A list of my most relevant publications is available here. In most cases, you can also get direct access to the bibliography information in LaTeX style as well as to the publishers’ sites to download them. You can also find my most relevant publications on Google Scholar, DBLP and Scopus. Please, visit my Lattes CV (in portuguese) for a full list of publications and projects.

             

Selected Journals

2024

• Samuel Fidelis, Márcio Castro, Frank Siqueira. Improving Edge AI for Industrial IoT Applications with Distributed Learning using Consensus. In: Design Automation for Embedded Systems (DAEM), 2024. pdf bib

2023

• Vanderlei Munhoz, Márcio Castro. Enabling the Execution of HPC Applications on Public Clouds with HPC@Cloud Toolkit. In: Concurrency and Computation: Practice and Experience (CCPE), 2023. pdf bib

2022

• João V. Souto, Márcio Castro. Improving Concurrency and Memory Usage in Distributed Operating Systems for Lightweight Manycores via Cooperative Time-sharing Lightweight Tasks. In: Journal of Parallel and Distributed Computing (JPDC), 2022. pdf bib

2021

• João F. Uller, João V. Souto, Pedro H. Penna, Márcio Castro, Henrique Freitas, Jean-François Méhaut. LWMPI: An MPI Library for NoC-Based Lightweight Manycore Processors with On-Chip Memory Constraints. In: Concurrency and Computation: Practice and Experience (CCPE), 2021. pdf bib

• Pedro H. Penna, João V. Souto, João F. Uller, Márcio Castro, Henrique Freitas, Jean-François Méhaut. Inter-Kernel Communication Facility of a Distributed Operating System for NoC-Based Lightweight Manycores. In: International Journal of Parallel and Distributed Computing (JPDC), 2021. pdf bib

• Alexandre Santana, Vinicius Freitas, Márcio Castro, Laércio L. Pilla, Jean-François Méhaut. ARTful: A Model for User-defined Schedulers Targeting Multiple HPC Runtime Systems. In: Software: Practice and Experience (SPE), 2021. pdf bib

• Lais Borin, George Lima, Márcio Castro, Patrícia D. M. Plentz. Dynamic Power Management Under the RUN Scheduling Algorithm: A Slack Filling Approach. In: Real-Time Systems (RTS), 2021. pdf bib

• Vinicius Freitas, Laércio L. Pilla, Alexandre de L. Santana, Márcio Castro, Johanne Cohen. PackStealLB: A Scalable Distributed Load Balancer based on Work Stealing and Workload Discretization. In: International Journal of Parallel and Distributed Computing (JPDC), v.150, 2021. pdf bib

2020

• Pedro H. Penna, Lucas A. Maciel, João V. Souto, Davidson F. Lima, Márcio Castro, François Broquedis, Henrique Freitas, Jean-François Méhaut. Co-Designing Clusters of Lightweight Manycores and Asymmetric Operating System Kernels. In: IEEE Embedded Systems Letters (LES), 2020. pdf bib

2019

• Pedro H. Penna, Antônio Tadeu A. Gomes, Márcio Castro, Patrícia D. M. Plentz, Henrique C. Freitas, François Broquedis, Jean-François Méhaut. A Comprehensive Performance Evaluation of the BinLPT Workload‐aware Loop Scheduler. In: Concurrency and Computation: Practice and Experience (CCPE), v. 31, no. 18, 2019. pdf bib

2017

• Sérgio G. Pfleger, Patrícia D. M. Plentz, Rodrigo C. O. Rocha, Alyson D. Pereira, Márcio Castro. Real-Time Video Denoising on Multicores and GPUs with Kalman-based and Bilateral Filters Fusion. In: Journal of Real-Time Image Processing (JRTIP), v. 16, no. 5, 2017. pdf bib

• Matheus A. Souza, Pedro H. Penna, Matheus M. Queiroz, Luís F. W. Góes, Henrique C. Freitas, Márcio Castro, Philippe O. A. Navaux, Jean-François Méhaut. CAP Bench: A Benchmark Suite for Performance and Energy Evaluation of Low-Power Many-Core Processors. In: Concurrency and Computation: Practice and Experience (CCPE), v. 29, no. 4, 2017. pdf bib

2016

• Pedro H. Penna, Márcio Castro, Henrique C. Freitas, François Broquedis, Jean-François Méhaut. Design Methodology for Workload-Aware Loop Scheduling Strategies Based on Genetic Algorithm and Simulation. In: Concurrency and Computation: Practice and Experience (CCPE), v. 29, no. 22, 2016. pdf bib

• Márcio Castro, Emilio Francesquini, Fabrice Dupros, Hideo Aochi, Philippe O. A. Navaux, Jean-François Méhaut. Seismic Wave Propagation Simulations on Low-power and Performance-centric Manycores. In: Parallel Computing (PARCO), v. 54, 2016. pdf bib

2015

• Laércio L. Pilla, Tiago C. Bozzetti, Márcio Castro, Philippe O. A. Navaux, Jean-François Méhaut. ComprehensiveBench: A Benchmark for the Extensive Evaluation of Global Scheduling Algorithms. In: Journal of Physics: Conference Series (JPCS), v. 649, 2015. pdf bib

• Emilio Francesquini, Márcio Castro, Pedro H. Penna, Fabrice Dupros, Henrique C. Freitas, Philippe O. A. Navaux, Jean-François Méhaut. On the Energy Efficiency and Performance of Irregular Application Executions on Multicore, NUMA and Manycore Platforms. In: International Journal of Parallel and Distributed Computing (JPDC), v. 76, 2015. pdf bib

• Edson L. Padoin, Laércio L. Pilla, Márcio Castro, Francieli Z. Boito, Philippe O. A. Navaux, Jean-François Méhaut. Performance/Energy Trade-off in Scientific Computing: The Case of ARM big.LITTLE and Intel Sandy Bridge. In: IET Computers & Digital Techniques (IET-CDT), v. 9, 2015. pdf bib

2014

• Márcio Castro, Luís F. W. Góes, Jean-François Méhaut. Adaptive Thread Mapping Strategies for Transactional Memory Applications. In: International Journal of Parallel and Distributed Computing (JPDC), v. 74, 2014. pdf bib

• Luís F. W. Góes, Christiane P. Ribeiro, Márcio Castro, Jean-François Méhaut, Murray Cole, Marcelo Cintra. Automatic Skeleton-Driven Memory Affinity for Transactional Worklist Applications. In: International Journal of Parallel Programming (IJPP), v. 42, 2014. pdf bib

2012

• Christiane P. Ribeiro, Márcio Castro, Vania Marangonzova-Martin, Jean-François Méhaut, Henrique C. Freitas, Carlos A. P. S. Martins. Evaluating CPU and Memory Affinity for Numerical Scientific Multithreaded Benchmarks on Multi-cores. In: IADIS International Journal on Computer Science and Information Systems (IJCSIS), no. 1, ISSN: 1646-3692, 2012. pdf bib

Selected Conferences

2023

• Vanderlei Munhoz, Antoine Bonfils, Márcio Castro, Odorico Mendizabal. A Performance Comparison of HPC Workloads on Traditional and Cloud-based HPC Clusters. Workshop on Cloud Computing (WCC) - International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Porto Alegre, Brazil: IEEE Computer Society, 2023. pdf bib

• Accepted Vanderlei Munhoz, Márcio Castro, Luis G. C. Rego. Evaluating the Parallel Simulation of Dynamics of Electrons in Molecules on AWS Spot Instances. Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Porto Alegre, Brazil: SBC, 2023.

• Accepted Pedro M. C. Neto, Márcio Castro, Frank Siqueira. Balanceamento de Carga Dinâmico em Ambientes Kubernetes com o Kubernetes Scheduling Extension (KSE). Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Porto Alegre, Brazil: SBC, 2023.

• Accepted Nicolas Vanz, João V. Souto, Márcio Castro. Virtualização e Migração de Processos em um Sistema Operacional Distribuído para Lightweight Manycores. Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Porto Alegre, Brazil: SBC, 2023.

2022

• Vanderlei Munhoz, Márcio Castro, Odorico Mendizabal. Strategies for Fault-Tolerant Tightly-coupled HPC Workloads Running on Low-Budget Spot Cloud Infrastructures. International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Bordeaux, France: IEEE Computer Society, 2022. pdf bib

• Vanderlei Munhoz, Márcio Castro. HPC@Cloud: A Provider-Agnostic Software Framework for Enabling HPC in Public Cloud Platforms. Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Florianópolis, Brazil: SBC, 2022. pdf bib

• Best Paper Samuel Fidelis, Márcio Castro, Frank Siqueira. Distributed Learning using Consensus on Edge AI. Brazilian Symposium on Computing Systems Engineering (SBESC). Fortaleza, Brazil: IEEE Computer Society, 2022. pdf bib

2021

• João V. Souto, Pedro H. Penna, Márcio Castro. A Task-based Execution Engine for Distributed Operating Systems Tailored to Lightweight Manycores with Limited On-Chip Memory. IEEE International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Belo Horizonte, Brazil: IEEE Computer Society, 2021. pdf bib

• Emmanuel Podestá Jr., Pedro H. Penna, João F. Uller, Márcio Castro. A Trace-driven Methodology to Evaluate and Optimize Memory Management Services of Distributed Operating Systems for Lightweight Manycores. ACM/SIGAPP Symposium On Applied Computing (SAC). Gwangju, South Korea: ACM, 2021. pdf bib

2020

• João F. Uller, João V. Souto, Pedro H. Penna, Márcio Castro, Henrique Freitas, Jean-François Méhaut. Enhancing Programmability in NoC-Based Lightweight Manycore Processors with a Portable MPI Library. Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Santo André, Brazil: SBC, 2020. pdf bib

• Anna V. Oikawa, Vinicius Freitas, Márcio Castro, Laércio L. Pilla. Adaptive Load Balancing based on Machine Learning for Iterative Parallel Applications. Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP). Västerås, Sweden: IEEE Computer Society, 2020. pdf bib

2019

• Pedro H. Penna, João V. Souto, Davidson F. Lima, Márcio Castro, François Broquedis, Henrique Freitas, Jean-François Méhaut. On the Performance and Isolation of Asymmetric Microkernel Design for Lightweight Manycores. Brazilian Symposium on Computing Systems Engineering (SBESC). Natal, Brazil: IEEE Computer Society, 2019. pdf bib

• Vinicius Freitas, Alexandre de L. Santana, Márcio Castro, Laércio L. Pilla. Distributed Memory Graph Representation for Load Balancing Data: Accelerating Data Structure Generation for Decentralized Scheduling. International Conference on High Performance Computing & Simulation (HPCS). Dublin, Ireland: IEEE Computer Society, 2019. pdf bib

• Pedro H. Penna, Matheus Souza, Emmanuel Podestá Jr., João V. Souto, Márcio Castro, François Broquedis, Henrique C. Freitas Jean-François Méhaut. RMem: An OS Service for Transparent Remote Memory Access in Lightweight Manycores. In: International Workshop on Programmability and Architectures for Heterogeneous Multicores (MULTIPROG). Valencia, Spain, 2019. pdf bib

2018

• Vinicius Freitas, Alexandre de L. Santana, Márcio Castro, Laércio L. Pilla. A Batch Task Migration Approach for Decentralized Global Rescheduling. In: International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Lyon, France: IEEE Computer Society, 2018. pdf bib

• Alexandre de L. Santana, Vinicius Freitas, Márcio Castro, Laércio L. Pilla, Jean-François Méhaut. Reducing Global Schedulers’ Complexity Through Runtime System Decoupling. In: Simpósio de Sistemas Computacionais de Alto Desempenho (WSCAD). São Paulo, Brazil: SBC, 2018. pdf bib

• Emmanuel Podestá Jr., Bruno M. do Nascimento, Márcio Castro. Energy Efficient Stencil Computations on the Low-Power Manycore MPPA-256 Processor. In: International European Conference on Parallel and Distributed Computing (Euro-Par). Turin, Italy: Springer, 2018. pdf bib

2017

• Alyson D. Pereira, Rodrigo Caetano O. Rocha, Márcio Castro, Luís Fabricio W. Góes, Mario A. R. Dantas. Extending OpenACC for Efficient Stencil Code Generation and Execution by Skeleton Frameworks. In: International Conference on High Performance Computing & Simulation (HPCS). Genoa, Italy: IEEE Computer Society, 2017. pdf bib

• Alyson D. Pereira, Rodrigo Caetano O. Rocha, Luiz Ramos, Márcio Castro, Luís Fabrício W. Góes. Automatic Partitioning of Stencil Computations on Heterogeneous Systems. In: Workshop on Applications for Multi-core Architectures (WAMCA) - International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Campinas, Brazil: IEEE Computer Society, 2017. pdf bib

• 2nd Best Paper Pedro H. Penna, Márcio Castro, Patricia D. M. Plentz, Henrique C. Freitas, François Broquedis, Jean-François Méhaut. BinLPT: A Novel Workload-Aware Loop Scheduler for Irregular Parallel Loops. In: Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD). Campinas, Brazil: Brazilian Computer Society, 2017. pdf bib

• Lais Borin, Márcio Castro, Patricia D. M. Plentz. Towards the Use of LITMUS-RT as a Testbed for Multiprocessor Scheduling in Energy Harvesting Real-time Systems. In: Brazilian Symposium on Computing Systems Engineering (SBESC). Curitiba, Brazil: IEEE Computer Society, 2017. pdf bib

• Pedro H. Penna, Henrique C. de Freitas, João Caram, Márcio Castro, Jean-François Méhaut. Using The Nanvix Operating System in Undergraduate Operating System Courses. In: Brazilian Symposium on Computing Systems Engineering (SBESC). Curitiba, Brazil: IEEE Computer Society, 2017. pdf bib

• Victor Martinez, Fabrice Dupros, Márcio Castro, Philippe O. A. Navaux. Performance Improvement of Stencil Computations for Multi-core Architectures based on Machine Learning. In: International Conference on Computational Science (ICCS). Zürich, Switzerland: Elsevier, 2017. pdf bib

• Pedro H. Penna, Eduardo C. Inacio, Márcio Castro, Patricia D. M. Plentz, Henrique C. Freitas, François Broquedis, Jean-François Méhaut. Assessing the Performance of the SRR Loop Scheduler with Irregular Workloads. In: International Conference on Computational Science (ICCS). Zürich, Switzerland: Elsevier, 2017. pdf bib

• Alyson Deives Pereira, Rodrigo Caetano O. Rocha, Márcio Castro, Luís Fabrício W. Góes, Mario Antonio Ribeiro Dantas. Enabling efficient stencil code generation in OpenACC. In: International Conference on Computational Science (ICCS). Zürich, Switzerland: Elsevier, 2017. pdf bib

• Felipe Volpato, Madalena P. da Silva, Alexandre L. Gonçalves, Márcio Castro, Mario A. R. Dantas. Provisioning and Delivering Sepsis Data Supported by an Enhanced SDN Environment. In: IEEE International Symposium on Computer-Based Medical Systems (CBMS). Thessaloniki, Greece: IEEE Computer Society, 2017. pdf bib

• Edson L. Padoin, Laércio L. Pilla, Márcio Castro, Philippe O. A. Navaux, Jean-François Méhaut. Exploration of Load Balancing Thresholds to Save Energy on Iterative Applications. In: Latin American High Performance Computing Conference (CARLA). Mexico City, Mexico: Springer, 2017. pdf bib

2016

• Renan Netto, Chrystian Guth, Vinicius Livramento, Márcio Castro, Laércio L. Pilla, José Luis Güntzel. Exploiting Parallelism to Speed Up Circuit Legalization. In: IEEE International Conference on Electronics, Circuits, & Systems (ICECS). Monte Carlo, Monaco: IEEE Computer Society, 2016. pdf bib

2014

• Edson L. Padoin, Márcio Castro, Laércio L. Pilla, Philippe O. A. Navaux, Jean-François Méhaut. Saving Energy by Exploiting Residual Imbalances on Iterative Applications. In: High Performance Computing Conference (HiPC). Goa, India: IEEE Computer Society, 2014. pdf bib

• Best Paper Márcio Castro, Fabrice Dupros, Emilio Francesquini, Jean-François Méhaut, Philippe O. A. Navaux. Energy Efficient Seismic Wave Propagation Simulation on a Low-power Manycore Processor. In: International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Paris, France: IEEE Computer Society, 2014. pdf bib

• Fernando Rui, Márcio Castro, Dalvan Griebler, Luiz Gustavo Fernandes. Evaluating the Impact of Transactional Characteristics on the Performance of Transactional Memory Applications. In: Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP). Turin, Italy: IEEE Computer Society, 2014. pdf bib

2013

• Márcio Castro, Emilio Francesquini, Thomas M. Nguélé, Jean-François Méhaut. Analysis of Computing and Energy Performance of Multicore, NUMA, and Manycore Platforms for an Irregular Application. In: Workshop on Irregular Applications: Architectures & Algorithms (IA³) - Supercomputing Conference (SC). Denver, USA: ACM, 2013. pdf bib

• Márcio Castro, Pedro Velho, Luiz Gustavo Fernandes, Jean-François Méhaut. A Parallel Approach to Fine-tune Field Emission Displays Using a Genetic Algorithm. In: Latin American Conference on High-Performance Computing (CLCAR). San José, Costa Rica, 2013. bib

2012

• Márcio Castro, Luís Fabrício W. Goés, Luiz Gustavo Fernandes, Jean-François Méhaut. Dynamic Thread Mapping Based on Machine Learning for Transactional Memory Applications. In: International European Conference on Parallel and Distributed Computing (Euro-Par). Vol. 7484. Lecture Notes in Computer Science (LNCS). Rhodes Island, Greece: Springer-Verlag, 2012. pdf bib

2011

• Márcio Castro, Luís Fabricio W. Góes, Christiane P. Ribeiro, Murray Cole, Marcelo Cintra, Jean-François Méhaut. A Machine Learning-Based Approach for Thread Mapping on Transactional Memory Applications. In: High Performance Computing Conference (HiPC). Bangalore, India: IEEE Computer Society, 2011. pdf bib

• Mateus Raeder, Dalvan Griebler, Neumar Ribeiro, Luiz Gustavo Fernandes, Márcio Castro. A Hybrid Parallel Version of ICTM for Cluster of NUMA Machines. In: IADIS International Conference on Applied Computing (AC). Rio de Janeiro, Brazil: IADIS Press, 2011. pdf bib

• Best Paper Poliana Oliveira, Henrique C. Freitas, Christiane P. Ribeiro, Márcio Castro, Vania Marangonzova-Martin, Jean-François Méhaut. Performance Evaluation of WiNoCs for Parallel Workloads Based on Collective Communications. In: IADIS International Conference on Applied Computing (AC). Rio de Janeiro, Brazil: IADIS Press, 2011. pdf bib

• Best Paper Christiane P. Ribeiro, Márcio Castro, Jean-François Méhaut, Vania Marangonzova-Martin, Henrique Freitas, Carlos A. P. S. Martins. Investigating the Impact of CPU and Memory Affinity on Multi-core Platforms: A Case Study of Numerical Scientific Multithreaded Applications. In: IADIS International Conference on Applied Computing (AC). Rio de Janeiro, Brazil: IADIS Press, 2011. pdf bib

• Márcio Castro, Kiril Georgiev, Vania Marangonzova-Martin, Jean-François Méhaut, Luiz Gustavo Fernandes, Miguel Santana. Analysis and Tracing of Applications Based on Software Transactional Memory on Multicore Architectures. In: Euromicro International Conference on Parallel, Distributed and Network-Based Computing (PDP). Aya Napa, Cyprus: IEEE Computer Society, 2011. pdf bib

2010

• Christiane P. Ribeiro, Márcio Castro, Jean-François Méhaut, Alexandre Carissimi. Improving Memory Affinity of Geophysics Applications on NUMA Platforms Using Minas. In: International Meeting on High Performance Computing for Computation Science (VECPAR). Vol. 6449. Lecture Notes in Computer Science (LNCS). Berkeley, USA: Springer-Verlag, 2010. pdf bib

2009

• Christiane P. Ribeiro, Jean-François Méhaut, Alexandre Carissimi, Márcio Castro, Luiz Gustavo Fernandes. Memory Affinity for Hierarchical Shared Memory Multiprocessors. In: International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). São Paulo, Brazil: IEEE Computer Society, 2009. pdf bib

• 2nd Best Paper Christiane P. Ribeiro, Márcio Castro, Luiz Gustavo Fernandes, Jean-François Méhaut, Alexandre Carissimi, Fabrice Dupros. High Performance Applications on Hierarchical Shared Memory Multiprocessors. In: Colloque d’Informatique: Brésil / INRIA, Coopérations, Avancées et Défis (COLIBRI). Bento Gonçalves, Brazil: Brazilian Computer Society, 2009. pdf bib

• Márcio Castro, Luiz Gustavo Fernandes, Christiane P. Ribeiro, Jean-François Méhaut, Marilton S. de Aguiar. NUMA-ICTM: A Parallel Version of ICTM Exploiting Memory Placement Strategies for NUMA Machines. In: International Parallel and Distributed Processing Symposium (IPDPS). Rome, Italy: IEEE Computer Society, 2009. pdf bib

2006

• Fabio Giannetti, Luiz Gustavo Fernandes, Rogerio Timmers, Thiago Nunes, Mateus Raeder, Márcio Castro. High Performance XSL-FO Rendering for Variable Data Printing. In: ACM Symposium on Applied Computing (ACM SAC). Dijon, France: ACM, 2006. pdf bib

2005

• Márcio Castro, Lucas Baldo, Luiz Gustavo Fernandes, Mateus Raeder, Pedro Velho. A Parallel Version for the Propagation Algorithm. In: International Conference on Parallel Computing Technologies (PaCT). Vol. 3606. Lecture Notes in Computer Science (LNCS). Krasnoyarsk, Russia: Springer-Verlag, 2005. pdf bib

Thesis and Dissertation

• Márcio Castro. Improving the Performance of Transactional Memory Applications on Multicores: A Machine Learning-based Approach. Ph.D. Thesis at Université de Grenoble Alpes (UGA), 2012. pdf bib

• Márcio Castro. NUMA-ICTM: Uma Versão Paralela do ICTM Explorando Estratégias de Alocação de Memória para Máquinas NUMA. M.Sc. Dissertation at Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS), 2009. pdf bib

• Márcio Castro, Gustavo Serra. Paralelização da Simulação da Trajetória de Elétrons em um Dispositivo FED. Final project presented for the B.Sc. Degree at Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS), 2006.