???global.info.a_carregar???
Dr. Geancarlo Abich is a Brazilian researcher that works on projects for software/hardware acceleration and reliability evaluation of Machine Learning models focused on edge computing. He received his bachelors degree in computing engineering from UNISC (Universidade de Santa Cruz do Sul), Brazil, 14', Masters degree in Computing and Ph.D. degree in Microelectronics from UFRGS (Universidade Federal do Rio Grande do Sul), Brazil, 17' and 22’, advised by the Prof. Ricardo Reis (UFRGS) and co-advised by Prof. Luciano Ost (Loughborough University) where he received the highest grade and his thesis advances become in a Book published by Springer Nature. In the earlier work, he contributed to the development of NoC-based MPSoCs management systems, soft-error reliability evaluation tools, and parallelism exploration on specialized neural network libraries. During his Ph.D. studies, Dr. Abich collaborated mainly with Prof. Luciano Ost at Loughborough University and also with companies such as IMPERAS and Arm (University Program). In the last year he worked as a postdoctoral fellow in the extension of his thesis to evaluate the performance and power costs of parallelism and fault mitigation in machine learning models aimed at resource-constrained devices. At the moment he holds a postdoctoral position at INESC-ID as team lead on performance modeling for advanced RISC-V architectures over the Horizon EU SYCLOPS project. The research of Dr. Geancarlo Abich focuses on achieving efficiency at different levels of abstraction, driving both performance gains and reliability at the software and hardware level by exploring the design space for new technologies to deploy AI at the extreme edge. He is currently collaborating with Prof. Luciano Ost (Loughborough University - UK), Prof. Ricardo Reis (UFRGS - Brazil), Prof. Leonel Souza and Prof. Aleksandar Ilic (INESC-ID - Portugal). The research he has been conducting in collaboration with their partners, including Universities from the UK, Brazil, and industrial partners like ARM and Imperas, led to the publication of 1 book, 4 journal papers, and 9 peer-reviewed international conferences.
Identificação

Identificação pessoal

Nome completo
Geancarlo Abich
Data de nascimento
1990/11/22
Género
Masculino

Nomes de citação

  • Abich, Geancarlo
  • Abich, G

Identificadores de autor

Ciência ID
FC18-5A6E-F581
ORCID iD
0000-0001-9387-1523
Google Scholar ID
d7fcdVwAAAAJ
LattesiD
http://lattes.cnpq.br/0218273654317320
Researcher Id
rid57843
Scopus Author Id
57193626912

Endereços de correio eletrónico

  • abich@ieee.org (Profissional)
  • geancarlo.abich@inesc-id.pt (Profissional)

Telefones

Telefone
  • 213100300 Ext.: 308 (Profissional)

Moradas

  • Rua Alves Redol, 9, Room 308, 1000-029, Lisboa, Lisboa, Portugal (Profissional)

Websites

Domínios de atuação

  • Ciências da Engenharia e Tecnologias - Engenharia Eletrotécnica, Eletrónica e Informática - Hardware e Arquitetura de Computadores
  • Ciências da Engenharia e Tecnologias - Engenharia Eletrotécnica, Eletrónica e Informática - Hardware e Arquitetura de Computadores

Idiomas

Idioma Conversação Leitura Escrita Compreensão Peer-review
Português (Idioma materno)
Inglês Utilizador proficiente (C1) Utilizador proficiente (C1) Utilizador proficiente (C1) Utilizador proficiente (C1) Utilizador proficiente (C1)
Espanhol; Castelhano Utilizador independente (B1) Utilizador independente (B1) Utilizador independente (B1) Utilizador independente (B1) Utilizador independente (B1)
Formação
Grau Classificação
2017/05/20 - 2022/03/16
Concluído
Pós Graduação em Microeletrônica (Doctor)
Especialização em Radiation Effects in Embedded Systems
Universidade Federal do Rio Grande do Sul, Brasil
"Early soft error reliability assessment of convolutional neural networks executing on resource-constrained IoT edge devices" (TESE/DISSERTAÇÃO)
A
2015/03/01 - 2017/05/20
Concluído
Pós Graduação em Computação (Master)
Especialização em MPSoCs
Universidade Federal do Rio Grande do Sul, Brasil
"Extending FreeRTOS to support dynamic and distributed task mapping in multiprocessor systems" (TESE/DISSERTAÇÃO)
A
2008/03/01 - 2014/12/20
Concluído
Engenharia de Comptutação (Bachelor)
Especialização em MPSoCs
Universidade de Santa Cruz do Sul, Brasil
"Applications Mapping Optimization in MPSoCs for Increased Reliability and Lifetime." (TESE/DISSERTAÇÃO)
10
Percurso profissional

Ciência

Categoria Profissional
Instituição de acolhimento
Empregador
2023/02/19 - Atual Investigador Contratado (Investigação) Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal
2023/01/01 - 2023/12/31 Pós-doutorado (Investigação) Universidade Federal do Rio Grande do Sul, Brasil
Universidade Federal do Rio Grande do Sul, Brasil

Docência no Ensino Superior

Categoria Profissional
Instituição de acolhimento
Empregador
2022/02/23 - 2023/12/31 Professor Auxiliar (Docente Universitário) Universidade de Santa Cruz do Sul, Brasil
Universidade de Santa Cruz do Sul, Brasil
Projetos

Projeto

Designação Financiadores
2023/01/01 - Atual Scaling extreme analYtics with Cross-architecture acceLeration based on OPen Standards
Investigador Pós-doutorado
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento em Lisboa, Portugal
European Commission
Em curso
Produções

Publicações

Artigo em conferência
  1. Abich, Geancarlo; Garibotti, Rafael; Gava, Jonas; Reis, Ricardo; Ost, Luciano. "Impact of Thread Parallelism on the Soft Error Reliability of Convolution Neural Networks". 2022.
    10.1109/lascas53948.2022.9789088
  2. Abich, Geancarlo; Reis, Ricardo; Ost, Luciano. "The Impact of Precision Bitwidth on the Soft Error Reliability of the MobileNet Network". 2021.
    10.1109/lascas51355.2021.9667153
  3. Abich, Geancarlo; Gava, Jonas; Reis, Ricardo; Ost, Luciano. "Soft Error Reliability Assessment of Neural Networks on Resource-constrained IoT Devices". 2020.
    10.1109/icecs49266.2020.9294951
  4. Hamerski, Jean Carlo; Abich, Geancarlo; Reis, Ricardo; Ost, Luciano; Amory, Alexandre. "A Design Patterns-Based Middleware for Multiprocessor Systems-on-Chip". 2018.
    10.1109/sbcci.2018.8533250
  5. Bortolon, Felipe T.; Abich, Geancarlo; Bampi, Sergio; Reis, Ricardo; Moraes, Fernando; Ost, Luciano. "Exploring the Impact of Soft Errors on NoC-based Multiprocessor Systems". 2018.
    10.1109/iscas.2018.8351391
  6. Hamerski, Jean Carlo; Abich, Geancarlo; Reis, Ricardo; Ost, Luciano; Amory, Alexandre. "Publish-subscribe programming for a NoC-based multiprocessor system-on-chip". 2017.
    10.1109/iscas.2017.8050967
  7. Abich, G.; Mandelli, M. G.; Rosa, F. R.; Moraes, F.; Ost, L.; Reis, R.. "Extending FreeRTOS to support dynamic and distributed mapping in multiprocessor systems". 2016.
    10.1109/icecs.2016.7841301
Artigo em revista
  1. Jonas Gava; Alex Hanneman; Geancarlo Abich; Rafael Garibotti; Sergio Cuenca-Asensi; Rodrigo Possamai Bastos; Ricardo Reis; Luciano Ost. "A Lightweight Mitigation Technique for Resource-constrained Devices Executing DNN Inference Models under Neutron Radiation". IEEE Transactions on Nuclear Science (2023): https://doi.org/10.1109/TNS.2023.3262448.
    10.1109/TNS.2023.3262448
  2. Geancarlo Abich; Rafael Garibotti; Ricardo Reis; Luciano Ost. "The Impact of Soft Errors in Memory Units of Edge Devices Executing Convolutional Neural Networks". IEEE Transactions on Circuits and Systems II: Express Briefs (2022): https://doi.org/10.1109/TCSII.2022.3141243.
    10.1109/TCSII.2022.3141243
  3. Geancarlo Abich; Jonas Gava; Rafael Garibotti; Ricardo Reis; Luciano Ost. "Applying Lightweight Soft Error Mitigation Techniques to Embedded Mixed Precision Deep Neural Networks". IEEE Transactions on Circuits and Systems I: Regular Papers (2021): https://doi.org/10.1109/TCSI.2021.3097981.
    10.1109/TCSI.2021.3097981
  4. Geancarlo Abich; Rafael Garibotti; Vitor Bandeira; Felipe da Rosa; Jonas Gava; Felipe Bortolon; Guilherme Medeiros; et al. "Evaluation of the soft error assessment consistency of a JIT-based virtual platform simulator". IET Computers & Digital Techniques (2021): https://doi.org/10.1049/cdt2.12017.
    10.1049/cdt2.12017
Livro
  1. Abich, G; Ost, Luciano; Reis, Ricardo. Autor correspondente: Abich, G. Early Soft Error Reliability Assessment of Convolutional Neural Networks Executing on Resource-Constrained IoT Edge Devices. Suiça: Springer Nature Switzerland. 2023.
    Publicado • 10.1007/978-3-031-18599-1