公开(公告)号：US10833969B2

公开(公告)日：2020-11-10

申请号：US15655855

申请日：2017-07-20

Applicant: INTEL CORPORATION

Inventor： Francesc Guim Bernat ,  Susanne M. Balle ,  Daniel Rivas Barragan ,  John Chun Kwok Leung ,  Suraj Prabhakaran ,  Murugasamy K. Nachimuthu ,  Slawomir Putyrski

IPC: H04L12/26 ,  G06F16/22 ,  G06F16/23 ,  H04L12/24 ,  H04L12/927 ,  H04Q9/00 ,  H04L29/08 ,  H04L12/925

Abstract: Techniques for increasing malleability in software-defined infrastructures are described. A compute node, including one or more processor circuits, may be configured to access one or more remote resources via a fabric, the compute node may be configured to monitor utilization of the one or more remote resources. The compute node may be further configured to identify based on one or more criteria that one or more remote resources may be released and initiate release of identified one or more remote resources. The compute node may be configured to generate a notification to a software stack indicating that the identified one or more remote resources has been released. Other embodiments are described and claimed.

公开(公告)号：US10805179B2

公开(公告)日：2020-10-13

申请号：US15857526

申请日：2017-12-28

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Kshitij Arun Doshi ,  Suraj Prabhakaran ,  Raghu Kondapalli ,  Alexander Bachmutsky

IPC: H04L12/24 ,  H04L29/08 ,  G06N5/04

Abstract: Various systems and methods for implementing a service-level agreement (SLA) apparatus receive a request from a requester via a network interface of the gateway, the request comprising an inference model identifier that identifies a handler of the request, and a response time indicator. The response time indicator relates to a time within which the request is to be handled indicates an undefined time within which the request is to be handled. The apparatus determines a network location of a handler that is a platform or an inference model to handle the request consistent with the response time indicator, and routes the request to the handler at the network location.

公开(公告)号：US20190281132A1

公开(公告)日：2019-09-12

申请号：US16415138

申请日：2019-05-17

Applicant: Intel Corporation

Inventor： Ramanathan Sethuraman ,  Timothy Verrall ,  Ned M. Smith ,  Thomas Willhalm ,  Brinda Ganesh ,  Francesc Guim Bernat ,  Karthik Kumar ,  Evan Custodio ,  Suraj Prabhakaran ,  Ignacio Astilleros Diez ,  Nilesh K. Jain ,  Ravi Iyer ,  Andrew J. Herdrich ,  Alexander Vul ,  Patrick G. Kutch ,  Kevin Bohan ,  Trevor Cooper

IPC: H04L29/08 ,  H04L9/08 ,  H04L29/06

Abstract: Technologies for managing telemetry and sensor data on an edge networking platform are disclosed. According to one embodiment disclosed herein, a device monitors telemetry data associated with multiple services provided in the edge networking platform. The device identifies, for each of the services and as a function of the associated telemetry data, one or more service telemetry patterns. The device generates a profile including the identified service telemetry patterns.

公开(公告)号：US20190141119A1

公开(公告)日：2019-05-09

申请号：US16234734

申请日：2018-12-28

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Ned Smith ,  Kshitij Doshi ,  Alexander Bachmutsky ,  Suraj Prabhakaran

IPC: H04L29/08 ,  H04L12/24

Abstract: Technologies for function as a service (FaaS) arbitration include an edge gateway, multiple endpoint devices, and multiple service providers. The edge gateway receives a registration request from a service provider that is indicative of an FaaS function identifier and a transform function. The edge gateway verifies an attestation received from the service provider and registers the service provider. The edge gateway receives a function execution request from an endpoint device that is indicative of the FaaS function identifier. The edge gateway selects the service provider based on the FaaS function identifier, programs an accelerator with the transform function, executes the transform function with the accelerator to transform the function execution request to a provider request, and submits the provider request to the service provider. The service provider may be selected based on an expected service level included in the function execution request. Other embodiments are described and claimed.

公开(公告)号：US20190140838A1

公开(公告)日：2019-05-09

申请号：US16234724

申请日：2018-12-28

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Johan Van De Groenendaal ,  Kshitij A. Doshi ,  Susanne M. Balle ,  Suraj Prabhakaran

IPC: H04L9/32 ,  H04L9/08

Abstract: Technologies for providing certified telemetry data indicative of resource utilizations include a device with circuitry configured to obtain telemetry data indicative of a utilization of one or more device resources over a time period. The circuitry is additionally configured to sign the obtained telemetry data with a private key associated with the present device. Further, the circuitry is configured to send the signed telemetry data to a telemetry service for analysis

公开(公告)号：US11818106B2

公开(公告)日：2023-11-14

申请号：US17403549

申请日：2021-08-16

Applicant: Intel Corporation

Inventor： Kshitij Arun Doshi ,  Francesc Guim Bernat ,  Suraj Prabhakaran

IPC: H04L9/40 ,  G06N3/08 ,  G06F21/14 ,  G06F21/62 ,  H04W12/02 ,  H04L67/10 ,  G06N3/045 ,  G06N3/04

CPC classification number: H04L63/0428 ,  G06F21/14 ,  G06F21/6245 ,  G06N3/045 ,  G06N3/08 ,  H04L67/10 ,  H04W12/02 ,  G06N3/04

Abstract: 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.

公开(公告)号：US11522682B2

公开(公告)日：2022-12-06

申请号：US17332733

申请日：2021-05-27

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Suraj Prabhakaran ,  Kshitij A. Doshi ,  Timothy Verrall

IPC: H04L9/08 ,  G06F3/06 ,  G06F9/50 ,  H04L69/12 ,  H04L69/32 ,  G06F16/25 ,  G06F16/2453 ,  H04L49/9005 ,  G11C8/12 ,  G11C29/02 ,  H04L41/0896 ,  G06F30/34 ,  B25J15/00 ,  G06F1/18 ,  G06F1/20 ,  G06F11/34 ,  G06F15/78 ,  H04L41/5025 ,  H04L67/1008 ,  H05K7/14 ,  H05K7/18 ,  H05K7/20 ,  H04L67/1001 ,  G11C29/36 ,  G11C29/38 ,  G11C29/44 ,  G06F16/22 ,  G06F16/2455 ,  G06F12/02 ,  G06F12/14 ,  G06F13/16 ,  G06F15/173 ,  G06F13/40 ,  G06F13/42 ,  G06F9/448 ,  G06F9/28 ,  G06F15/16 ,  H04L41/0893 ,  H04L69/22 ,  H04L69/321 ,  H04L41/0213 ,  H04L41/0668 ,  H04L41/0677 ,  H04L45/28 ,  H04L45/7453 ,  H04L47/11 ,  H04L47/125 ,  H04L49/00 ,  H04L49/351 ,  G06F9/4401 ,  G06F9/445 ,  G06F12/06 ,  G06F16/23 ,  G06F16/248 ,  G06F16/901 ,  G06F16/11 ,  G06F9/44 ,  G06F9/48 ,  G06F21/10 ,  G06N3/063 ,  G06Q10/06 ,  G06Q30/02 ,  H04L41/14 ,  H04L41/5019 ,  H04L49/40 ,  H04L9/40 ,  G06F12/0802 ,  G06F12/1045

Abstract: Technologies for providing streamlined provisioning of accelerated functions in a disaggregated architecture include a compute sled. The compute sled includes a network interface controller and circuitry to determine whether to accelerate a function of a workload executed by the compute sled, and send, to a memory sled and in response to a determination to accelerate the function, a data set on which the function is to operate. The circuitry is also to receive, from the memory sled, a service identifier indicative of a memory location independent handle for data associated with the function, send, to a compute device, a request to schedule acceleration of the function on the data set, receive a notification of completion of the acceleration of the function, and obtain, in response to receipt of the notification and using the service identifier, a resultant data set from the memory sled. The resultant data set was produced by an accelerator device during acceleration of the function on the data set. Other embodiments are also described and claimed.

公开(公告)号：US11494633B2

公开(公告)日：2022-11-08

申请号：US15859472

申请日：2017-12-30

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Suraj Prabhakaran ,  Kshitij A. Doshi ,  Da-Ming Chiang

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/063

Abstract: Examples include techniques to manage training or trained models for deep learning applications. Examples include routing commands to configure a training model to be implemented by a training module or configure a trained model to be implemented by an inference module. The commands routed via out-of-band (OOB) link while training data for the training models or input data for the trained models are routed via inband links.

公开(公告)号：US11444866B2

公开(公告)日：2022-09-13

申请号：US15655864

申请日：2017-07-20

Applicant: INTEL CORPORATION

Inventor： Daniel Rivas Barragan ,  Francesc Guim Bernat ,  Susanne M. Balle ,  John Chun Kwok Leung ,  Suraj Prabhakaran ,  Murugasamy K. Nachimuthu ,  Slawomir Putyrski

IPC: G06F15/173 ,  H04L43/16 ,  G06F16/22 ,  G06F16/23 ,  H04L41/0896 ,  H04L43/0876 ,  H04L47/80 ,  H04Q9/00 ,  H04L41/12 ,  H04L67/10 ,  H04L41/5025 ,  H04L67/1031 ,  H04L41/0816 ,  H04L67/00 ,  H04L43/0852 ,  H04L43/0894 ,  H04L41/5009 ,  H04L41/5054 ,  H04L41/16 ,  H04L47/722

Abstract: Techniques for managing static and dynamic partitions in software-defined infrastructures (SDI) are described. An SDI manager component may include one or more processor circuits to access one or more resources. The SDI manager component may include a partition manager to create one or more partitions using the one or more resources, the one or more partitions each including a plurality of nodes of a similar resource type. The SDI manager may generate an update to a pre-composed partition table, stored within a non-transitory computer-readable storage medium, including the created one or more partitions, and receive a request from an orchestrator for a node. The SDI manager may select one of the created one or more partitions to the orchestrator based upon the pre-composed partition table, and identify the selected partition to the orchestrator. Other embodiments are described and claimed.

公开(公告)号：US11416295B2

公开(公告)日：2022-08-16

申请号：US16563171

申请日：2019-09-06

Applicant: Intel Corporation

Inventor： Francesc Guim Bernat ,  Karthik Kumar ,  Suraj Prabhakaran ,  Timothy Verrall ,  Thomas Willhalm ,  Mark Schmisseur

IPC: G06F9/50 ,  G06F16/27 ,  G06F21/62 ,  G06F16/23 ,  H04L9/06 ,  H04L9/32 ,  H04L41/12 ,  H04L47/70 ,  H04L67/52 ,  H04L67/60 ,  G06F21/60 ,  H04L9/08

Abstract: Technologies for providing efficient data access in an edge infrastructure include a compute device comprising circuitry configured to identify pools of resources that are usable to access data at an edge location. The circuitry is also configured to receive a request to execute a function at an edge location. The request identifies a data access performance target for the function. The circuitry is also configured to map, based on a data access performance of each pool and the data access performance target of the function, the function to a set of the pools to satisfy the data access performance target.