DARTS.8.1.6.pdf
- Filesize: 389 kB
- 2 pages
Document
ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems (Artifact)
Authors
Iryna De Albuquerque Silva 
,
Thomas Carle ,
Claire Pagetti
-
Part of:
Issue:
Special Issue of the 34th Euromicro Conference on Real-Time Systems (ECRTS 2022)
Volume: DARTS, Volume 8 (ECOOP 2022)
Conference: Euromicro Conference on Real-Time Systems (ECRTS)
Journal: Dagstuhl Artifacts Series (DARTS) - License:
Creative Commons Attribution 4.0 International license
- Publication Date: 2022-06-28
Artifact Description
Document Identifiers
Author Details
Cite AsGet BibTex
Iryna De Albuquerque Silva, Thomas Carle, Adrien Gauffriau, and Claire Pagetti. ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems (Artifact). In Special Issue of the 34th Euromicro Conference on Real-Time Systems (ECRTS 2022). Dagstuhl Artifacts Series (DARTS), Volume 8, Issue 1, pp. 6:1-6:2, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
https://doi.org/10.4230/DARTS.8.1.6
https://doi.org/10.4230/DARTS.8.1.6
Artifact
DARTS-8-1-6-artifact-41ab74c69d68149a2c966faa52ac59bf.zip
(Filesize: 1.29 GB)
Abstract
Machine learning applications have been gaining considerable attention in the field of safety-critical systems. Nonetheless, there is up to now no accepted development process that reaches classical safety confidence levels. This is the reason why we have developed a generic programming framework called ACETONE that is compliant with safety objectives (including traceability and WCET computation) for machine learning. More practically, the framework generates C code from a detailed description of off-line trained feed-forward deep neural networks that preserves the semantics of the original trained model and for which the WCET can be assessed with OTAWA. We have compared our results with Keras2c and uTVM with static runtime on a realistic set of benchmarks.
Subject Classification
ACM Subject Classification
- Computer systems organization → Real-time systems
- Software and its engineering → Software notations and tools
Keywords
- Real-time safety-critical systems
- Worst Case Execution Time analysis
- Artificial Neural Networks implementation
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads