Abstract
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 and security for mixed-criticality tasks. In this paper, we describe the rationale behind the selection of the baseline research platforms which will be used to develop and demonstrate the project concepts, including a performance comparison to identify the most efficient one.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1340-1343 |
| Number of pages | 4 |
| ISBN (Electronic) | 9783981926354 |
| DOIs | |
| State | Published - Feb 1 2021 |
| Externally published | Yes |
| Event | 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021 - Virtual, Online Duration: Feb 1 2021 → Feb 5 2021 |
Publication series
| Name | Proceedings -Design, Automation and Test in Europe, DATE |
|---|---|
| Volume | 2021-February |
| ISSN (Print) | 1530-1591 |
Conference
| Conference | 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021 |
|---|---|
| City | Virtual, Online |
| Period | 02/1/21 → 02/5/21 |
Funding
Real-time Performance: We have also performed latency tests on the high performance (non real-time) CPUs of the candidate platforms. We observed similar results for all platforms around 50μs, which is acceptable for real-time systems. VI. PLATFORM SELECTION AND CONCLUSION Based on our evaluation, the NVIDIA Xavier is the most powerful platform that we benchmarked. It is more power efficient than the TX2, and given that it supports a higher power mode (30W), more cores (8) and larger memory (32GB), it is safe to assume that it can deliver much higher overall performance, to support a larger number and more complex applications to experiment with our software update, monitoring and controllability solutions. Therefore, this will be the prioritised research platform, followed by the Xilinx Ultrascale+ as a best effort candidate. ACKNOWLEDGMENTS This work is funded by the European Commission’s Horizon 2020 programme under the UP2DATE project (grant agreement 871465). It is also partially supported by the Spanish Ministry of Economy and Competitiveness under grants PID2019-107255GB and FJCI-2017-34095 and HiPEAC. REFERENCES [1] I. Agirre et al., “UP2DATE: Safe and Secure Over-the-air Software Updates on High-performance Mixed-criticality Systems,” in DSD, 2020. [2] R. Mancuso et al., “WCET(m) Estimation in Multi-core Systems Using Single Core Equivalence,” in ECRTS, 2015, pp. 174–183. [3] E. Díaz et al., “MC2: Multicore and Cache Analysis via Deterministic and Probabilistic Jitter Bounding,” in Ada-Europe, 2017. [4] E. Díaz et al., “Modelling Multicore Contention on the AURIX™ TC27x,” in Design Automation Conference (DAC), 2018, pp. 1–6. [5] M. Fernández et al., “Assessing the suitability of the ngmp multi-core processor in the space domain,” in EMSOFT, 2012. [6] I. Rodriguez et al., “GPU4S Bench: Design and Implementation of an Open GPU Benchmarking Suite for Space On-board Processing,” Universitat Politecnica de Catalunya, Tech. Rep. UPC-DAC-RR-CAP-2019-1, https://www.ac.upc.edu/app/research-reports/public/html/ research center index-CAP-2019,en.html. [7] L. Kosmidis et al., “GPU4S: Major Project Outcomes, Lessons Learnt and Way Forward,” in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2021.