A5070877994- Real-Time Systems Scheduling
- Parallel Computing and Optimization Techniques
- Radiation Effects in Electronics
- Real-time simulation and control systems
- Distributed and Parallel Computing Systems
- Software Reliability and Analysis Research
- Distributed systems and fault tolerance
- Simulation Techniques and Applications
- Model-Driven Software Engineering Techniques
- Physical Unclonable Functions (PUFs) and Hardware Security
- Information and Cyber Security
- Formal Methods in Verification
- Technology Assessment and Management
- Cloud Computing and Resource Management
- Digital Transformation in Industry
- VLSI and Analog Circuit Testing
- Software System Performance and Reliability
- Scientific Computing and Data Management
- Scientific Research and Discoveries
- Robotics and Automated Systems
- Software Testing and Debugging Techniques
- Manufacturing Process and Optimization
- Spacecraft Design and Technology
- Smart Grid Security and Resilience
- Stochastic Gradient Optimization Techniques
Ikerlan
2019-2024
Boeing (Spain)
2023
Digital Research Alliance of Canada
2023
GAIKER Technology Centre
2022
Universitat Politècnica de Catalunya
2020-2022
Critical real-time systems require strict resource provisioning in terms of memory and timing. The constant need for higher performance these has led industry to recently include GPUs. However, GPU software ecosystems are by their nature closed source, forcing system engineers consider them as black boxes, complicating provisioning. In this work we reverse engineer the internal operations increase understanding observed behaviour how resources internally managed. This way, allow accurately...
Critical real-time systems require strict resource provisioning in terms of memory and timing. The constant need for higher performance these has led industry to recently include GPUs. However, GPU software ecosystems are by their nature closed source, forcing system engineers consider them as black boxes, complicating provisioning. In this work, we reverse engineer the internal operations increase understanding observed behaviour how resources internally managed. We present our methodology...
Deep learning technology has enabled the development of increasingly complex safety-related autonomous systems using high-performance computers, such as graphics processing units (GPUs), which provide required high computing performance for execution parallel algorithms, matrix–matrix multiplications (a central element deep software libraries). However, safety certification algorithms and GPU-based is a challenge to be addressed. For example, achieving fault-tolerance diagnostic coverage...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Cyber–physical systems (CPS) integrate diverse elements developed by various vendors, often dispersed geographically, posing significant development challenges. This paper presents an improved version of our previously co-simulation interface based on the non-proprietary Distributed Co-Simulation Protocol (DCP) standard, now optimized for broader hardware platform compatibility. The core contributions include a demonstration interface’s hardware-agnostic capabilities and its straightforward...
Cyber-physical systems are composed of a variety elements developed by different vendors that often geographically distributed. Therefore, its development process presents double challenge: each element has to be individually and, at the same time, correct interaction with rest ensured. In previous work, we proposed and an interface, based on non-proprietary Distributed Co-simulation Protocol standard, ease between these elements. this paper, improve it applicable in hardware platforms test...
Over-the-air Software Updates (OTASU) in the critical domain are already a reality. OTASU provide huge benefits terms of user experience, security, and efficiency. However, due to involved risks, safety security mechanisms new regulations needed for their adoption domain. The automotive industry is race adopt safe secure OTASU, as by 2024, compliance UN will become compulsory. standards providing specifications requirements still infancy. Many other dependable system domains, that now more...
Autonomous systems require high-performance processing capabilities, which demand the use of powerful accelerators such as GPUs. However, GPUs in critical presents several challenges, since GPU programming models rely on explicit dynamic memory management. Traditionally, allocation is restricted to certain controlled scenarios, programs be rewritten so that all required allocated at beginning program and released its end. many applications do not follow this approach. Moreover, when used, it...
The UP2DATE H2020 project focuses on highperformance heterogeneous embedded platforms for critical systems. We will develop observability and controllability solutions to support online updates while ensuring safety security mixed-criticality tasks. In this paper, we describe the rationale behind selection of baseline research which be used demonstrate concepts, including a performance comparison identify most efficient one.
In the domain of safety-critical systems there is an increasing need for more compute-capable and higher performance devices. This comes from dramatic increase on software complexity caused by newest intelligent autonomous systems. Graphics Processing Units (GPUs), as multi-processing accelerators, are ideal choice in this aspect due to their ability handle big amount data computations. order ease challenging task programming such devices, vendors continuously adding features, Unified Memory...