-
公开(公告)号:US20200167196A1
公开(公告)日:2020-05-28
申请号:US16723760
申请日:2019-12-20
Applicant: Intel Corporation
Inventor: Ned Smith , Francesc Guim Bernat , Sanjay Bakshi , Katalin Bartfai-Walcott , Kapil Sood , Kshitij Doshi , Robert Munoz
Abstract: Methods and apparatus to execute a workload in an edge environment are disclosed. An example apparatus includes a node scheduler to accept a task from a workload scheduler, the task including a description of a workload and tokens, a workload executor to execute the workload, the node scheduler to access a result of execution of the workload and provide the result to the workload scheduler, and a controller to access the tokens and distribute at least one of the tokens to at least one provider, the provider to provide a resource to the apparatus to execute the workload.
-
公开(公告)号:US20190044882A1
公开(公告)日:2019-02-07
申请号:US16023792
申请日:2018-06-29
Applicant: Intel Corporation
Inventor: Rajesh Poorchandran , Mats Agerstam , Karthik Veeramani , Katalin Bartfai-Walcott , Rajneesh Chowdhury
IPC: H04L12/927 , H04L12/813 , H04L12/859 , H04L12/851 , H04L12/873
Abstract: Technologies for context-aware dynamic bandwidth allocation include a network compute device configured to collect context inputs from a plurality of compute devices communicatively coupled to the network compute device. The network compute device is further configured to identify a context of each compute device based on the collected context inputs and determine a bandwidth priority for each compute device based on the identified context. Additionally, the network compute device is configure to determine an amount of bandwidth from a total available bandwidth to allocate to the compute device based on the determined bandwidth priority and update a moderated bandwidth allocation policy to reflect the determined amount of bandwidth allocated to the compute device. Other embodiments are described herein.
-