Monitoring and Debugging of High Performance Distributed Heterogeneous Cloud Applications
Ce projet, intitulé "Automated monitoring and debugging of large scale manycore heterogeneous systems" est divisé en 4 sous-projets.
- Distributed Applications in the Cloud, Edge and 5G network
- Heterogeneous Multi-Core Coprocessors
- Machine Learning and performance analysis Tools
- New Architecture for Tool integration
Automated monitoring and debugging of large scale manycore heterogeneous systems
Ce projet, intitulé "Automated monitoring and debugging of large scale manycore heterogeneous systems" est divisé en 4 sous-projets.
- Data collection through the whole hardware/software stack**
- Architecture for real-time and scalable system-level and cloud-level monitoring and analysis**
- Anomaly Detection and diagnosis with Machine Learning**
- Tracing and debugging support for advanced programming environments**
Software Debugging and Monitoring for Heterogeneous Many-Core Telecom Systems (HSDM)
Ce projet, intitulé "Software Debugging and Monitoring for Heterogeneous Many-Core Telecom Systems" est divisé en 6 sous-projets. Les pistes 1-5 font partie de la subvention de recherche et développement coopérative du CRSNG, tandis que la piste 6 doit être financée par Prompt:
- Tracing, Debugging and Profiling Mechanisms and Architecture on Many-Core Systems
- Cloud Debugging and Monitoring
- Advanced analysis
- Parallel and Incremental Analysis
- Model-Driven Engineering support
- Case Studies
Diagnostics for Real Time Distributed Multi-core Architecture in Avionics
Ce projet comporte quatre domaines de recherche:
- Tracing and Sampling for Real-Time partially simulated Avionics Systems
- Analysis of Real-Time Avionics Systems from Tracing and Sampling data
- Trace abstraction and correlation techniques for real-time avionic systems
- Visualization of Avionic System Traces
Online surveillance of critical computer systems through advanced host-based detection
Ce projet comporte quatre domaines de recherche:
- Scalable Observation infrastructure - Low disturbance multi-level observation and production of enhanced data
- Scalable Observation infrastructure - Advanced host-based Centralized data store and software pattern identification
- Scalable Detection infrastructure - Harmonized Anomaly Detection Techniques
- Scalable Detection infrastructure - Knowledge base for the Linux kernel
Integrated tracing, profiling and debugging for tuning large heterogeneous clusters
Ce projet comporte quatre domaines de recherche:
- Tracing the whole hardware infrastructure, from network processors to application-specific many-core processors
- Coordinating multiple sources of monitoring information in the cluster
- Cluster level modeling and analysis
- Integration of Tracer in Cloud Computing Environment
Tracing and Monitoring Tools for Distributed Multi-Core Systems
Ce projet, d'une durée de trois ans, est financé conjointement par Ericsson, Recherche et développement pour la défense Canada et le Conseil de recherches en sciences naturelles et en génie du Canada. Dirigé à l'École polytechnique par le DORSAL, il est mené en collaboration avec l'Université Concordia, l'Université Laval et l'Université d'Ottawa. Il comporte sept axes de recherche:
- Instrumentation adaptative de fautes ("Adaptative fault probing")
- Synchronisation de traces distribuées multi-niveaux et multi-coeurs ("Multi-level, multi-core distributed traces synchronization")
- Abstraction, analyse et corrélation de traces ("Trace Abstraction, Analysis and Correlation")
- Identification automatique de fautes ("Automated Fault Identification")
- Modélisation de système basée sur les traces d'exécution ("Trace Directed Modeling")
- Surveillance de l'intégrité des systèmes et activation de mesures de réaction ("System Health Monitoring and Reactive measures activation")
- Prédiction de l'impact de l'infrastructure de traçage et de surveillance ("Tracing and Monitoring Framework Impact Prediction")