Parallel Applications Modelling Group

GMAP is a research group at Pontifical Catholic University of Rio Grande do Sul (PUCRS). Historically, the group has carried out several researches about modeling and adapting real world and robust applications from different domains (physics, mathematics, geology, image processing, biology, aerospace, and many others) to run efficiently in High-Performance Computing (HPC) architectures. GMAP researchers are also working on ways to design and provide new parallelism abstractions for the next generation computer architectures and algorithms. The goal is to simplify parallel programming for application programmers, providing new domain-specific languages, libraries, and frameworks.

Research Lines

High-level and Structured Parallelism Abstractions

The research line HSPA (High-level and Structured Parallelism Abstractions) aims to create programming interfaces for the user/programmer who is not able in dealing with parallel programming paradigm. The idea is to offer a higher level of abstraction, where the performance of applications is not compromised. The interfaces developed in this research line go toward specific domains that can later extend to other areas. The scope of the study is broad as regards the use of technologies for the development of the interface and parallelism.

Parallel Application Modeling

The Parallel Applications Modelling research line is centered on the study of high performance solutions for problems originated in other areas of knowledge (Biology, Geology, Physics, etc). The development of high performance solutions for problems requires a grasp in many levels of specialized knowledge. Besides an analysis of the algorithmic complexity of the problem to be parallelized, it is also necessary to have knowledge about the developing environments and program tests, parallel programming techniques, performance evaluations and high performance architectures.

Energy Efficiency in High Performance Environments

This research line aims to study and propose software solutions to reduce energy consumption in high-performance environments. Target environments of research developed in this line are: clusters, grids, and clouds. We can highlight as examples of proposed solutions the creation of scheduling policies as well as the use of hardware techniques, aimed to reduce energy consumption in running large applications.

Team

Prof. Dr. Luiz Gustavo Leão Fernandes

Group Head

He works with big data and stream processing, application modeling for high performance computing, cloud computing, performance evaluation, energy efficiency and verified computing for high performance computing, scientific computing, and methodologies, languages, and libraries for parallel programming.

Prof. Dr. Dalvan Griebler

Research Coordinator

He works with high-level parallelism abstractions, compiler design, source-to-source transformations, high-performance computing, applications, architectures, parallel programming tools, open source cloud computing platforms, and virtualization technologies.

Last Papers

142 entries « 1 of 29 »

2020

Garcia, Adriano M; Serpa, Matheus; Griebler, Dalvan; Schepke, Claudio; Fernandes, Luiz G L; Navaux, Philippe O A

The Impact of CPU Frequency Scaling on Power Consumption of Computing Infrastructures Book Chapter doi

Gervasi, Osvaldo; Murgante, Beniamino; Misra, Sanjay; Garau, Chiara; ć, Ivan Ble{č}i; Taniar, David; Apduhan, Bernady O; Rocha, Ana Maria A C; Tarantino, Eufemia; Torre, Carmelo Maria; Karaca, Yeliz (Ed.): Computational Science and Its Applications -- ICCSA 2020, pp. 142–157, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-58817-5.

Abstract | Links

Stein, Charles M; Rockenbach, Dinei A; Griebler, Dalvan; Torquati, Massimo; Mencagli, Gabriele; Danelutto, Marco; Fernandes, Luiz G

Latency‐aware adaptive micro‐batching techniques for streamed data compression on graphics processing units Journal Article doi

Concurrency and Computation: Practice and Experience, na (na), pp. e5786, 2020.

Abstract | Links

Löff, Junior; Griebler, Dalvan; Fernandes, Luiz G L

Implementação Paralela do LU no NPB C++ Utilizando um Pipeline Implícito Inproceedings doi

XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS), pp. 37-40, Sociedade Brasileira de Computação (SBC), Santa Maria, BR, 2020.

Abstract | Links

de Araújo, Gabriell Alves; Griebler, Dalvan; Fernandes, Luiz G L

Implementação CUDA dos Kernels NPB Inproceedings doi

XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS), pp. 85-88, Sociedade Brasileira de Computação (SBC), Santa Maria, BR, 2020.

Abstract | Links

Hoffmann, Renato Barreto; Griebler, Dalvan; Fernandes, Luis G L

Geração Automática de Código TBB na SPar Inproceedings doi

XX Escola Regional de Alto Desempenho da Região Sul (ERAD-RS), pp. 97-100, Sociedade Brasileira de Computação (SBC), Santa Maria, BR, 2020.

Abstract | Links

142 entries « 1 of 29 »

Projects

GMAP is involved in various research projects in many areas of computing. To see a list of all completed or ongoing projects, please visit the Projects page.

Last News

Online meeting with GMAP members

Due to the current restrictions imposed by COVID-19, since April 13 this year, meetings with GMAP members have been held every two weeks via videoconference. The meetings are guided by the general coordinator Prof. Dr. Luiz Gustavo Fernandes with the collaboration of the research coordinator Prof. Dr. Dalvan Griebler. Online meetings are a space for…

GMAP members win the Best Paper Award at an international conference.

GMAP members Adriano Marques Garcia, Dalvan Griebler, and Luiz Gustavo Fernandes, together with co-authors Matheus Serpa (UFRGS), Claudio Schepke (UNIPAMPA) and Philippe Navaux (UFRGS) won the best paper award at the 20th International Conference on Computational Science and its Applications (ICCSA 2020). The event took place from 1 to 4 July in the city of…

Students and Researchers from GMAP have Papers Accepted for Publication at ERAD/RS 2020

This year, as in all the last years, GMAP submitted papers to the High-Performance Regional School of Rio Grande do Sul (ERAD/RS). The ERAD works as a way to disseminate knowledge in the area of High-Performance Computing and related areas. In 2020, there were 6 submissions, and all accepted for publication. The authors of the…

Contact us!

If you have any questions or proposals, whether you are a student or a company seeking partnership for research projects, we are available!

Address

Av. Ipiranga, 6681
Prédio 32, Sala 601 – 6º andar
Porto Alegre – RS / Brazil
Zip code: 90619-900

Phone number

+55 51 33203611
Phone extension: 8601

Email

gmap.poa@gmail.com

Or, feel free to use the form below to contact us.

Send