais trabalhos da literatura consistem em implementações antigas,abrindo margens para possíveis questionamentos. Nessa direção, foram rea-lizados novos estudos de paralelização para GPUs das aplicações EP e FT. Osresultados foram similares ou melhores que o estado-da-arte.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{JUSTO:ERAD:19,
title = {Acelerando o Reconhecimento de Pessoas em Vídeos com MPI},
author = {Gabriel B. Justo and Adriano Vogel and Dalvan Griebler and Luiz G. Fernandes},
url = {https://gmap.pucrs.br/dalvan/papers/2019/CR_ERAD_IC_Justo_2019.pdf},
year = {2019},
date = {2019-04-01},
booktitle = {Escola Regional de Alto Desempenho (ERAD/RS)},
pages = {4},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Três de Maio, BR},
abstract = {Diversas aplicações de processamento de vídeo demandam paralelismo para aumentar o desempenho. O objetivo deste trabalho é implementar etestar versões com processamento distribuído em aplicações de reconhecimentofacial em vídeos. As implementações foram avaliadas quanto ao seu desempe-nho. Os resultados mostraram que essas aplicações podem ter uma aceleraçãosignificativa em ambientes distribuídos.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{STEIN:LZSS-multigpu:PDP:19,
title = {Stream Parallelism on the LZSS Data Compression Application for Multi-Cores with GPUs},
author = {Charles Michael Stein and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},
url = {https://doi.org/10.1109/EMPDP.2019.8671624},
doi = {10.1109/EMPDP.2019.8671624},
year = {2019},
date = {2019-02-01},
booktitle = {27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},
pages = {247-251},
publisher = {IEEE},
address = {Pavia, Italy},
series = {PDP'19},
abstract = {GPUs have been used to accelerate different data parallel applications. The challenge consists in using GPUs to accelerate stream processing applications. Our goal is to investigate and evaluate whether stream parallel applications may benefit from parallel execution on both CPU and GPU cores. In this paper, we introduce new parallel algorithms for the Lempel-Ziv-Storer-Szymanski (LZSS) data compression application. We implemented the algorithms targeting both CPUs and GPUs. GPUs have been used with CUDA and OpenCL to exploit inner algorithm data parallelism. Outer stream parallelism has been exploited using CPU cores through SPar. The parallel implementation of LZSS achieved 135 fold speedup using a multi-core CPU and two GPUs. We also observed speedups in applications where we were not expecting to get it using the same combine data-stream parallel exploitation techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{MARON:parametric-parsec:PDP:19,
title = {Should PARSEC Benchmarks be More Parametric? A Case Study with Dedup},
author = {Carlos A. F. Maron and Adriano Vogel and Dalvan Griebler and Luiz Gustavo Fernandes},
url = {https://doi.org/10.1109/EMPDP.2019.8671592},
doi = {10.1109/EMPDP.2019.8671592},
year = {2019},
date = {2019-02-01},
booktitle = {27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},
pages = {217-221},
publisher = {IEEE},
address = {Pavia, Italy},
series = {PDP'19},
abstract = {Parallel applications of the same domain can present similar patterns of behavior and characteristics. Characterizing common application behaviors can help for understanding performance aspects in the real-world scenario. One way to better understand and evaluate applications' characteristics is by using customizable/parametric benchmarks that enable users to represent important characteristics at run-time. We observed that parameterization techniques should be better exploited in the available benchmarks, especially on stream processing domain. For instance, although widely used, the stream processing benchmarks available in PARSEC do not support the simulation and evaluation of relevant and modern characteristics. Therefore, our goal is to identify the stream parallelism characteristics present in PARSEC. We also implemented a ready to use parameterization support and evaluated the application behaviors considering relevant performance metrics for stream parallelism (service time, throughput, latency). We choose Dedup to be our case study. The experimental results have shown performance improvements in our parameterization support for Dedup. Moreover, this support increased the customization space for benchmark users, which is simple to use. In the future, our solution can be potentially explored on different parallel architectures and parallel programming frameworks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}