@inproceedings{HOFFMANN:ERAD:20,
title = {Geração Automática de Código TBB na SPar},
author = {Renato Barreto Hoffmann and Dalvan Griebler and Luiz Gustavo Fernandes},
url = {https://doi.org/10.5753/eradrs.2020.10765},
doi = {10.5753/eradrs.2020.10765},
year = {2020},
date = {2020-04-01},
booktitle = {XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS)},
pages = {97-100},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Santa Maria, BR},
abstract = {Técnicas de programação paralela são necessárias para extrair todo o potencial dos processadores de múltiplos núcleos. Para isso, foi criada a SPar, uma linguagem para abstração do paralelismo de stream. Esse trabalho descreve a implementação da geração de código automática para a biblioteca TBB na SPar, uma vez que gerava-se código para FastFlow. Os testes com aplicações resultaram em tempos de execução até 12,76 vezes mais rápidos.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{JUSTO:ERAD:20,
title = {Acelerando uma Aplicação de Detecção de Pistas com MPI},
author = {Gabriel Justo and Renato Barreto Hoffmann and Adriano Vogel and Dalvan Griebler and Luiz Gustavo Fernandes},
url = {https://doi.org/10.5753/eradrs.2020.10770},
doi = {10.5753/eradrs.2020.10770},
year = {2020},
date = {2020-04-01},
booktitle = {XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS)},
pages = {117-120},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Santa Maria, BR},
abstract = {Aplicações de stream de vídeo demandam processamento de alto desempenho para atender requisitos de tempo real. Nesse cenário, a programação paralela distribuída é uma alternativa para acelerar e escalar o desempenho. Neste trabalho, o objetivo é paralelizar uma aplicação de detecção de pistas com a biblioteca MPI usando o padrão Farm e implementando duas estratégias de distribuição de tarefas. Os resultados evidenciam os ganhos de desempenho.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{GARCIA:ERAD:20,
title = {Proposta de uma Suíte de Benchmarks para Processamento de Stream em Sistemas Multi-Core},
author = {Adriano Marques Garcia and Dalvan Griebler and Luiz Gustavo Fernandes},
url = {https://doi.org/10.5753/eradrs.2020.10790},
doi = {10.5753/eradrs.2020.10790},
year = {2020},
date = {2020-04-01},
booktitle = {XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS)},
pages = {167-168},
publisher = {Sociedade Brasileira de Computação (SBC)},
address = {Santa Maria, BR},
abstract = {O aumento no volume de dados gerados por sistemas computacionais e a necessidade por processamento rápido desses dados vem alavancando a área de processamento de stream. Entretanto, ainda não existe um benchmark para auxiliar desenvolvedores e pesquisadores. Este trabalho visa propor uma suíte de benchmarks para processamento de stream em arquiteturas multi-core e discute as características necessárias no desenvolvimento dessa suíte.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{ARAUJO:PDP:20,
title = {Efficient NAS Parallel Benchmark Kernels with CUDA},
author = {Gabriell Alves de Araujo and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},
url = {https://doi.org/10.1109/PDP50117.2020.00009},
doi = {10.1109/PDP50117.2020.00009},
year = {2020},
date = {2020-03-01},
booktitle = {28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},
pages = {9-16},
publisher = {IEEE},
address = {Västerås, Sweden, Sweden},
series = {PDP'20},
abstract = {NAS Parallel Benchmarks (NPB) are one of the standard benchmark suites used to evaluate parallel hardware and software. There are many research efforts trying to provide different parallel versions apart from the original OpenMP and MPI. Concerning GPU accelerators, there are only the OpenCL and OpenACC available as consolidated versions. Our goal is to provide an efficient parallel implementation of the five NPB kernels with CUDA. Our contribution covers different aspects. First, best parallel programming practices were followed to implement NPB kernels using CUDA. Second, the support of larger workloads (class B and C) allow to stress and investigate the memory of robust GPUs. Third, we show that it is possible to make NPB efficient and suitable for GPUs although the benchmarks were designed for CPUs in the past. We succeed in achieving double performance with respect to the state-of-the-art in some cases as well as implementing efficient memory usage. Fourth, we discuss new experiments comparing performance and memory usage against OpenACC and OpenCL state-of-the-art versions using a relative new GPU architecture. The experimental results also revealed that our version is the best one for all the NPB kernels compared to OpenACC and OpenCL. The greatest differences were observed for the FT and EP kernels.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{VOGEL:CCIS:20,
title = {Parallel Stream Processing with MPI for Video Analytics and Data Visualization},
author = {Adriano Vogel and Cassiano Rista and Gabriel Justo and Endrius Ewald and Dalvan Griebler and Gabriele Mencagli and Luiz Gustavo Fernandes},
url = {https://doi.org/10.1007/978-3-030-41050-6_7},
doi = {10.1007/978-3-030-41050-6_7},
year = {2020},
date = {2020-02-01},
booktitle = {High Performance Computing Systems},
volume = {1171},
pages = {102-116},
publisher = {Springer},
address = {Cham},
series = {Communications in Computer and Information Science (CCIS)},
abstract = {The amount of data generated is increasing exponentially. However, processing data and producing fast results is a technological challenge. Parallel stream processing can be implemented for handling high frequency and big data flows. The MPI parallel programming model offers low-level and flexible mechanisms for dealing with distributed architectures such as clusters. This paper aims to use it to accelerate video analytics and data visualization applications so that insight can be obtained as soon as the data arrives. Experiments were conducted with a Domain-Specific Language for Geospatial Data Visualization and a Person Recognizer video application. We applied the same stream parallelism strategy and two task distribution strategies. The dynamic task distribution achieved better performance than the static distribution in the HPC cluster. The data visualization achieved lower throughput with respect to the video analytics due to the I/O intensive operations. Also, the MPI programming model shows promising performance outcomes for stream processing applications.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}