-
公开(公告)号：US20130103866A1
公开(公告)日：2013-04-25
申请号：US13715402
申请日：2012-12-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Zhihong Gao , Ke Li
IPC: G06F13/42
CPC classification number: G06F13/385 , G06F3/0601 , G06F3/0628 , G06F13/105 , G06F13/20 , G06F13/38 , G06F13/382 , G06F13/40 , G06F13/4004 , G06F13/4009 , G06F13/4045 , G06F13/4063 , G06F13/4221 , G06F13/4265 , G06F13/4282 , G06F2213/0026 , G06F2213/0028 , G06F2213/0036 , H04L12/4633 , H04L2212/00
Abstract: A method, device, and system for packet transmission on the PCIE bus according to the embodiments of the present invention, a SCSI protocol packet is encapsulated to obtain an encapsulated SCSI protocol packet, and the encapsulated SCSI protocol packet is carried in a PCIE data packet, and then the PCIE data packet carrying the encapsulated SCSI protocol packet is transmitted to the receiver device through the PCIE bus. Thereby, transmission of SCSI protocol packets is implemented on the PCIE bus, and any devices interconnected through the PCIE bus can operate each other through SCSI protocol packets with a high data transmission bandwidth and high processing speed, without requiring a specific physical device or adapter to perform protocol conversion.
Abstract translation: 根据本发明的实施例的PCIE总线上的分组传输的方法，设备和系统，封装了SCSI协议分组以获得封装的SCSI协议分组，并且封装的SCSI协议分组被携带在PCIE数据分组中 ，然后携带封装的SCSI协议分组的PCIE数据分组通过PCIE总线传输到接收机设备。 因此，在PCIE总线上实现SCSI协议分组的传输，并且通过PCIE总线互连的任何设备可以通过具有高数据传输带宽和高处理速度的SCSI协议分组彼此操作，而不需要特定的物理设备或适配器 执行协议转换。
-
公开(公告)号：US20240020005A1
公开(公告)日：2024-01-18
申请号：US18475849
申请日：2023-09-27
Applicant: Huawei Technologies Co., Ltd.
Inventor： Bang Liu , Kai Zhu , Ke Li , Wen Yang , Jianqiang Shen
IPC: G06F3/06
CPC classification number: G06F3/0608 , G06F3/0641 , G06F3/0673
Abstract: A data compression method includes providing one or more data block sets, where each data block set includes a plurality of data blocks with a same fingerprint; providing one or more compression groups based on a similarity degree between a plurality of data blocks included in each data block set, where one compression group includes a plurality of similar data blocks, the plurality of similar data blocks are a subset of data blocks included in the one or more data block sets, and a similarity degree between the plurality of similar data blocks meets a specific similarity condition; and compressing the plurality of similar data blocks included in the compression group.
-
公开(公告)号：US09117033B2
公开(公告)日：2015-08-25
申请号：US13715402
申请日：2012-12-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Zhihong Gao , Ke Li
CPC classification number: G06F13/385 , G06F3/0601 , G06F3/0628 , G06F13/105 , G06F13/20 , G06F13/38 , G06F13/382 , G06F13/40 , G06F13/4004 , G06F13/4009 , G06F13/4045 , G06F13/4063 , G06F13/4221 , G06F13/4265 , G06F13/4282 , G06F2213/0026 , G06F2213/0028 , G06F2213/0036 , H04L12/4633 , H04L2212/00
Abstract: A method, device, and system for packet transmission on the PCIE bus according to the embodiments of the present invention, a SCSI protocol packet is encapsulated to obtain an encapsulated SCSI protocol packet, and the encapsulated SCSI protocol packet is carried in a PCIE data packet, and then the PCIE data packet carrying the encapsulated SCSI protocol packet is transmitted to the receiver device through the PCIE bus. Thereby, transmission of SCSI protocol packets is implemented on the PCIE bus, and any devices interconnected through the PCIE bus can operate each other through SCSI protocol packets with a high data transmission bandwidth and high processing speed, without requiring a specific physical device or adapter to perform protocol conversion.
Abstract translation: 根据本发明的实施例的PCIE总线上的分组传输的方法，设备和系统，封装了SCSI协议分组以获得封装的SCSI协议分组，并且封装的SCSI协议分组被携带在PCIE数据分组中 ，然后携带封装的SCSI协议分组的PCIE数据分组通过PCIE总线传输到接收机设备。 因此，在PCIE总线上实现SCSI协议分组的传输，并且通过PCIE总线互连的任何设备可以通过具有高数据传输带宽和高处理速度的SCSI协议分组彼此操作，而不需要特定的物理设备或适配器 执行协议转换。
-
Patent Agency Ranking
公开(公告)号：US11593916B2
公开(公告)日：2023-02-28
申请号：US17029554
申请日：2020-09-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Chunfeng Yao , Bailan Feng , Bo Yan , Ke Li , Bahetiyaer Bare , Li Qian
IPC: G06T3/40 , G06V10/48 , G06V10/44 , G06V10/764 , G06V10/82
Abstract: An image super-resolution method includes preprocessing the low-resolution image to obtain a vertical gradient map, a horizontal gradient map, and a luminance map, which are used as three different dimensions of information to constitute a to-be-input feature map, performing size conversion on the to-be-input feature map to obtain an input feature map, performing nonlinear transformation on the input feature map to obtain an input feature map obtained after the nonlinear transformation, and performing weighted processing on the input feature map and the input feature map obtained after the nonlinear transformation, to obtain an output feature map, performing size conversion on the output feature map to obtain a residual map, and combining the low-resolution image and the residual map to obtain a high-resolution image.
-
公开(公告)号：US20210004935A1
公开(公告)日：2021-01-07
申请号：US17029554
申请日：2020-09-23
Applicant: Huawei Technologies Co., Ltd.
Inventor： Chunfeng Yao , Bailan Feng , Bo Yan , Ke Li , Bahetiyaer Bare , Li Qian
Abstract: An image super-resolution method includes preprocessing the low-resolution image to obtain a vertical gradient map, a horizontal gradient map, and a luminance map, which are used as three different dimensions of information to constitute a to-be-input feature map, performing size conversion on the to-be-input feature map to obtain an input feature map, performing nonlinear transformation on the input feature map to obtain an input feature map obtained after the nonlinear transformation, and performing weighted processing on the input feature map and the input feature map obtained after the nonlinear transformation, to obtain an output feature map, performing size conversion on the output feature map to obtain a residual map, and combining the low-resolution image and the residual map to obtain a high-resolution image.
-
公开(公告)号：US09641396B2
公开(公告)日：2017-05-02
申请号：US14180087
申请日：2014-02-13
Applicant: Huawei Technologies Co., Ltd.
IPC: H04L12/24 , H04L12/42 , H04L12/46 , H04L12/437 , H04L12/26 , H04L12/751
CPC classification number: H04L41/12 , H04L12/42 , H04L12/437 , H04L12/4675 , H04L43/0811 , H04L45/02
Abstract: Embodiments of the present invention disclose a packet processing method and system. In the method in the embodiment of the present invention, because a root node configures different control VLANs for any two rings that have an adjacent edge in an area, different control VLANs are used to transmit a protocol packet in a ring that has its own control VLAN configured. The method and system may be applied to a ring network of a metro Ethernet to provide multi-path protection and implement rapid convergence of service switchover. In addition, a network topology structure is not limited to a network topology with a single ring or only two intersecting points, and may be applied to all network topology situations.
-
公开(公告)号：US20150095220A1
公开(公告)日：2015-04-02
申请号：US14569108
申请日：2014-12-12
Applicant: Huawei Technologies Co., Ltd.
Inventor： Qi Chen , Ke Li , Dingsheng Xue , Heng Jiang
IPC: G06Q20/38
Abstract: Embodiments of the present invention disclose a method and an apparatus for transaction processing. The method includes: receiving a transaction request, determining, when it is determined that a real-time account book is undergoing compute-intensive transaction processing, whether an account record of an account on which a transaction is to be performed exists in a temporary account book, and if yes, processing the transaction request based on the account record, and updating the account record in the temporary account book according to a processing result, and if no, reading the account record from the real-time account book, processing the transaction request based on the account record, and recording, in the temporary account book, the updated account record according to a processing result; and updating, after the transaction processing is complete, the real-time account book according to the temporary account book, and deleting the account record after the updating.
Abstract translation: 本发明的实施例公开了一种用于事务处理的方法和装置。 该方法包括：接收交易请求，确定何时确定实时账簿正在进行计算密集型交易处理，是否在临时账户中存在要进行交易的账户的账户记录 书，如果是，则根据账户记录处理交易请求，并根据处理结果更新临时账簿中的账户记录，如果否，则从实时账簿读取账户记录，处理 根据账户记录的交易请求，并根据处理结果在临时账簿中记录更新的账户记录; 并在交易处理完成之后根据临时账簿更新实时账簿，并在更新后删除该账户记录。
-
公开(公告)号：US20140169155A1
公开(公告)日：2014-06-19
申请号：US14180087
申请日：2014-02-13
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
IPC: H04L12/24 , H04L12/437 , H04L12/26
CPC classification number: H04L41/12 , H04L12/42 , H04L12/437 , H04L12/4675 , H04L43/0811 , H04L45/02
Abstract: Embodiments of the present invention disclose a packet processing method and system. In the method in the embodiment of the present invention, because a root node configures different control VLANs for any two rings that have an adjacent edge in an area, different control VLANs are used to transmit a protocol packet in a ring that has its own control VLAN configured. The method and system may be applied to a ring network of a metro Ethernet to provide multi-path protection and implement rapid convergence of service switchover. In addition, a network topology structure is not limited to a network topology with a single ring or only two intersecting points, and may be applied to all network topology situations.
Abstract translation: 本发明的实施例公开了一种分组处理方法和系统。 在本发明实施例的方法中，由于根节点对于区域中具有相邻边缘的任何两个环配置不同的控制VLAN，所以使用不同的控制VLAN在具有自己控制的环中传输协议报文 配置VLAN 该方法和系统可以应用于城域以太网的环网，提供多路径保护，实现业务切换的快速收敛。 此外，网络拓扑结构不限于具有单环或仅两个相交点的网络拓扑，并且可以应用于所有网络拓扑情况。
-
-
-
-
-
-
-
Search Results
8
records
(took 0.019 seconds)
