Integrated visualization
    1.
    发明授权

    公开(公告)号:US10360701B2

    公开(公告)日:2019-07-23

    申请号:US15203631

    申请日:2016-07-06

    Abstract: A system may provide a visualization function during computational functions performed by a host system. Access to a library of functions including a visualization function is provided. Then, a computing application is executed. The execution of the computing application includes generating multi-dimensional data, invoking the visualization function from the library, and providing a visual representation of at least a portion of the multi-dimensional data for display within the computing application using the visualization function.

    COOLING CONTAINER
    2.
    发明申请
    COOLING CONTAINER 审中-公开

    公开(公告)号:US20200229319A1

    公开(公告)日:2020-07-16

    申请号:US16247350

    申请日:2019-01-14

    Abstract: Example containers are provided to retain and cool electronic devices in environments where power and/or coolant (e.g., airflow) is limited or finite. In examples, a container can include a housing and a conduit system. The housing can include a plurality of sides including a front side and a back side, and can be structured to retain at least a first computing device. In addition, the housing can provide for a first and second inlet opening and a first and second outlet opening on the back side of the container. The conduit system can be provided within the housing to guide the airflow received from each of the first and second outlet openings through an interior volume of the container to cause the airflow to exit from each of the first and second outlet openings. Further, the conduit system can include a plurality of structures that combine to guide at least a portion of the airflow received through the first and second inlet openings through a top region of the interior volume as the airflow is moved from the back side of the container to the front side of the container. Further still, the conduit system can guide at least a portion of the warmed airflow to a bottom region of the interior volume as the warmed airflow is moved from the front side to the back side of the container.

    Cooling container
    3.
    发明授权

    公开(公告)号:US11464133B2

    公开(公告)日:2022-10-04

    申请号:US16247350

    申请日:2019-01-14

    Abstract: Example containers are provided to retain and cool electronic devices in environments where power and/or coolant (e.g., airflow) is limited or finite. In examples, a container can include a housing and a conduit system. The housing can include a plurality of sides including a front side and a back side, and can be structured to retain at least a first computing device. In addition, the housing can provide for a first and second inlet opening and a first and second outlet opening on the back side of the container. The conduit system can be provided within the housing to guide the airflow received from each of the first and second outlet openings through an interior volume of the container to cause the airflow to exit from each of the first and second outlet openings. Further, the conduit system can include a plurality of structures that combine to guide at least a portion of the airflow received through the first and second inlet openings through a top region of the interior volume as the airflow is moved from the back side of the container to the front side of the container. Further still, the conduit system can guide at least a portion of the warmed airflow to a bottom region of the interior volume as the warmed airflow is moved from the front side to the back side of the container.

    Managing power in a high performance computing system for resiliency and cooling

    公开(公告)号:US10809779B2

    公开(公告)日:2020-10-20

    申请号:US15889982

    申请日:2018-02-06

    Abstract: An apparatus and method thermally manage a high performance computing system having a plurality of nodes with microprocessors. To that end, the apparatus and method monitor the temperature of at least one of a) the environment of the high performance computing system and b) at least a portion of the high performance computing system. In response, the apparatus and method control the processing speed of at least one of the microprocessors on at least one the plurality of nodes as a function or at least one of the monitored temperatures.

    Method and system for shared direct access storage

    公开(公告)号:US11029847B2

    公开(公告)日:2021-06-08

    申请号:US15353413

    申请日:2016-11-16

    Abstract: In high performance computing, the potential compute power in a data center will scale to and beyond a billion-billion calculations per second (“Exascale” computing levels). Limitations caused by hierarchical memory architectures where data is temporarily stored in slower or less available memories will increasingly limit high performance computing systems from approaching their maximum potential processing capabilities. Furthermore, time spent and power consumed copying data into and out of a slower tier memory will increase costs associated with high performance computing at an accelerating rate. New technologies, such as the novel Zero Copy Architecture disclosed herein, where each compute node writes locally for performance, yet can quickly access data globally with low latency will be required. The result is the ability to perform burst buffer operations and in situ analytics, visualization and computational steering without the need for a data copy or movement.

    SYSTEM AND METHODS FOR FAULT TOLERANCE IN DECENTRALIZED MODEL BUILDING FOR MACHINE LEARNING USING BLOCKCHAIN

    公开(公告)号:US20200311583A1

    公开(公告)日:2020-10-01

    申请号:US16372098

    申请日:2019-04-01

    Abstract: Decentralized machine learning to build models is performed at nodes where local training datasets are generated. A blockchain platform may be used to coordinate decentralized machine learning (ML) over a series of iterations. For each iteration, a distributed ledger may be used to coordinate the nodes communicating via a decentralized network. A master node on the decentralized network, can include fault tolerance features. Fault tolerance involves determining whether a number of computing nodes in a population for participating in an iteration of training is above a threshold. The master node ensures that the minimum number of computing nodes for a population, indicated by the threshold, is met before continuing with an iteration. Thus, the master node can prevent decentralized ML from continuing with an insufficient population of participating node that may impact the precision of the model and/or the overall learning ability of the decentralized ML system.

Patent Agency Ranking