Entrée-sortie

Résumé

Dans un système à base de processeur, de microprocesseur, de microcontrôleur ou d'automate, on appelle entrée-sortie toute interface permettant d’échanger des données entre le processeur et les périphériques qui lui sont associés. De la sorte, le système peut réagir à des modifications de son environnement, voire le contrôler. Elles sont parfois désignées par l'acronyme I/O, issu de l'anglais Input/Output ou encore E/S pour entrée/sortie. Dans un système d'exploitation :

les entrées sont les données envoyées par un périphérique (disque, réseau, clavier, capteur…) à destination d'une unité centrale de traitement (processeur) ;
les sorties sont les données émises par une unité centrale de traitement à destination d'un périphérique (disque, réseau, écran, imprimante, actionneur…).

Exemple simplifié :

taper sur les touches du clavier envoie une série de codes vers le processeur ; ces codes sont considérés comme des données d'entrée ;
le processeur affiche les résultats du trait

Source officielle

https://fr.wikipedia.org/wiki/Entr%C3%A9e-sortie

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (100)

Publications associées

Chargement

Personnes associées (16)

Personnes associées

Chargement

Unités associées (17)

Unités associées

Chargement

Concepts associés (73)

En informatique, un système d'exploitation (souvent appelé OS — de l'anglais operating system — ou parfois SE — en français) est un ensemble de programmes qui dirige l'utilisation des ressources d'u

Un ordinateur est un système de traitement de l'information programmable tel que défini par Alan Turing et qui fonctionne par la lecture séquentielle d'un ensemble d'instructions, organisées en progr

A central processing unit (CPU)—also called a central processor or main processor—is the most important processor in a given computer. Its electronic circuitry executes instructions of a computer pr

Afficher plus

Concepts associés

Chargement

Cours associés (83)

Cours associés

Chargement

Séances de cours associées (231)

Afficher plus

Séances de cours associées

Chargement

At the LENI a heat pump model has been developed, which aims to simulate a single state compression heat pump in both steady state and transient regime. For gaining the experimental data and for the simulation the same set of input data is used. The goal is to approximate the output values of the model ym to the ones measured in the experiments. Therefore a certain number of parameters need to be defined in order of obtaining the highest accuracy possible. At the beginning these different parameters γ need to be found and a criterion needs to be appointed which can be used to judge the accuracy of the model. The first approach to the identification is to only work with the steady states. This includes to select steady values out of a data sheet and to change the model so that only steady states are computed. As soon as the model is successfully running for the steady states an optimizer needs to be chosen to finally output the best values of parameters. Subsequently the improvement of the output vector ym needs to be checked. As during the examination some computational problems have been revealed, which interfered with the optimization, various influences on the heat pump model were investigated. It was tried to find the reason for numerical problems and to eliminate those in order to finally be able to optimise the parameters. To identify the model in the transient regime the model needs to be linearised at a typical operation condition. The new chosen criterion must also take into account the transient regimes and the optimality of the solution has to be proved. The numerical problems which exist for the steady state also influence the transient regime. As the emphasis was therefore put on finding the origin of the instabilities, the identification of the transient regime was only briefly worked on.

2010

Chargement

F-BLEAU: Fast Black-box Leakage Estimation

Giovanni Cherubin

We consider the problem of measuring how much a system reveals about its secret inputs. We work in the black-box setting: we assume no prior knowledge of the system's internals, and we run the system for choices of secrets and measure its leakage from the respective outputs. Our goal is to estimate the Bayes risk, from which one can derive some of the most popular leakage measures (e.g., min-entropy leakage). The state-of-the-art method for estimating these leakage measures is the frequentist paradigm, which approximates the system's internals by looking at the frequencies of its inputs and outputs. Unfortunately, this does not scale for systems with large output spaces, where it would require too many input-output examples. Consequently, it also cannot be applied to systems with continuous outputs (e.g., time side channels, network traffic). In this paper, we exploit an analogy between Machine Learning (ML) and black-box leakage estimation to show that the Bayes risk of a system can be estimated by using a class of ML methods: the universally consistent learning rules; these rules can exploit patterns in the input-output examples to improve the estimates' convergence, while retaining formal optimality guarantees. We focus on a set of them, the nearest neighbor rules; we show that they significantly reduce the number of black-box queries required for a precise estimation whenever nearby outputs tend to be produced by the same secret; furthermore, some of them can tackle systems with continuous outputs. We illustrate the applicability of these techniques on both synthetic and real-world data, and we compare them with the state-of-the-art tool, leakiEst, which is based on the frequentist approach.

IEEE2019

Chargement

LaMBERT: Light and Multigranular BERT

Ljupche Milosheski

Pre-training complex language models is essential for the success of the recent methods such as BERT or OpenAI GPT. Their size makes not only the pre-training phase, but also consecutive applications to be computationally expensive. BERT-like models excel at token-level tasks as they provide reliable token embeddings, but they fall short when it comes to sentence or higher-level structure embeddings. The reason is that these models do not have a built-in mechanism that explicitly provides such representations. We introduce Light and Multigranural BERT that has similar complexity to BERT in the number of parameters, but is about 3 times faster by modifying the input representation, which consequently introduces changes to the attention mechanism and at the same time produces reliable segment embeddings as it is one of our training objectives. The model we publish achieves 70.7% on the MNLI task, which is promising bearing in mind there were two major issues with it.

2020

Chargement