中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.017 seconds)

    Dynamic provisioning of computing resources
    3.
    发明授权
    Dynamic provisioning of computing resources 有权
    动态配置计算资源

    公开(公告)号：US09535754B1

    公开(公告)日：2017-01-03

    申请号：US14615135

    申请日：2015-02-05

    Applicant: Amazon Technologies, Inc.

    Inventor： Anthony Joseph Suarez ,  Jason Roy Rupard ,  Eden Grail Adogla ,  Michael Francis Quigley

    IPC: G06F9/46 ,  G06F9/50 ,  G06F9/48

    CPC classification number: G06F9/5011 ,  G06F9/4881 ,  G06F9/5027

    Abstract: Dynamic provisioning of computing resources may be implemented to provision computing resources for a data center or other collection of computing resources. Computing resources for provisioning may be detected. A build manifest describing configuration operations to provision the computing resources to perform respective tasks may be identified. The build manifest may be evaluated to direct the computing resources to perform the configuration operations according to the build manifest. In some embodiments, the provisioning of the computing resources may be paused or undone according to the build manifest. Upon completion of the configuration operations, the computing resources may be made available to perform the respective tasks.

    Abstract translation: 可以实现计算资源的动态配置以为数据中心或其他计算资源集合提供计算资源。 可以检测用于供应的计算资源。 可以识别描述配置操作以构建计算资源以执行相应任务的构建清单。 可以评估构建清单以指导计算资源根据构建清单执行配置操作。 在一些实施例中，计算资源的供应可以根据构建清单暂停或撤消。 在完成配置操作之后，可以使计算资源可用于执行相应的任务。

    Dynamic regulation of parallelism for job scheduling
    5.
    发明授权
    Dynamic regulation of parallelism for job scheduling 有权

    公开(公告)号：US11175950B1

    公开(公告)日：2021-11-16

    申请号：US16877269

    申请日：2020-05-18

    Applicant: Amazon Technologies, Inc.

    Inventor： Xu Yang ,  Jason Roy Rupard ,  Aswin Damodar ,  Devendra D Chavan ,  Ujjwal Kamal Kabra ,  Brian W Barrett ,  Stephen William Kendrex

    IPC: G06F9/48 ,  G06F9/54 ,  G06F9/38

    Abstract: Methods, systems, and computer-readable media for dynamic regulation of parallelism for job scheduling are disclosed. A job scheduler sends a resource manager a request to execute a first set of compute jobs using a set of computing resources. The number of jobs corresponds to a first parallelism value. The job scheduler receives a response indicating that the number of computing resources was sufficient or insufficient to schedule the jobs. The job scheduler sends another request to execute another set of compute jobs whose number corresponds to a new parallelism value determined based at least in part on the response. If the number of computing resources was sufficient, the new parallelism value represents an increase over the first parallelism value. If the number of computing resources was insufficient, the new parallelism value represents a decrease from the first parallelism value.

    Providing an application programming interface (API) including a bulk computing task operation
    6.
    发明授权
    Providing an application programming interface (API) including a bulk computing task operation 有权

    公开(公告)号：US11138033B1

    公开(公告)日：2021-10-05

    申请号：US16111549

    申请日：2018-08-24

    Applicant: Amazon Technologies, Inc.

    Inventor： SongPerk Sem ,  Jason Roy Rupard ,  Aswin Damodar ,  Chetan Hosmani

    IPC: G06F3/00 ,  G06F9/48 ,  G06F9/50 ,  G06F9/54

    Abstract: Techniques are described for providing an application programming interface (API) that includes a bulk computing task operation. A bulk computing task operation enables users to request performance of any number of computing tasks using a single API request. To submit a bulk task request, a user generates or causes the generation of bulk task data describing a plurality of computing tasks to be executed by an application or service, and causes the bulk task data to be stored at an accessible storage location. A single bulk task API request can be generated that includes an identifier of the storage location at which the corresponding bulk task data is stored. The submission of a bulk task API request results in a synchronous response to the requesting client including an identifier of the request that can be used to request status updates, while processing the request can occur asynchronously using backend resources.

Patent Agency Ranking