Fast Virtual Prototyping for Embedded Computing Systems Design and Exploration - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Fast Virtual Prototyping for Embedded Computing Systems Design and Exploration

Résumé

Virtual Prototyping has been widely adopted as a cost-effective solution for early hardware and software co-validation. However, as systems grow in complexity and scale, both the time required to get to a correct virtual prototype, and the time required to run real software on it can quickly become unmanageable. This paper introduces a feature-rich integrated virtual prototyping solution, designed to meet industrial needs not only in terms of performance, but also in terms of ease, rapidity and automation of modelling and exploration. It introduces novel methods to leverage the QEMU dynamic binary translator and the abstraction levels offered by SystemC/TLM 2.0 to provide the best possible trade-offs between accuracy and performance at all steps of the design. The solution also ships with a dynamic platform composition infrastructure that makes it possible to model and explore a myriad of architectures using a compact high-level description. Results obtained simulating a RISC-V SMP architecture running the PARSEC benchmark suite reveal that simulation speed can range from 30 MIPS in accurate simulation mode to 220 MIPS in fast functional validation mode.
Fichier principal
Vignette du fichier
rapido_2019_CEA_COPYRIGHT_DOI.pdf (712.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02023805 , version 1 (18-02-2019)

Identifiants

Citer

Amir Charif, Gabriel Busnot, Rania Mameesh, Tanguy Sassolas, Nicolas Ventroux. Fast Virtual Prototyping for Embedded Computing Systems Design and Exploration. RAPIDO2019 - 11th Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools, Jan 2019, Valence, Spain. pp.1-8, ⟨10.1145/3300189.3300192⟩. ⟨hal-02023805⟩
234 Consultations
1350 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More