F
Frédéric Pétrot
Researcher at University of Grenoble
Publications - 158
Citations - 1962
Frédéric Pétrot is an academic researcher from University of Grenoble. The author has contributed to research in topics: MPSoC & Software. The author has an hindex of 23, co-authored 153 publications receiving 1802 citations. Previous affiliations of Frédéric Pétrot include Pierre-and-Marie-Curie University & Grenoble Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Ternary neural networks for resource-efficient AI applications
TL;DR: In this paper, the authors proposed ternary neural networks (TNNs) to make deep learning more resource-efficient by using a teacher-student approach based on a novel, layer-wise greedy methodology.
Journal ArticleDOI
Elevator-First: A Deadlock-Free Distributed Routing Algorithm for Vertically Partially Connected 3D-NoCs
TL;DR: It is formally proved that independently of the shape and dimensions of the planar topologies and of the number and placement of the TSVs, the proposed routing algorithm using two virtual channels in the plane is deadlock and livelock free.
Proceedings ArticleDOI
COSY communication IP's
J.-Y. Brunel,Wido Kruijtzer,H. J. H. N. Kenter,Frédéric Pétrot,L. Pasquier,E. A. de Kock,W. J. M. Smits +6 more
TL;DR: The Fsprit/OMI-COSY project defines transaction-levels to set-up the exchange of IP's in separating function from architecture and body-behavior from proprietary interfaces, which are supported by the COSY Communications IPs presented in this paper.
Proceedings ArticleDOI
Programming models and HW-SW interfaces abstraction for multi-processor SoC
TL;DR: This paper deals with parallel programming models to abstract both hardware and software interfaces in the case of heterogeneous MPSoC design.
Proceedings ArticleDOI
Using binary translation in event driven simulation for fast and flexible MPSoC simulation
TL;DR: This paper investigates the use of instruction set simulators (ISS) based on binary translation to accelerate full timed multiprocessor system simulation at transaction level and proposes a range of solutions trading off simulation speed versus accuracy.