arXiv subjects

Francois Leduc-Primeau

Publications and source records attributed to Francois Leduc-Primeau.

5 recordsLinked to original sources

arXiv2023

Quark: An Integer RISC-V Vector Processor for Sub-Byte Quantized DNN Inference

In this paper, we present Quark, an integer RISC-V vector processor specifically tailored for sub-byte DNN inference. Quark is implemented in GlobalFoundries' 22FDX FD-SOI technology. It is designed on top of Ara, an open-source 64-bit RISC-V vector processor. To accommodate sub-byte DNN inference, Quark extends Ara by adding specialized vector instructions to perform sub-byte quantized operations. We also remove the floating-point unit from Quarks' lanes and use the CVA6 RISC-V scalar core for the re-scaling operations that are required in quantized neural network inference. This makes each lane of Quark 2 times smaller and 1.9 times more power efficient compared to the ones of Ara. In this paper we show that Quark can run quantized models at sub-byte precision. Notably we show that for 1-bit and 2-bit quantized models, Quark can accelerate computation of Conv2d over various ranges of inputs and kernel sizes.

cs.AR↗

arXiv2021

Decentralized Beamforming for Cell-Free Massive MIMO with Unsupervised Learning

Cell-free massive MIMO (CF-mMIMO) systems represent a promising approach to increase the spectral efficiency of wireless communication systems. However, near-optimal beamforming solutions require a large amount of signaling exchange between access points (APs) and the network controller (NC). In this letter, we propose two unsupervised deep neural networks (DNN) architectures, fully and partially distributed, that can perform decentralized coordinated beamforming with zero or limited communication overhead between APs and NC, for both fully digital and hybrid precoding. The proposed DNNs achieve near-optimal sum-rate while also reducing computational complexity by 10-24x compared to conventional near-optimal solutions.

eess.SP↗

arXiv2021

Energy Optimization of Faulty Quantized Min-Sum LDPC Decoders

The objective of this paper is to minimize the energy consumption of a quantized Min-Sum LDPC decoder, by considering aggressive voltage downscaling of the decoder circuit. Since low power supply may introduce faults in the memories used by the decoder architecture, this paper proposes to optimize the energy consumption of the faulty Min-Sum decoder while satisfying a given performance criterion. The proposed optimization method relies on a coordinate descent algorithm that optimizes code and decoder parameters which have a strong influence on the decoder energy consumption: codeword length, number of quantization bits, and failure probability of the memories. Optimal parameter values are provided for several codes defined by their protographs, and significant energy gains are observed compared to non-optimized setups.

cs.IT↗

arXiv2020

Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming

Hybrid beamforming is a promising technique to reduce the complexity and cost of massive multiple-input multiple-output (MIMO) systems while providing high data rate. However, the hybrid precoder design is a challenging task requiring channel state information (CSI) feedback and solving a complex optimization problem. This paper proposes a novel RSSI-based unsupervised deep learning method to design the hybrid beamforming in massive MIMO systems. Furthermore, we propose i) a method to design the synchronization signal (SS) in initial access (IA); and ii) a method to design the codebook for the analog precoder. We also evaluate the system performance through a realistic channel model in various scenarios. We show that the proposed method not only greatly increases the spectral efficiency especially in frequency-division duplex (FDD) communication by using partial CSI feedback, but also has near-optimal sum-rate and outperforms other state-of-the-art full-CSI solutions.

eess.SP↗

arXiv2016

Stall Pattern Avoidance in Polynomial Product Codes

Product codes are a concatenated error-correction scheme that has been often considered for applications requiring very low bit-error rates, which demand that the error floor be decreased as much as possible. In this work, we consider product codes constructed from polynomial algebraic codes, and propose a novel low-complexity post-processing technique that is able to improve the error-correction performance by orders of magnitude. We provide lower bounds for the error rate achievable under post processing, and present simulation results indicating that these bounds are tight.

cs.IT↗