-
公开(公告)号：US20220198217A1
公开(公告)日：2022-06-23
申请号：US17130003
申请日：2020-12-22
摘要： A model parallel training technique for neural architecture search including the following operations: (i) receiving a plurality of ML (machine learning) models that can be substantially interchangeably applied to a computing task; (ii) for each given ML model of the plurality of ML models: (a) determining how the given ML model should be split for model parallel processing operations, and (b) computing a model parallelism score (MPS) for the given ML model, with the MPS being based on an assumption that the split for the given ML model will be used at runtime; and (iii) selecting a selected ML model based, at least in part, on the MPS scores of the ML models of the plurality of ML models.
-
公开(公告)号：US20200218440A1
公开(公告)日：2020-07-09
申请号：US16239223
申请日：2019-01-03
发明人： Yin Xia , Lu Fu , Bin Xu , Jie Hu , Xiao Lin Sun , Zhang Yu Lin , Lei Pan
IPC分类号： G06F3/0488 , G06F9/54 , G06F3/0484
摘要： A computer-implemented method and a computer system are proposed. According to the method, one or more candidate target applications are obtained in response to determination of one or more pieces of source contents from one or more source applications. A target application is determined from the one or more candidate target applications, wherein the one or more candidate target applications are shown one by one in a pre-defined order. The one or more pieces of source contents are pasted into one or more target areas in response to determining the one or more target areas in the target application.
-
公开(公告)号：US11586480B2
公开(公告)日：2023-02-21
申请号：US17102581
申请日：2020-11-24
发明人： Guang Han Sui , Jing Li , Bin Xu , Fei Qi
摘要： A set of workload criteria is determined from a workload associated with a plurality of sources. The workload is divided among a set of workload groups according to the set of workload criteria and a first workload scheduler. A set of edge computing resources is assigned to each workload group within the set according to the set of workload criteria and the set of workload groups. A portion of the workload associated with a subset of the plurality of sources is handled by a first subset of edge computing resources and a second workload scheduler, where the subset of sources is associated with a first workload group. The handling includes balancing, by the second workload scheduler, the portion of the workload among the subset of sources. The handled workload is reported to a control center.
-
公开(公告)号：US20200241674A1
公开(公告)日：2020-07-30
申请号：US16256621
申请日：2019-01-24
发明人： Bin Xu , Yin Xia , Lu Fu , Lei Pan , Xiao Lin Sun
IPC分类号： G06F3/041 , G06F3/0488 , G06F9/30 , B60K37/06
摘要： A computer-implemented. method, a computer system and a computer program product that facilitate adjusting screen sensitivity of a touch screen are proposed. The computer-implemented method comprises: determining, by a device operatively coupled to one or more processing units, one or more operational areas for an interface of an application running on a touch screen device; and determining, by the device, a screen sensitivity for each of the one or more operational areas respectively.
-
公开(公告)号：US10594771B2
公开(公告)日：2020-03-17
申请号：US15428203
申请日：2017-02-09
发明人： Feng Gao , Peng Hui Jiang , Jing Li , Qin Li , Guang H. Sui , Bin Xu , Jian Hua Zhang
摘要： A method for distributed file transfers with high performance and reliability includes creating, on a first Trivial File Transfer Protocol (TFTP) server, a global cache, where the global cache is used to store up to a first portion of a data file. The method further includes storing, on the first TFTP server, in the global cache, one or more continuous data blocks that have exceeded a defined first request rate threshold, where the one or more continuous data blocks make up a subset of the data blocks of the first portion of the data file. The method further includes predicting, on the first TFTP server, a next data block in the data file to be stored in the global cache and in response to predicting the next data block, storing, on the first TFTP server, the next data block in the global cache.
-
公开(公告)号：US10009412B1
公开(公告)日：2018-06-26
申请号：US15840444
申请日：2017-12-13
发明人： Feng Gao , Peng Hui Jiang , Jing Li , Qin Li , Guang H. Sui , Bin Xu , Jian Hua Zhang
CPC分类号： H04L67/06 , H04L67/10 , H04L67/2842 , H04L67/42
摘要： A method for distributed file transfers with high performance and reliability includes creating, on a first Trivial File Transfer Protocol (TFTP) server, a global cache, where the global cache is used to store up to a first portion of a data file. The method further includes storing, on the first TFTP server, in the global cache, one or more continuous data blocks that have exceeded a defined first request rate threshold, where the one or more continuous data blocks make up a subset of the data blocks of the first portion of the data file. The method further includes predicting, on the first TFTP server, a next data block in the data file to be stored in the global cache and in response to predicting the next data block, storing, on the first TFTP server, the next data block in the global cache.
-
公开(公告)号：US11586447B2
公开(公告)日：2023-02-21
申请号：US16668003
申请日：2019-10-30
发明人： Cheng Fang Wang , Li Cao , Peng Fei Tian , Hong Yi Zhang , Yong Wu , Bin Xu , Qing Li
IPC分类号： G06F9/4401 , G06F9/50
摘要： A method, computer system and computer program product for processing configuration after a cluster migration are provided. In this method, a network booting program is received at a computing node from a management node for a cluster. The cluster includes at least one computing node. An operating system is booted in a memory of the computing node with the received network booting program. Configuration changes are received from the management node, and the configurations in a local storage of the computing node are updated according to the received configuration changes.
-
公开(公告)号：US20220164242A1
公开(公告)日：2022-05-26
申请号：US17102581
申请日：2020-11-24
发明人： Guang Han Sui , Jing Li , Bin Xu , Fei Qi
摘要： A set of workload criteria is determined from a workload associated with a plurality of sources. The workload is divided among a set of workload groups according to the set of workload criteria and a first workload scheduler. A set of edge computing resources is assigned to each workload group within the set according to the set of workload criteria and the set of workload groups. A portion of the workload associated with a subset of the plurality of sources is handled by a first subset of edge computing resources and a second workload scheduler, where the subset of sources is associated with a first workload group. The handling includes balancing, by the second workload scheduler, the portion of the workload among the subset of sources. The handled workload is reported to a control center.
-
公开(公告)号：US11054925B2
公开(公告)日：2021-07-06
申请号：US16256621
申请日：2019-01-24
发明人： Bin Xu , Yin Xia , Lu Fu , Lei Pan , Xiao Lin Sun
IPC分类号： G06F3/0488 , G06F3/041 , G06F9/30 , B60K37/06 , B60K35/00
摘要： A computer-implemented method, a computer system and a computer program product that facilitate adjusting screen sensitivity of a touch screen are proposed. The computer-implemented method comprises: determining, by a device operatively coupled to one or more processing units, one or more operational areas for an interface of an application running on a touch screen device; and determining, by the device, a screen sensitivity for each of the one or more operational areas respectively.
-
公开(公告)号：US10834543B2
公开(公告)日：2020-11-10
申请号：US16199861
申请日：2018-11-26
发明人： Yin Xia , Lu Fu , Zhang Yu Lin , Lei Pan , Jie Hu , Bin Xu , Xiao Lin Sun
摘要： Initiating a communication group of devices using device vibration includes encoding a message into a vibration signal using an encoder in a master device, the message including a connection request. A vibration pattern is emitted using a vibration motor by controlling the vibration motor to vibrate with a pattern corresponding to modulations of the vibration signal to send the message through a medium in contact with the master device. A response vibration pattern is received from responding devices using a sensor, the response vibration pattern carrying a response message. The response vibration pattern is decoded with a decoder of the master device to extract the response message from the response vibration pattern. A communication group is established at a host according to the response message for communication between the master device and the responding devices.
-
-
-
-
-
-
-
-
-
搜索结果
24 条记录 (耗时 0.019 秒)
