Performance Prediction of Application Mapping in Manycore Systems with Artificial Neural Networks

Abdoulaye Gamatié 1 Roman Ursu 1 Manuel Selva 1 Gilles Sassatelli 1
1 SysMIC - Conception et Test de Systèmes MICroélectroniques
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : The growing demand for smarter high-performance embedded systems leads to the integration of multiple functionalities in on-chip systems with tens (even hundreds) of cores. This trend opens a very challenging question about the optimal resource allocation in those manycore systems. Answering this question is key to meet the performance and energy requirements. This paper deals with a learning technique applicable to manycore systems in order to predict mapping-related performances. The resulting prediction models can enable to improve dynamic resource allocation decisions. Our proposal is demonstrated on two automotive application case studies with very promising results.
Complete list of metadatas

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01385641
Contributor : Abdoulaye Gamatié <>
Submitted on : Friday, October 21, 2016 - 5:11:40 PM
Last modification on : Monday, May 13, 2019 - 11:22:29 AM

Identifiers

Collections

Citation

Abdoulaye Gamatié, Roman Ursu, Manuel Selva, Gilles Sassatelli. Performance Prediction of Application Mapping in Manycore Systems with Artificial Neural Networks. MCSoC: Embedded Multicore/Many-core Systems-on-Chip, Sep 2016, Lyon, France. pp.185-192, ⟨10.1109/MCSoC.2016.17⟩. ⟨lirmm-01385641⟩

Share

Metrics

Record views

265