Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
A method includes: dequeuing a signal primitive from a signaling command queue in the set of command queues, the signal primitive pointing to a waiting command queue; in response to the signal primitive pointing to the waiting command queue, incrementing a number of pending signal primitives in the signal-wait counter matrix; dequeuing a wait primitive from the waiting command queue, the wait primitive pointing to the signaling command queue; in response to the wait primitive pointing to the signaling command queue, accessing the register to read the number of pending signal primitives; in response to the number of pending signal primitives indicating at least one pending signal primitive: decrementing the number of pending signal primitives; and dequeuing an instruction from the waiting command queue; and dispatching a control signal representing the instruction to a resource.
G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
G06F 9/52 - Synchronisation de programmesExclusion mutuelle, p. ex. au moyen de sémaphores
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
3.
METHOD FOR AUTOMATIC HYBRID QUANTIZATION OF DEEP ARTIFICIAL NEURAL NETWORKS
A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer. The method additionally includes, while a loss-of-accuracy threshold exceeds the accuracy of the quantized network: converting a floating-point layer represented by the low-bit-width layer to a high-bit-width layer; replacing the low-bit-width layer with the high-bit-width layer in the quantized network; updating the accuracy of the quantized network; and, in response to the accuracy of the quantized network exceeding the loss-of-accuracy threshold, returning the quantized network.
A tensor traversal engine in a processor system comprising a source memory component and a destination memory component, the tensor traversal engine comprising: a control signal register storing a control signal for a strided data transfer operation from the source memory component to the destination memory component, the control signal comprising an initial source address, an initial destination address, a first source stride length in a first dimension, and a first source stride count in the first dimension; a source address register communicatively coupled to the control signal register; a destination address register communicatively coupled to the control signal register; a first source stride counter communicatively coupled to the control signal register; and control logic communicatively coupled to the control signal register, the source address register, and the first source stride counter.
G06F 9/345 - Adressage de l'opérande d'instruction ou du résultat ou accès à l'opérande d'instruction ou au résultat d'opérandes ou de résultats multiples
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
5.
PROCESSOR SYSTEM AND METHOD FOR INCREASING DATA-TRANSFER BANDWIDTH DURING EXECUTION OF A SCHEDULED PARALLEL PROCESS
A broadcast subsystem of a processor system includes: a set of broadcast buses, each broadcast bus in the set of broadcast buses electrically coupled to a subset of primary memory units in the set of primary memory units; a primary memory unit queue: configured to store a first set of data transfer requests associated with the set of primary memory units; electrically coupled to the data buffer a broadcast scheduler: electrically coupled to the primary memory unit queue; electrically coupled to the set of broadcast buses; and configured to transfer source data from the data buffer to a target subset of primary memory units in the set of primary memory units via the set of broadcast buses based on the set of data transfer requests stored in the primary memory unit queue.
G06N 3/10 - Interfaces, langages de programmation ou boîtes à outils de développement logiciel, p. ex. pour la simulation de réseaux neuronaux
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
A method includes: dequeuing a signal primitive from a signaling command queue in the set of command queues, the signal primitive pointing to a waiting command queue; in response to the signal primitive pointing to the waiting command queue, incrementing a number of pending signal primitives in the signal-wait counter matrix; dequeuing a wait primitive from the waiting command queue, the wait primitive pointing to the signaling command queue; in response to the wait primitive pointing to the signaling command queue, accessing the register to read the number of pending signal primitives; in response to the number of pending signal primitives indicating at least one pending signal primitive: decrementing the number of pending signal primitives; and dequeuing an instruction from the waiting command queue; and dispatching a control signal representing the instruction to a resource.
G06F 9/46 - Dispositions pour la multiprogrammation
G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
G06F 9/52 - Synchronisation de programmesExclusion mutuelle, p. ex. au moyen de sémaphores
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer. The method additionally includes, while a loss-of-accuracy threshold exceeds the accuracy of the quantized network: converting a floating-point layer represented by the low-bit-width layer to a high-bit-width layer; replacing the low-bit-width layer with the high-bit-width layer in the quantized network; updating the accuracy of the quantized network; and, in response to the accuracy of the quantized network exceeding the loss-of-accuracy threshold, returning the quantized network.
A tensor traversal engine in a processor system comprising a source memory component and a destination memory component, the tensor traversal engine comprising: a control signal register storing a control signal for a strided data transfer operation from the source memory component to the destination memory component, the control signal comprising an initial source address, an initial destination address, a first source stride length in a first dimension, and a first source stride count in the first dimension; a source address register communicatively coupled to the control signal register; a destination address register communicatively coupled to the control signal register; a first source stride counter communicatively coupled to the control signal register; and control logic communicatively coupled to the control signal register, the source address register, and the first source stride counter.
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06F 9/345 - Adressage de l'opérande d'instruction ou du résultat ou accès à l'opérande d'instruction ou au résultat d'opérandes ou de résultats multiples
G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
A method includes: accessing a static schedule of a target neural network for execution by a processing device, the target neural network including a set of layers; generating a set of expected performance metrics of the target neural network based on the static schedule, the set of expected performance metrics including a first expected performance metric for a first layer in the set of layers; accessing a set of runtime performance metrics captured during execution of the target neural network by the processing device, the set of runtime performance metrics including a first runtime performance metric for the first layer; and, in response to detecting a difference between the first runtime performance metric and the first expected performance metric exceeding a threshold, serving an alert at a user interface.
A method includes: accessing a static schedule of a target neural network for execution by a processing device, the target neural network including a set of layers; generating a set of expected performance metrics of the target neural network based on the static schedule, the set of expected performance metrics including a first expected performance metric for a first layer in the set of layers; accessing a set of runtime performance metrics captured during execution of the target neural network by the processing device, the set of runtime performance metrics including a first runtime performance metric for the first layer; and, in response to detecting a difference between the first runtime performance metric and the first expected performance metric exceeding a threshold, serving an alert at a user interface.
A tensor traversal engine in a processor system comprising a source memory component and a destination memory component, the tensor traversal engine comprising: a control signal register storing a control signal for a strided data transfer operation from the source memory component to the destination memory component, the control signal comprising an initial source address, an initial destination address, a first source stride length in a first dimension, and a first source stride count in the first dimension; a source address register communicatively coupled to the control signal register; a destination address register communicatively coupled to the control signal register; a first source stride counter communicatively coupled to the control signal register; and control logic communicatively coupled to the control signal register, the source address register, and the first source stride counter.
G06F 9/345 - Adressage de l'opérande d'instruction ou du résultat ou accès à l'opérande d'instruction ou au résultat d'opérandes ou de résultats multiples
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
A broadcast subsystem of a processor system includes: a set of broadcast buses, each broadcast bus in the set of broadcast buses electrically coupled to a subset of primary memory units in the set of primary memory units; a primary memory unit queue: configured to store a first set of data transfer requests associated with the set of primary memory units; electrically coupled to the data buffer a broadcast scheduler: electrically coupled to the primary memory unit queue; electrically coupled to the set of broadcast buses; and configured to transfer source data from the data buffer to a target subset of primary memory units in the set of primary memory units via the set of broadcast buses based on the set of data transfer requests stored in the primary memory unit queue.
G06N 3/10 - Interfaces, langages de programmation ou boîtes à outils de développement logiciel, p. ex. pour la simulation de réseaux neuronaux
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
A method includes: dequeuing a signal primitive from a signaling command queue in the set of command queues, the signal primitive pointing to a waiting command queue; in response to the signal primitive pointing to the waiting command queue, incrementing a number of pending signal primitives in the signal-wait counter matrix; dequeuing a wait primitive from the waiting command queue, the wait primitive pointing to the signaling command queue; in response to the wait primitive pointing to the signaling command queue, accessing the register to read the number of pending signal primitives; in response to the number of pending signal primitives indicating at least one pending signal primitive: decrementing the number of pending signal primitives; and dequeuing an instruction from the waiting command queue; and dispatching a control signal representing the instruction to a resource.
G06F 9/46 - Dispositions pour la multiprogrammation
G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
G06F 9/52 - Synchronisation de programmesExclusion mutuelle, p. ex. au moyen de sémaphores
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
09 - Appareils et instruments scientifiques et électriques
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Microprocessors; integrated circuit modules; multichip
modules; downloadable computer software development tools;
downloadable software development kits (SDKs); downloadable
proxy software; downloadable computer software; all of the
foregoing for use in edge computing, fog computing,
decentralized computing, Internet of Things, artificial
intelligence, machine learning, deep learning, image feature
extraction, predictive analytics, software development, high
performance computing and computer and telecommunication
networks. Development and implementation of computer software,
computer hardware and technology solutions for edge AI
applications for the purpose of low power consumption and
highly efficient AI computing and distributed device
management; consulting services in the fields of artificial
intelligence and edge computing.
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
A broadcast subsystem of a processor system includes: a set of broadcast buses, each broadcast bus in the set of broadcast buses electrically coupled to a subset of primary memory units in the set of primary memory units; a primary memory unit queue: configured to store a first set of data transfer requests associated with the set of primary memory units; and electrically coupled to the data buffer a broadcast scheduler: electrically coupled to the primary memory unit queue; electrically coupled to the set of broadcast buses; and configured to transfer source data from the data buffer to a target subset of primary memory units in the set of primary memory units via the set of broadcast buses based on the set of data transfer requests stored in the primary memory unit queue.
G06N 3/10 - Interfaces, langages de programmation ou boîtes à outils de développement logiciel, p. ex. pour la simulation de réseaux neuronaux
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
A broadcast subsystem of a processor system includes: a set of broadcast buses, each broadcast bus in the set of broadcast buses electrically coupled to a subset of primary memory units in the set of primary memory units; a primary memory unit queue: configured to store a first set of data transfer requests associated with the set of primary memory units; and electrically coupled to the data buffer a broadcast scheduler: electrically coupled to the primary memory unit queue; electrically coupled to the set of broadcast buses; and configured to transfer source data from the data buffer to a target subset of primary memory units in the set of primary memory units via the set of broadcast buses based on the set of data transfer requests stored in the primary memory unit queue.
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
19.
A PROCESSOR SYSTEM AND METHOD FOR INCREASING DATA-TRANSFER BANDWIDTH DURING EXECUTION OF A SCHEDULED PARALLEL PROCESS
A broadcast subsystem of a processor system includes: a set of broadcast buses, each broadcast bus in the set of broadcast buses electrically coupled to a subset of primary memory units in the set of primary memory units; a primary memory unit queue: configured to store a first set of data transfer requests associated with the set of primary memory units; and electrically coupled to the data buffer a broadcast scheduler: electrically coupled to the primary memory unit queue; electrically coupled to the set of broadcast buses; and configured to transfer source data from the data buffer to a target subset of primary memory units in the set of primary memory units via the set of broadcast buses based on the set of data transfer requests stored in the primary memory unit queue.
A tensor traversal engine in a processor system comprising a source memory component and a destination memory component, the tensor traversal engine comprising: a control signal register storing a control signal for a strided data transfer operation from the source memory component to the destination memory component, the control signal comprising an initial source address, an initial destination address, a first source stride length in a first dimension, and a first source stride count in the first dimension; a source address register communicatively coupled to the control signal register; a destination address register communicatively coupled to the control signal register; a first source stride counter communicatively coupled to the control signal register; and control logic communicatively coupled to the control signal register, the source address register, and the first source stride counter.
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 9/345 - Adressage de l'opérande d'instruction ou du résultat ou accès à l'opérande d'instruction ou au résultat d'opérandes ou de résultats multiples
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
A tensor traversal engine in a processor system comprising a source memory component and a destination memory component, the tensor traversal engine comprising: a control signal register storing a control signal for a strided data transfer operation from the source memory component to the destination memory component, the control signal comprising an initial source address, an initial destination address, a first source stride length in a first dimension, and a first source stride count in the first dimension; a source address register communicatively coupled to the control signal register; a destination address register communicatively coupled to the control signal register; a first source stride counter communicatively coupled to the control signal register; and control logic communicatively coupled to the control signal register, the source address register, and the first source stride counter.
G06F 9/345 - Adressage de l'opérande d'instruction ou du résultat ou accès à l'opérande d'instruction ou au résultat d'opérandes ou de résultats multiples
G06F 9/30 - Dispositions pour exécuter des instructions machines, p. ex. décodage d'instructions
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06F 9/50 - Allocation de ressources, p. ex. de l'unité centrale de traitement [UCT]
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
23.
System and method for queuing commands in a deep learning processor
A method includes: dequeuing a signal primitive from a signaling command queue in the set of command queues, the signal primitive pointing to a waiting command queue; in response to the signal primitive pointing to the waiting command queue, incrementing a number of pending signal primitives in the signal-wait counter matrix; dequeuing a wait primitive from the waiting command queue, the wait primitive pointing to the signaling command queue; in response to the wait primitive pointing to the signaling command queue, accessing the register to read the number of pending signal primitives; in response to the number of pending signal primitives indicating at least one pending signal primitive: decrementing the number of pending signal primitives; and dequeuing an instruction from the waiting command queue; and dispatching a control signal representing the instruction to a resource.
G06F 9/46 - Dispositions pour la multiprogrammation
G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
G06F 9/52 - Synchronisation de programmesExclusion mutuelle, p. ex. au moyen de sémaphores
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
24.
Method for static scheduling of artificial neural networks for a processor
A method for scheduling an artificial neural network includes: accessing a processor representation of a multicore processor comprising processor cores, direct memory access cores, and a cost model; and accessing a network structure defining a set of layers. The method also includes, for each layer in the set of layers: generating a graph based on the processor representation, the graph defining compute nodes, data transfer nodes, and edges representing dependencies between the compute nodes and the data transfer nodes; and generating a schedule for the layer based on the graph, the schedule assigning the compute nodes to the processor cores and assigning the data transfer nodes to the direct memory access cores. The method further includes aggregating the schedule for each layer in the set of layers to generate a complete schedule for the artificial neural network.
G06F 18/21 - Conception ou mise en place de systèmes ou de techniquesExtraction de caractéristiques dans l'espace des caractéristiquesSéparation aveugle de sources
G06F 30/20 - Optimisation, vérification ou simulation de l’objet conçu
G06F 119/06 - Analyse de puissance ou optimisation de puissance
25.
Method for automatic hybrid quantization of deep artificial neural networks
A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer. The method additionally includes, while a loss-of-accuracy threshold exceeds the accuracy of the quantized network: converting a floating-point layer represented by the low-bit-width layer to a high-bit-width layer; replacing the low-bit-width layer with the high-bit-width layer in the quantized network; updating the accuracy of the quantized network; and, in response to the accuracy of the quantized network exceeding the loss-of-accuracy threshold, returning the quantized network.
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
Disclosed herein is a processor for deep learning. In one embodiment, the processor comprises: a load and store unit configured to load and store image pixel data and stencil data; a register unit, implementing a banked register file, configured to: load and store a subset of the image pixel data from the load and store unit, and concurrently provide access to image pixel values stored in a register file entry of the banked register file, wherein the subset of the image pixel data comprises the image pixel values stored in the register file entry; and a plurality of arithmetic logic units configured to concurrently perform one or more operations on the image pixel values stored in the register file entry and corresponding stencil data of the stencil data.
G06K 9/56 - Combinaisons de fonctions de prétraitement en utilisant un opérateur local, c. à d. des moyens pour opérer sur un point image élémentaire en fonction des éléments situés à proximité immédiate de ce point
G06T 5/20 - Amélioration ou restauration d'image utilisant des opérateurs locaux
