公开(公告)号：US20190227843A1

公开(公告)日：2019-07-25

申请号：US16369036

申请日：2019-03-29

Applicant: Intel Corporation

Inventor： Evan Custodio ,  Francesc Guim Bernat ,  Suraj Prabhakaran ,  Trevor Cooper ,  Ned M. Smith ,  Kshitij Doshi ,  Petar Torre

IPC: G06F9/50

Abstract: 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.

公开(公告)号：US20190044918A1

公开(公告)日：2019-02-07

申请号：US15941724

申请日：2018-03-30

Applicant: Intel Corporation

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

IPC: H04L29/06 ,  G06N3/08

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：US20190042294A1

公开(公告)日：2019-02-07

申请号：US15952274

申请日：2018-04-13

Applicant: Intel Corporation

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

IPC: G06F9/455 ,  G06F9/50 ,  H04L29/08

Abstract: A method and system for implementing virtualized network functions (VNFs) in a network. Physical resources of the network are abstracted into virtual resource pools and shared by virtual network entities. A virtual channel is set up for communicating data between a first VNF and a second VNF. A memory pool is allocated for the virtual channel from a set of memory pools. New interfaces are provided for communication between VNFs. The new interfaces may allow to push and pull payloads or data units from one VNF to another. The data may be stored in a queue in the pooled memory allocated for the VNFs/services. Certain processing may be performed before the data is stored in the memory pool.

公开(公告)号：US20190042234A1

公开(公告)日：2019-02-07

申请号：US15912733

申请日：2018-03-06

Applicant: Intel Corporation

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

IPC: G06F9/28 ,  G06F9/448 ,  G06F15/16

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.