Introducing Dynamic Adaptation in High Performance Real-Time Computing Platforms for Sensors

Abstract : In high-end, data-intensive embedded sensor applications (radar, optronics), the evolution of algorithms is limited by the computation platform capabilities. These platforms impose Size, Weight and Power (SWaP) restrictions on top of reliability, cost, security and (potentially hard) real-time constraints. Thus mostly static mapping methods are used, negating the system's adaptation capabilities. Through the study of several industrial use-cases, our work aims at mitigating the aforementioned limitations by introducing a low-latency dynamic resource management system derived from techniques used in large-scale systems such as cloud and grid environments. We expect that this approach will be able to guarantee non-functional properties of applications and provide Quality of Service (QoS) negotiation on heterogeneous platforms.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01624262
Contributor : Baptiste Goupille--Lescar <>
Submitted on : Thursday, October 26, 2017 - 10:27:59 AM
Last modification on : Friday, September 13, 2019 - 9:51:33 AM
Long-term archiving on : Saturday, January 27, 2018 - 12:52:18 PM

File

ANDARE-2017_GoupilleLescar.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01624262, version 1

Citation

Baptiste Goupille-Lescar, Eric Lenormand, Christine Morin, Nikos Parlavantzas. Introducing Dynamic Adaptation in High Performance Real-Time Computing Platforms for Sensors. ANDARE 2017 - 1st Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems, Sep 2017, Portland, OR, United States. ⟨hal-01624262⟩

Share

Metrics

Record views

690

Files downloads

153