SAFEXPLAIN will play a key role in the 2025 HiPEAC conference, an annual conference providing a high-quality forum for computer architects and compiler builders working in the field of high-performance computer architecture and compilation for embedded systems.
This year, SAFEXPLAIN results will be presented as part of two workshops during the second day of the conference: the Women@HPC MAR WHPC chapter: Building the diversity continuum in cutting-edge technologies workshop and the MCS: Mixed Critical Systems – Safe Intelligent CPS and the development cycle workshop.
This WS centers on building a robust community that highlights the contributions of diverse groups in developing cutting-edge technologies, including high-performance computing (HPC), artificial intelligence (AI), and critical real-time embedded systems (CRTES). As part of this goal the WS is bringing together female experts in HPC, AI, and real-time systems to discuss their latest advancements in various cutting-edge technologies. This workshop seeks to foster an inclusive environment where the achievements of diverse communities are recognized, and where collaborative efforts can thrive to advance the frontiers of technology.
Irune Yarza from IKERLAN will discuss how AI has the potential to revolutionize the development of next-generation autonomous safety-critical systems as part of her presentation on “Ensuring Functional Safety in AI-based critical systems: A railway case study”. She will discuss the challenges posed by integrating cutting-edge AI technologies with established safety engineering processes and standards and will highlight the contributions of SAFEXPLAIN for addressing this issue. She will discuss ongoing work on the proposed architectural solution which is specifically tailored to a railway case study.
Women@HPC MAR WHPC chapter: Building the diversity continuum in cutting-edge technologies
10h-13:00, Extra2
MCS: Mixed Critical Systems – Safe Intelligent CPS and the development cycle
10h-17:30, Room 7
The WS will delve into different approaches to a continuous development process for functionality, real-time high-performance platforms that ensure safety and security during execution, and a development life cycle that incorporates safety and security measures in accordance with forthcoming standards. SAFEXPLAIN will address the development of AI that is not only safe but also explainable, making decision its decision-making processes transparent and comprehensible.
Robert Lowe from the Research Institutes of Swededn (RISE) will present the SAFEXPLAIN project and its role in addressing uncertainty in software development/deployment when integrating AI within safety critical autonomous systems. His presentation will take place as part of the second session entitled Safe Artificial Intelligent Dependable Autonomous Systems, chaired by Irune Agirre.
Carlo Donzella and Stefano Lodico from exida development will share insights into “SOTIF-compliant V&V (Verification & Validation) and STPA (Systems Theoretic Process Analysis) for critical systems with AI-based components” as part of the third session on Safe Artificial Intelligent Dependable Autonomous Systems II, chaired by Kim Grüttner.
Will you attend HiPEAC 2025?
Stop by booth 27 where SAFEXPLAIN coordinator, the Barcelona Supercomputing Center, will be hosting a booth.
