Andre Leon Sampaio Gradvohl - DTI     Professor Doutor MS-3.2 - RDIDP.

IEEE Senior Member.
Pós-Doutorado em Sistemas Distribuídos, Laboratoire d'Informatique de Paris 6, Université Pierre et Marie Curie (Paris VI), França, 2014.
Doutor em Telecomunicações, Faculdade de Engenharia Elétrica e Computação da UNICAMP (FEEC/UNICAMP), 2005.
Mestre em Engenharia Eletrônica e Computação, Instituto Tecnológico de Aeronáutica (ITA), 2000.
Especialista em Jornalismo Científico, Laboratório de Estudos Avançados em Jornalismo, UNICAMP, 2010.
Bacharel em Computação, Universidade Federal do Ceará (UFC), 1997.

E-Mail: gradvohl@ft.unicamp.br
Página Pessoal: https://www.visualcv.com/andre-leon-gradvohl
Telefone: (19) 2113-3343



Áreas de Interesse:

Algumas Publicações:
  • Combinando TV Interativa e Hipervídeo
    Apresenta uma implementação para televisão interativa, baseada no conceito de hipervídeo. A inovação que o conceito de hipervídeo proposto neste texto traz é a possibilidade de se associar informações complementares aos objetos apresentados nas cenas.
    Veja detalhes no IEEE.
  • Comparing Distributed Online Stream Processing Systems Considering Fault Tolerance Issues
    An analysis of four online stream processing systems (MillWheel, S4, Spark Streaming and Storm) regarding the strategies they use for fault tolerance.
    Available at JETWI.
  • An approach for interactive television based on insertion of hypermedia information in MPEG standard video
    The idea reported in this paper implements an approach to transmit complementary information about the content being watched in a digital video coded in Moving Pictures Experts Group (MPEG) standard format.
    Available at IEEE.
  • Solar filaments detection using parallel programming in hybrid architectures
    Describes our parallel OpenMP-MPI hybrid solutions for processing Sun images, and our results obtained in a hybrid system, i.e. a cluster with several multi-core nodes.
    Available at ACM.
  • Metalanguage for high-performance computing on hybrid architectures
    Artigo em Português. Disponível na IEEE.
    In high-performance computing, hybrid systems are defined as architectures where shared and distributed memory systems coexist. To explore most of the potential of such systems, programmer usually need more than one programming model simultaneously. For distributed memory systems, the master/worker model with message exchange is commonly used. In that case, the MPI is the most used programming library. On the other hand, for shared memory systems, the fork/join model, as used by PThreads and OpenMP application programming interfaces, are de facto standards. In this paper, I propose a metalanguage to combine both programming models. The metalanguage has annotated statements to specify which parts of code runs in shared memory systems and which others runs in distributed memory systems. A metacompiler will translate the metalanguage and will generate a C code with OpenMP pragmas, PThreads and MPI function calls. As a result, I show that the programs written using metalanguage code are more clean and understandable. Therefore, it is easier to program high-performance computing programs with it.
  • Gaspra - software for astronomical image processing in high-performance computing clusters
    There is a huge amount of information generated by telescopes as astronomical images. Therefore, software and equipment could process these images to find new phenomena and obtain new knowledge about the space. Considering the need of rapid processing of those images, we present a software for astronomical image processing in high-performance computing clusters, which use shared and distributed memory systems, called Gaspra. We designed Gaspra to batch process large sets of astronomical images, allowing researchers to create scientific workflows to obtain new knowledge from these astronomy imagery data sets. Experiments with Gaspra show a 3.5-fold speedup to process a single image in 5 processing nodes, each node supporting 64 different threads.
    Available at RBCA.
  • Investigating Metrics to Build a Benchmark Tool for Complex Event Processing Systems
    In this paper, we summarized some key metrics used to assess systems for processing online data streams. In addition, we discuss three benchmark tools found in the literature to assess this type of system. At the end of this paper, we propose a new benchmark tool for complex event processing distributed systems called B2-4CEP, which incorporate the metrics described in this paper.
    Available at IEEE.

Disciplinas:
  • ST662 A - Linguagem e Técnicas de Programação III (Linguagem Java)
  • TT304 A/B - Sistemas Operacionais
  • XXX - Minicurso Introdução à Computação de Alto Desempenho  Material Didático
  • ST564A - Introdução a Teleprocessamento e Redes
  • ST762 B - Laboratório de Programação III (Linguagem Java)  Material Didático
  • TT106 - Organização e Arquitetura de Computadores
  • XXX - Minicurso Introdução ao OpenMP  Material Didático
  • ST096 - Ciência, Tecnologia e Sociedade
  • FT077 - Processamento de Alto Desempenho

Projetos e Pesquisas:

Links Interessantes:
  • HighPIDS - Research group web page
  • Currículo Lattes
  • Somos Unicamp

  • Arquivos para Downloads:
    • XXX - Minicurso Introdução ao OpenMP   Download

    Endereço:
    Universidade Estadual de Campinas - UNICAMP
    Faculdade de Tecnologia - FT 

    Rua Paschoal Marmo, 1888 - Jardim Nova Itália 
    CEP:13484-332 
    Limeira - SP - Brasil 
    Fone/Fax: +55 (19) 2113-3368 / 2113-3339


    Esta página não é uma publicação oficial da Unicamp, seu conteúdo não foi examinado e/ou editado por esta instituição.
    A responsabilidade do seu conteúdo é exclusivamente do autor.