Vision processing unitA vision processing unit (VPU) is (as of 2023) an emerging class of microprocessor; it is a specific type of AI accelerator, designed to accelerate machine vision tasks. Vision processing units are distinct from video processing units (which are specialised for video encoding and decoding) in their suitability for running machine vision algorithms such as CNN (convolutional neural networks), SIFT (scale-invariant feature transform) and similar.
Electronic system-level design and verificationElectronic system level (ESL) design and verification is an electronic design methodology, focused on higher abstraction level concerns. The term Electronic System Level or ESL Design was first defined by Gartner Dataquest, an EDA-industry-analysis firm, on February 1, 2001. It is defined in ESL Design and Verification as: "the utilization of appropriate abstractions in order to increase comprehension about a system, and to enhance the probability of a successful implementation of functionality in a cost-effective manner.
Programmable Array LogicProgrammable Array Logic (PAL) is a family of programmable logic device semiconductors used to implement logic functions in digital circuits introduced by Monolithic Memories, Inc. (MMI) in March 1978. MMI obtained a registered trademark on the term PAL for use in "Programmable Semiconductor Logic Circuits". The trademark is currently held by Lattice Semiconductor. PAL devices consisted of a small PROM (programmable read-only memory) core and additional output logic used to implement particular desired logic functions with few components.
Gate arrayA gate array is an approach to the design and manufacture of application-specific integrated circuits (ASICs) using a prefabricated chip with components that are later interconnected into logic devices (e.g. NAND gates, flip-flops, etc.) according to custom order by adding metal interconnect layers in the factory. It was popular during the upheaval in the semiconductor industry in the 1980s, and its usage declined by the end of the 1990s.
Vérification formelleIn the context of hardware and software systems, formal verification is the act of proving or disproving the correctness of intended algorithms underlying a system with respect to a certain formal specification or property, using formal methods of mathematics. Formal verification can be helpful in proving the correctness of systems such as: cryptographic protocols, combinational circuits, digital circuits with internal memory, and software expressed as source code.
Single instruction multiple dataSingle Instruction on Multiple Data (signifiant en anglais : « instruction unique, données multiples »), ou SIMD, est une des quatre catégories d'architecture définies par la taxonomie de Flynn en 1966 et désigne un mode de fonctionnement des ordinateurs dotés de capacités de parallélisme. Dans ce mode, la même instruction est appliquée simultanément à plusieurs données pour produire plusieurs résultats.
Central processing unitA 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 program, such as arithmetic, logic, controlling, and input/output (I/O) operations. This role contrasts with that of external components, such as main memory and I/O circuitry, and specialized coprocessors such as graphics processing units (GPUs). The form, design, and implementation of CPUs have changed over time, but their fundamental operation remains almost unchanged.
Designvignette|Chaise de Charles Rennie Mackintosh, 1897. Le design, le stylisme ou la stylique est une activité de création souvent à vocation industrielle ou commerciale, pouvant s’orienter vers les milieux sociaux, politiques, scientifiques et environnementaux. Le but premier du design est d’inventer, d’améliorer ou de faciliter l’usage ou le processus d’un élément ayant à interagir avec un produit ou un service matériel ou virtuel.
SIMTSIMT (de l'Single Instruction, Multiple Threads, selon la taxonomie de Flynn) est une amélioration de SIMD (de l'Single Instruction, Multiple Data) qui permettait sur des processeur arithmétique spécialisés de faire des calculs sur plusieurs données en une seule instruction, en l'adaptant au calcul multithread (c'est-à-dire, comportant plusieurs files d'exécution). MIMD (multiple instruction, multiple data) SIMD (Single Instruction, Multiple Data) SPMD (Single Pogram, Multiple Data) Processeur vectoriel Cat
Processeur superscalaireUn processeur est dit superscalaire s'il est capable d'exécuter plusieurs instructions simultanément parmi une suite d'instructions. Pour cela, il comporte plusieurs unités de calcul, et est capable de détecter l'absence de dépendances entre instructions. Un processeur superscalaire cherche à exploiter le parallélisme entre instructions pour accélérer l'exécution des programmes. Cette approche évite de modifier les programmes pour exploiter le parallélisme : le processeur détecte lui-même les instructions pouvant être exécutées en parallèle, contrairement à d'autres approches, comme le VLIW.