Publications associées à Multiplication

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

David Atienza Alonso, Giovanni Ansaloni, Alireza Amirshahi

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

2024

EdgeAI-Aware Design of In-Memory Computing Architectures

Marco Antonio Rios

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

EPFL2024

Computational Imaging SPAD Cameras

Andrei Ardelean

Vision systems built around conventional image sensors have to read, encode and transmit large quantities of pixel information, a majority of which is redundant. As a result, new computational imaging sensor architectures were developed to preprocess the r ...

EPFL2023

A 16-bit Floating-Point Near-SRAM Architecture for Low-power Sparse Matrix-Vector Multiplication

David Atienza Alonso, Giovanni Ansaloni, Grégoire Axel Eggermann, Marco Antonio Rios

State-of-the-art Artificial Intelligence (AI) algorithms, such as graph neural networks and recommendation systems, require floating-point computation of very large matrix multiplications over sparse data. Their execution in resource-constrained scenarios, ...

New York2023

Fabrication and Characterization of High Aspect Ratio Amorphous Silicon Based Microchannel Plates

Christophe Ballif, Nicolas Würsch, Janina Christine Isabelle Löffler, Samira Alexandra Frey, Mohammad Beygi

This contribution focuses on the fabrication and characterization of microchannel plates made of hydrogenated amorphous silicon (AMCPs). Flexible fabrication processes and the semi-conducting nature of amorphous silicon could give these detectors the advan ...

2021

Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)

Rachid Guerraoui, Sadegh Farhadkhani, El Mahdi El Mhamdi, Le Nguyen Hoang, Sébastien Louis Alexandre Rouault, Arsany Hany Abdelmessih Guirguis

We study Byzantine collaborative learning, where n nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another. No node is trusted, and f < n nodes can behave arbitrarily. We prove that collaborati ...

2021

Characterization of Amorphous Silicon Based Microchannel Plates with High Aspect Ratio

Christophe Ballif, Nicolas Würsch, Janina Christine Isabelle Löffler, Samira Alexandra Frey

Microchannel plates (MCPs) fabricated out of hydrogenated amorphous silicon offer a promising alternative to conventional lead glass ones. Progress in the fabrication process has allowed for detectors with higher aspect ratios, which significantly increase ...

IEEE2019

Reducing the Multiplicative Complexity in Logic Networks for Cryptography and Security Applications

Giovanni De Micheli, Mathias Soeken, Luca Gaetano Amarù, Eleonora Testa

Reducing the number of AND gates plays a central role in many cryptography and security applications. We propose a logic synthesis algorithm and tool to minimize the number of AND gates in a logic network composed of AND, XOR, and inverter gates. Our appro ...

ASSOC COMPUTING MACHINERY2019

The Role of Multiplicative Complexity in Compiling Low T-count Oracle Circuits

Giovanni De Micheli, Mathias Soeken, Giulia Meuli

We present a constructive method to create quantum circuits that implement oracles vertical bar x vertical bar y |0 (k) -> vertical bar x vertical bar y circle plus f(x)vertical bar 0 (k) for n-variable Boolean functions f with low T-count. In our method f ...

IEEE2019

Sur quelques équations aux dérivées partielles en lien avec le lemme de Poincaré

David Valentin Strütt

In this thesis, we study two distinct problems. The first problem consists of studying the linear system of partial differential equations which consists of taking a k-form, and applying the exterior derivative 'd' to it and add the wedge product with a 1- ...

EPFL2018

A Householder-Based Algorithm For Hessenberg-Triangular Reduction

Daniel Kressner, Zvonimir Bujanovic

The QZ algorithm for computing eigenvalues and eigenvectors of a matrix pencil A - lambda B requires that the matrices first be reduced to Hessenberg-triangular (HT) form. The current method of choice for HT reduction relies entirely on Givens rotations re ...

SIAM PUBLICATIONS2018

Arithmetic and geometric structures in cryptography

Benjamin Pierre Charles Wesolowski

We explore a few algebraic and geometric structures, through certain questions posed by modern cryptography. We focus on the cases of discrete logarithms in finite fields of small characteristic, the structure of isogeny graphs of ordinary abelian varietie ...

EPFL2018

On finitely generated modules over quasi-Euclidean rings

Luc Guyot

Let R be a unital commutative ring, and let M be an R-module that is generated by k elements but not less. Let be the subgroup of generated by the elementary matrices. In this paper we study the action of by matrix multiplication on the set of unimodular r ...

Springer Verlag2017

Generalized Virasoro algebra: left-symmetry and related algebraic and hydrodynamic properties

Tudor Ratiu

Motivated by the work of Kupershmidt (J. Nonlin. Math. Phys. 6 (1998), 222 -245) we discuss the occurrence of left symmetry in a generalized Virasoro algebra. The multiplication rule is defined, which is necessary and sufficient for this algebra to be quas ...

Taylor & Francis Ltd2016

Computational Aspects of Jacobians of Hyperelliptic Curves

Alina Dudeanu

Nowadays, one area of research in cryptanalysis is solving the Discrete Logarithm Problem (DLP) in finite groups whose group representation is not yet exploited. For such groups, the best one can do is using a generic method to attack the DLP, the fastest ...

EPFL2016

Neuromorphic Computing Using Non-Volatile Memory

Yusuf Leblebici, Irem Boybat Kara, Alessandro Fumarola, Seyoung Kim, Abu Sebastian, Severin Sidler

Dense crossbar arrays of non-volatile memory (NVM) devices represent one possible path for implementing massively-parallel and highly energy-efficient neuromorphic computing systems. We first review recent advances in the application of NVM devices to thre ...

2016

On the Continuous Steering of the Scale of Tight Wavelet Frames

Michaël Unser, Daniel Sage, Zsuzsanna Püspöki, John Paul Ward

In analogy with steerable wavelets, we present a general construction of adaptable tight wavelet frames, with an emphasis on scaling operations. In particular, the derived wavelets can be "dilated" by a procedure comparable to the operation of steering ste ...

SIAM2016

Faster ECC over $\mathbb{F}_{2^{521}-1}$

Robert Granger

In this paper we present a new multiplication algorithm for residues modulo the Mersenne prime

2^{521}−1

. Using this approach, on an Intel Haswell Core i7-4770, constant-time variable-base scalar multiplication on NIST’s (and SECG’s) curve P-521 requires ...

Springer Berlin Heidelberg2015

Sampling-Based Nuclear Data Uncertainty Quantification for Continuous Energy Monte Carlo Codes

Ting Zhu

The goal of the present PhD research is to establish a methodology of nuclear data uncertainty quantification (NDUQ) for MCNPX, the continuous-energy Monte-Carlo (M-C) code. The high fidelity (continuous-energy treatment and flexible geometry modelling) of ...

EPFL2015

Liftings of reduction maps for quaternion algebras

Dimitar Petkov Jetchev

We construct liftings of reduction maps from complex multiplication (CM) points to supersingular points for general quaternion algebras and use these liftings to establish a precise correspondence between CM points on indefinite quaternion algebras with a ...

Oxford University Press2013