Journals [ACL]

  • Y. Djebrouni, N. Benarba, O. Touat, P. De Rosa, S. Bouchenak, A. Bonifati, P. Felber, V. Marangozova, and V. Schiavoni. 2024. Bias Mitigation in Federated Learning for Edge Computing. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 7, 4, Article 157 (December 2023), 35 pages. (Rang A*)

  • V.Marangozova-Martin, A. El-Rheddane, N. De Palma. Multi-Level Elasticity for Data Stream Processing. IEEE TPDS, vol. 30, no. 10, pp. 2326-2337, 1 Oct. 2019 (Rang A*).

  • Martin A, Marangozova-Martin V. Automatic benchmark profiling through advanced workflow-based trace analysis. Softw Pract Exper. 2018 ;1–23 (Rang A)

  • C. Pousa Ribeiro, M. Castro, V. Marangozova-Martin, J.-F. Mehaut, H. Cota de Freitas, and C. Augusto Paiva da Silva Martins. Evaluating CPU and Memory Affinity for Numerical Scientific Multithreaded Benchmarks on Multi-cores. IADIS International Journal on Computer Science and Information Systems(IJCSIS), 7(1) :79–93, 2012.

  • Conferences [ACT]

  • Y.Djebrouni, I.Rocha, S. Bouchenak, L. Chen, P. Felber, V. Marangozova, V. Schiavoni. Characterizing Distributed Machine Learning Workloads on Apache Spark. In Proceedings of the 24th International Middleware Conference (Middleware '23). ACM, New York, NY, USA, 151–164. (Rang A).

  • Alexis Martin, Vania Marangozova-Martin. Automatic Benchmark Profiling Through Advanced Trace Analysis. Euro-Par 2016 : 63-74 (Rang A)

  • K.Georgiev and V. Marangozova-Martin. MPSoC Zoom Debugging : A Deterministic Record-Partial Replay Approach. 12th IEEE International Conference on Embedded and Ubiquitous Computing (EUC’2014). (Acceptation 30%)

  • D. Dosimont, G. Pagano, G.Huard, V. Marangozova-Martin and J-M. Vincent. Efficient Analysis Methodology for Huge Application Traces. International Conference on High Performance Computing and Simulation (HPCS). July, 2014. Bologna, Italy. Campagne

  • L. Stanisic, B. Videau, J. Cronsioe, A. Degomme, V. Marangozova-Martin, A. Legrand, and J.-F. Mehaut. Performance Analysis of HPC Applications on Low-Power Embedded Platforms. In Proceedings of the Conference on Design, Automation, Test in Europe (DA- TE’13), Grenoble, Mar. 2013. Special Day on High-Performance Low-Power Computing.

  • G. Pagano, D. Dosimont, G. Huard, V. Marangozova-Martin, and J.-M. Vincent. Trace Management and Analysis for Embedded Systems. IEEE International Symposium on Embedded Multicore SoCs (MCSoC-13), Tokyo, Japan, Dec. 2013. (Acceptation 30%)

  • B. Videau, V. Marangozova-Martin, and J. Cronsioe. BOAST : Bringing Optimization through Automatic Source-to-Source Transformations. 7th International Symposium on Embedded Multicore/Manycore System-on-Chip (MCSoC), 2013 (Acceptation 30%)

  • B. Videau, V. Marangozova-Martin, L. Genovese, and T. Deutsch. Optimizing 3D Convo- lutions for Wavelet Transforms on CPUs with SSE Units and GPUs. 19th Euro-Par International Conference, 2013. (Rank A)

  • K. Pouget, M. Santana, V. Marangozova-Martin, and J.-F. Mehaut. Debugging Component-Based Embedded Applications. SCOPES (Software and Compilers for Embed- ded Systems) Workshop, 2012. (Rank A)

  • M. Bastos Castro, K. Georgiev, V. Marangozova-Martin, J.-F. Mehaut, L. Gustavo Fernandes, and M. Santana. Analysis and Tracing of Applications Based on Software Transactional Memory on Multicore Architectures. Euromicro International Conference on Parallel, Distributed and Network-Based Computing (PDP), 2011.

  • P. Oliveira, H. Cota de Freitas, C. Pousa Ribeiro, M. Bastos Castro, V. Marangozova- Martin, and J.-F. Mehaut. Performance Evaluation of WiNoCs for Parallel Workloads Based on Collective Communications. IADIS International Conference on Applied Computing (AC), Rio de Janeiro, Brazil, 2011.

  • C. Pousa Ribeiro, M. Bastos Castro, J.-F. Mehaut, V. Marangozova-Martin, H. Cota de Freitas, and C. A. P. S. Martins. Investigating the Impact of CPU and Memory Affinity on Multi-core Platforms : A Case Study of Numerical Scientific Multithreaded Applications. IADIS International Conference on Applied Computing (AC), Rio de Janeiro, Brazil, 2011.

  • C. Prada, V. Marangozova-Martin, J.-F. Mehaut, and M. Santana. A Generic Component- Based Approach to MPSoC Observation. 9th IEEE/IFIP International Conference on Embedded and UbiquitousComputing (EUC 2011), 2011.

  • Short communications [COM] and posters [AFF] in conferences and workshops

  • G. Pagano and V. Marangozova-Martin. The FrameSoC Software Architecture for Multiple- View Trace Data Analysis. ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS 2014). Rome, Italie. Juin 2014

  • G. Pagano, D. Dosimont, G. Huard, V. Marangozova-Martin, and J.-M. Vincent. Trace Management and Analysis for Embedded Systems. IEEE International Symposium on Embedded Multicore SoCs (MCSoC-13), Tokyo, Japan, Dec. 2013.

  • V. Marangozova-Martin and G. Pagano. SoC-TRACE : Handling the Challenge of Em- bedded Software Design and Optimization. ACM/IFIP/Usenix International Middleware Conference, Montreal, Canada, Dec. 2012. (Rank A)

  • Habilitation to Direct Research

  • Vania Marangozova-Martin. Towards Generic System Observation Management. 2015.

  • Rapports

  • K. Georgiev and V. Marangozova-Martin. Deterministic Partial Replay for MPSoC Debug- ging. Rapport de recherche RR-8515, INRIA Grenoble, France, 2014.

  • G.Pagano and V. Marangozova-Martin. FrameSoC Workbench : Facilitating Trace Analysis through a Consistent User Interface. Rapport technique RT-447, INRIA, Avril 2014.

  • Communications

  • Johanna Sepúlveda, Vania Marangozova-Martin, Jerónimo Castrillón. Architecture, Lan- guages, Compilation and Hardware support for Emerging ManYcore systems (ALCHEMY) : Preface. ICCS 2017 : 1071-1072

  • A. Martin, G. Pagano, V. Marangozova-Martin and J. Correnoz. Analyse de systèmes embarqués par structuration de traces d’exécution. Conférence en parallélisme, architecture et systèmes (ComPAS), Neuchâtel, Suisse. Avril 2014

  • Software & Data

    SWAT : Système de Workflow pour l’Analyse de Traces.

  • Logiciel libre issu du travail de thèse d’Alexis Martin.

  • Framesoc : une infrastructure de gestion de traces.
    Logiciel libre basé sur le framework Eclispe produit dans le cadre du projet SoC-TRACE.

  • Traces d’exécution LTTng de 10 benchmarks Phoronix
    Mise à disposition en accès libre d’environ 500 Giga-octets de traces, issues de différentes configurations d’exécution de 10 benchmarks standards sur deux plates-formes (une machine de bureau classique et une plate-forme embarquée).