Intel Corporation

Suraj Prabhakaran

Francesc Guim Bernat

Kshitij Arun Doshi

Ned M Smith

Karthik Kumar

Timothy Verrall

Da-Ming Chiang

Brinda Ganesh

Mark A Schmisseur

Susanne M Balle

Daniel Rivas Barragan

Petar Torre

Murugasamy K Nachimuthu

Alexander Bachmutsky

Evan Custodio

Slawomir Putyrski

John Chun Kwok Leung

Thomas Willhalm

Andrew J Herdrich

Raghu R Kondapalli

Dario Sabella

Miltiadis Filippou

Neal Conrad Oliver

Alexander Vul

Mohan J Kumar

Patrick G Kutch

Trevor Cooper

Rashmin N Patel

Monica Kenguva

Anil Rao

Ignacio Astilleros Diez

Felipe Pastor Beneyto

Joe Cahill

Ramanathan Sethuraman

Patrick Bohan

Kapil Sood

Tarun Viswanathan

Nilesh K Jain

Bassam N Coury

Mark S Myers

Johan G Van De Groenendaal

Benjamin Graniello

Ravi Iyer

Tushar Gohad

Uzair Qureshi

Kevin Bohan

Francesc Cesc Guim Bernat

There is disclosed an example of an artificial intelligence (AI) system, including: a first hardware platform; a fabric interface configured to communicatively couple the first hardware platform to a second hardware platform; a processor hosted on the first hardware platform and programmed to operate on an AI problem; and a first training accelerator, including: an accelerator hardware; a platform inter-chip link (ICL) configured to communicatively couple the first training accelerator to a second training accelerator on the first hardware platform without aid of the processor; a fabric ICL to communicatively couple the first training accelerator to a third training accelerator on a second hardware platform without aid of the processor; and a system decoder configured to operate the fabric ICL and platform ICL to share data of the accelerator hardware between the first training accelerator and second and third training accelerators without aid of the processor.

System decoder for training accelerators

Examples include techniques for artificial intelligence (AI) capabilities at a network switch. These examples include receiving a request to register a neural network for loading to an inference resource located at the network switch and loading the neural network based on information included in the request to support an AI service to be provided by users requesting the AI service.

Techniques for artificial intelligence capabilities at a network device

Examples described herein relate to a network interface device. In some examples, the network interface device includes a device interface; input/output circuitry to receive Ethernet compliant packets and output Ethernet compliant packets; circuitry to monitor a particular page for a rate of data copying among nodes within a group of two or more nodes; and circuitry to perform one or more actions based, at least in part, on the rate of data copying among the nodes within the group of two or more nodes to attempt to reduce a number of copy operations of the data among the nodes within the group of two or more nodes, wherein the group of two or more nodes are part of a distributed shared memory (DSM).

Management of distributed shared memory

Systems and techniques for intelligent data forwarding in edge networks are described herein. A request may be received from an edge user device for a service via a first endpoint. A time value may be calculated using a timestamp of the request. Motion characteristics may be determined for the edge user device using the time value. A response to the request may be transmitted to a second endpoint based on the motion characteristics.

Intelligent data forwarding in edge networks

Various systems and methods of initiating and performing contextualized AI inferencing, are described herein. In an example, operations performed with a gateway computing device to invoke an inferencing model include receiving and processing a request for an inferencing operation, selecting an implementation of the inferencing model on a remote service based on a model specification and contextual data from the edge device, and executing the selected implementation of the inferencing model, such that results from the inferencing model are provided back to the edge device. Also in an example, operations performed with an edge computing device to request an inferencing model include collecting contextual data, generating an inferencing request, transmitting the inference request to a gateway device, and receiving and processing the results of execution. Further techniques for implementing a registration of the inference model, and invoking particular variants of an inference model, are also described.

Distributed and contextualized artificial intelligence inference service

Example edge gateway circuitry to schedule service requests in a network computing system includes: gateway-level hardware queue manager circuitry to: parse the service requests based on service parameters in the service requests; and schedule the service requests in a queue based on the service parameters, the service requests received from client devices; and hardware queue manager communication interface circuitry to send ones of the service requests from the queue to rack-level hardware queue manager circuitry in a physical rack, the ones of the service requests corresponding to functions as a service provided by resources in the physical rack.

Methods and apparatus to schedule service requests in a network computing system using hardware queue managers

An architecture to perform resource management among multiple network nodes and associated resources is disclosed. Example resource management techniques include those relating to: proactive reservation of edge computing resources; deadline-driven resource allocation; speculative edge QoS pre-allocation; and automatic QoS migration across edge computing nodes. In a specific example, a technique for service migration includes: identifying a service operated with computing resources in an edge computing system, involving computing capabilities for a connected edge device with an identified service level; identifying a mobility condition for the service, based on a change in network connectivity with the connected edge device; and performing a migration of the service to another edge computing system based on the identified mobility condition, to enable the service to be continued at the second edge computing apparatus to provide computing capabilities for the connected edge device with the identified service level.

Quality of service (QoS) management in edge computing environments

Technologies for fulfilling service requests in an edge architecture include an edge gateway device to receive a request from an edge device or an intermediate tier device of an edge network to perform a function of a service by an entity hosting the service. The edge gateway device is to identify one or more input data to fulfill the request by the service and request the one or more input data from an edge resource identified to provide the input data. The edge gateway device is to provide the input data to the entity associated with the request.

Technologies for multi-tier prefetching in a context-aware edge gateway

Technologies for migrating data between edge accelerators hosted on different edge locations include a device hosted on a present edge location. The device includes one or more processors to: receive a workload from a requesting device, determine one or more accelerator devices hosted on the present edge location to perform the workload, and transmit the workload to the one or more accelerator devices to process the workload. The one or more processor is further to determine whether to perform data migration from the one or more accelerator devices to one or more different edge accelerator devices hosted on a different edge location, and send, in response to a determination to perform the data migration, a request to the one or more accelerator devices on the present edge location for transformed workload data to be processed by the one or more different edge accelerator devices.

Technologies for data migration between edge accelerators hosted on different edge locations

An architecture to allow Multi-Access Edge Computing (MEC) billing and charge tracking, is disclosed. In an example, a tracking process, such as is performed by an edge computing apparatus, includes: receiving a computational processing request for a service operated with computing resources of the edge computing apparatus from a connected edge device within the first access network, wherein the computational processing request includes an identification of the connected edge device; identifying a processing device, within the first access network, for performing the computational processing request; and storing the identification of the connected edge device, a processing device identification, and data describing the computational processes completed by the processing device in association with the computational processing request.

Multi-access edge computing (MEC) billing and charging tracking enhancements

Techniques for artificial intelligence capabilities at a network switch

Systems and techniques for AI model and data camouflaging techniques for cloud edge are described herein. In an example, a neural network transformation system is adapted to receive, from a client, camouflaged input data, the camouflaged input data resulting from application of a first encoding transformation to raw input data. The neural network transformation system may be further adapted to use the camouflaged input data as input to a neural network model, the neural network model created using a training data set created by applying the first encoding transformation on training data. The neural network transformation system may be further adapted to receive a result from the neural network model and transmit output data to the client, the output data based on the result.

AI model and data transforming techniques for cloud edge

Examples described herein relate to management of battery-use by one or more computing resources in the event of a power outage. Data used by one or more computing resources can be backed-up using battery power. Battery power is allocated to data back-up operations based at least on one or more of: criticality level of data, priority of an application that processes the data, or priority level of resource. The computing resource can back-up data to a persistent storage media. The computing resource can store a log of data that is backed-up or not backed-up. The log can be used by the computing resource to access the backed-up data for continuing to process the data and to determine what data is not available for processing.

Priority-based battery allocation for resources during power outage

A computing cluster can receive a request to perform a workload from a client. The request can include a service discovery agent. If the request is authenticated and permitted on the computing cluster, the service discovery agent is executed. Execution of the service discovery agent can lead to discovery of resource capabilities of the cluster and selection of the appropriate resource based on performance requirements. The selected resource can be deployed for execution of the workload.

Computing resource discovery and allocation

Growing community of inventors

Aachen, Germany

Suraj Prabhakaran