Sébastien Le Beux

Sébastien Le Beux

Auto-generated profile, based on publicly available information

Sébastien Le Beux

Concordia University, Montreal, Quebec, Canada

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 September 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
ODOceane Destras
Oceane Destras
SBSébastien Le Beux
Sébastien Le Beux
FMFelipe Magalhaes
Felipe Magalhaes
GNGabriela Nicolescu
Gabriela Nicolescu
Integrated photonics arises as a fast and energy-efficient technology for the implementation of artificial neural networks (ANNs). Indeed, with the growing interest in ANNs, photonics shows great promise to overcome current limitations of electronic-based implementation. For example, it has been shown that neural networks integrating optical matrix multiplications can potentially run two orders of magnitude faster than their electronic counterparts. However, the transposition in the optical domain of the activation functions, which is a key feature of ANNs, remains a challenge. There is no direct optical implementation of state-of-the-art activation functions. Currently, most designs require time-consuming and power-hungry electro-optical conversions. In this survey, we review both all-optical and opto-electronic activation functions proposed in the state-of-the-art. We present activation functions with their key characteristics, and we summarize challenges for their use in the context of all-optical neural networks. We then highlight research directions for the implementation of fully optical neural networks.

21 July 2014 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
SBSébastien Le Beux
Sébastien Le Beux
HLHui Li
Hui Li
GNGabriela Nicolescu
Gabriela Nicolescu
JTJelena Trajkovic
Jelena Trajkovic
IOIan O'Connor
Ian O'Connor

5 May 2016 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
HLHui Li
Hui Li
AFAlain Fourmigue
Alain Fourmigue
SBSebastien Le Beux
Sebastien Le Beux
IOIan O'Connor
Ian O'Connor
GNGabriela Nicolescu
Gabriela Nicolescu
Nanophotonic is an emerging technology considered as one of the key solutions for future generation on-chip interconnects. However, silicon photonic devices are highly sensitive to temperature variation. Under a given chip activity, this leads to a lower laser efficiency and a drift of wavelengths of optical devices (on-chip lasers and microring resonators (MRs)), which results in a higher Bit Error Ratio (BER). In this paper, we propose to jointly tune the on-chip lasers and and MRs in order to align the wavelengths of the emitted signals with the resonant wavelengths of the MRs. Our method allows significant improvements of the power consumption with regard to the related methods, while meeting the BER requirement. Compared to methods for which laser tuning is not possible, results show that a combined tuning of laser and MRs leads to 53 percent energy reduction when the uniform chip activity decreases from 20 to 5 percent. BER-energy tradeoffs have been explored and allow strategies to be defined to minimize either the energy, or the BER. As a key result, we have shown that, under specific chip activities, increasing the laser power consumption allows both energy and BER to be improved. This trend has been observed for a MWSR channel interconnecting 12 interfaces.

1 August 2014
Verified
Conference Paper
Closed access
ZMZhong Ming
Zhong Ming
ZWZheng Wang
Zheng Wang
HGHuaxi Gu
Huaxi Gu
SBSebastien Le Beux
Sebastien Le Beux
Microprocessor architectures trend to include more and more cores. To achieve high performance of multicore parallel computing's low-latency and high-throughput, Networks-on-Chip (NoC) are required. Multicast is also a key characteristic to meet the communications performances requirements. However, current multicast algorithm may not have enough ability to ensure communication performance. We propose a new distributed multicast routing algorithm using the shortest path to each destination, meanwhile focusing on minimizing the link usage. By building a tree of fully-used shared path and appending other destinations to the tree, we can obtain the minimal link usage multicast tree. The performance results show that, for an 8×8 mesh topology, at 0.05 injection rates, our scheme reduced 45% of latency than RPM.

22 October 2021 in ACM Journal on Emerging Technologies in Computing Systems
Verified
Journal Article
Open access
HEHassnaa El-Derhalli
Hassnaa El-Derhalli
LCLéa Constans
Léa Constans
SBSébastien Le Beux
Sébastien Le Beux
ARAlfredo De Rossi
Alfredo De Rossi
FRFabrice Raineri
Fabrice Raineri
STSofiène Tahar
Sofiène Tahar
Stochastic computing allows a drastic reduction in hardware complexity using serial processing of bit streams. While the induced high computing latency can be overcome using integrated optics technology, the design of realistic optical stochastic computing architectures calls for energy efficient switching devices. Photonics Crystal (PhC) nanocavities are μm 2 scale devices offering 100fJ switching operation under picoseconds-scale switching speed. Fabrication process allows controlling the Quality factor of each nanocavity resonance, leading to opportunities to implement architectures involving cascaded gates and multi-wavelength signaling. In this paper, we investigate the design of cascaded gates architecture using nanocavities in the context of stochastic computing. We propose a transmission model considering key nanocavity device parameters, such as Quality factors, resonance wavelength, and switching efficiency. The model is calibrated with experimental measurements. We propose the design of XOR gate and multiplexer. We illustrate the use of the gates to design an edge detection filter. System-level exploration of laser power, bit-stream length and bit-error rate is carried out for the processing of gray-scale images. The results show that the proposed architecture leads to 8.5nJ/pixel energy consumption and 512ns/pixel processing time.

14 March 2022
Verified
Conference Paper
Open access
PZParya Zolfaghari
Parya Zolfaghari
JOJoel Ortiz
Joel Ortiz
CKCedric Killian
Cedric Killian
SBSebastien Le Beux
Sebastien Le Beux
Integrated optics is a promising technology to take advantage of light propagation for high throughput chip-scale interconnects in many core architectures. A key challenge for the deployment of nanophotonic interconnects is their high static power, which is induced by signal losses and devices calibration. To tackle this challenge, we propose to use Phase Change Material (PCM) to configure optical paths between writers and readers. The non-volatility of PCM elements and the high contrast between crystalline and amorphous phase states allow to bypass unused readers, thus reducing losses and calibration requirements. We evaluate the efficiency of the proposed PCM-based interconnects using system level simulations carried out with SNIPER manycore simulator. For this purpose, we have modified the simulator to partition clusters according to executed applications. Simulation results show that bypassing readers using PCM leads up to 52% communication power saving.