-
公开(公告)号：US10530326B2
公开(公告)日：2020-01-07
申请号：US15796239
申请日：2017-10-27
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiaofeng Zhang , Lixia Qiu , Ke Chen
Abstract: An input/output apparatus of a multiplexer is provided, including: a main tap and at least two branch taps of the main tap, where each of the at least two branch taps is configured to couple to a different resonant cavity in the multiplexer, and the at least two branch taps include a first branch tap and a second branch tap; a coupling polarity of the first branch tap is opposite to that of the second branch tap; and a coupling calculation frequency of the second branch tap is closest to a coupling calculation frequency of the first branch tap. The input/output apparatus of the multiplexer enables two channels with closest frequencies to use different coupling polarities. Because the coupling polarities are different, signals naturally do not interfere with each other, and signal interference between channels is eliminated in principle. The embodiments of the present disclosure further provide a corresponding multiplexer.
-
公开(公告)号：US09780998B2
公开(公告)日：2017-10-03
申请号：US14676191
申请日：2015-04-01
Applicant: Huawei Technologies Co., Ltd.
Inventor： Lijun Li , Xiaofeng Zhang
IPC: H04L12/24 , G06F9/455 , H04L12/721 , H04L12/713 , H04L29/12
CPC classification number: H04L41/0806 , G06F9/45558 , G06F2009/45595 , H04L41/08 , H04L41/0803 , H04L41/0843 , H04L41/0896 , H04L45/38 , H04L45/586 , H04L61/2038 , H04L61/6004
Abstract: A method and an apparatus for managing one or more physical network interface cards and a physical host are provided. One or more virtual network interface cards are created, where each of the virtual network interface cards has a standard network interface card feature and an operation interface; the one or more virtual network interface cards are separately associated with one or more function modules of the physical network interface cards; and the physical network interface cards are managed by managing the one or more virtual network interface cards. In this way, differences in underlying hardware are shielded for an upper layer, and convenient and efficient centralized management are provided, thereby further improving network resource utilization.
-
公开(公告)号：US09223712B2
公开(公告)日：2015-12-29
申请号：US13968714
申请日：2013-08-16
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiaofeng Zhang
CPC classification number: G06F12/0866 , G06F12/084 , G06F12/0842 , G06F12/0864 , G06F12/0871 , G06F2212/222 , G06F2212/261
Abstract: A data cache method, device, and system in a multi-node system are provided. The method includes: dividing a cache area of a cache medium into multiple sub-areas, where each sub-area is corresponding to a node in the system; dividing each of the sub-areas into a thread cache area and a global cache area; when a process reads a file, detecting a read frequency of the file; when the read frequency of the file is greater than a first threshold and the size of the file does not exceed a second threshold, caching the file in the thread cache area; or when the read frequency of the file is greater than the first threshold and the size of the file exceeds the second threshold, caching the file in the global cache area. Thus overheads of remote access of a system are reduced, and I/O performance of the system is improved.
Abstract translation: 提供了多节点系统中的数据高速缓存方法，设备和系统。 该方法包括：将高速缓存介质的高速缓存区域划分为多个子区域，其中每个子区域对应于系统中的节点; 将每个子区域划分为线程高速缓存区域和全局缓存区域; 当进程读取文件时，检测文件的读取频率; 当文件的读取频率大于第一阈值并且文件的大小不超过第二阈值时，将文件高速缓存在线程高速缓存区域中; 或者当文件的读取频率大于第一阈值并且文件的大小超过第二阈值时，将文件高速缓存在全局缓存区域中。 因此，减少了系统的远程访问开销，提高了系统的I / O性能。
-
24.发明申请公开(公告)号：US20150113114A1
公开(公告)日：2015-04-23
申请号：US14584597
申请日：2014-12-29
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiaofeng Zhang , Lijun Li
IPC: H04L12/24
CPC classification number: H04L41/20 , G06F13/385
Abstract: The present invention provides a network interface adapter registration method, driver, and server, where the method includes: registering, by a driver of a server, a network interface adapter with a kernel of the server as a physical network device; and registering, by the driver, apart of or all hardware queue receiving and sending groups of the network interface adapter with the kernel of the server as virtual network devices, where the physical network device is configured to manage the network interface adapter and all the virtual network devices, and each of the virtual network devices is configured to receive or send data of an application or a chip in the server. The foregoing method resolves a problem in the prior art that management and a direct operation cannot be performed on a single hardware queue of the network interface adapter.
Abstract translation: 本发明提供了一种网络接口适配器注册方法，驱动程序和服务器，其中所述方法包括：由服务器的驱动程序将网络接口适配器与服务器的内核注册为物理网络设备; 并且由所述驱动程序将所述网络接口适配器的所有硬件队列接收和发送组与所述服务器的内核作为虚拟网络设备进行注册，其中所述物理网络设备被配置为管理所述网络接口适配器和所有虚拟 网络设备，并且每个虚拟网络设备被配置为在服务器中接收或发送应用或芯片的数据。 上述方法解决了现有技术中的问题，即管理和直接操作不能在网络接口适配器的单个硬件队列上执行。
-
25.发明申请METHOD FOR MANAGING A PROCESSOR, LOCK CONTENTION MANAGEMENT APPARATUS, AND COMPUTER SYSTEM 有权管理处理器，锁定管理装置和计算机系统的方法公开(公告)号：US20140250248A1
公开(公告)日：2014-09-04
申请号：US14274294
申请日：2014-05-09
Applicant: Huawei Technologies Co., LTD.
Inventor： Xiaofeng Zhang , Han Zheng
IPC: G06F9/30
CPC classification number: G06F9/3009 , G06F9/524
Abstract: A method for managing a processor includes: obtaining an online request of a processor of a computer system; collecting lock contention information of the computer system if a lock contention status flag indicates a non-lock thrashing status; determining whether the computer system is in a lock thrashing status according to the lock contention information; and accepting the online request if it is determined that the computer system is in a non-lock thrashing status. By using the management method according to embodiments of the present application, processor performance degradation and a waste of idle processor resources that are caused by the case that the computer system is in a lock thrashing status are prevented, thereby improving utilization efficiency of processor resources and promoting overall performance of the computer system.
Abstract translation: 一种用于管理处理器的方法包括：获得计算机系统的处理器的在线请求; 如果锁争用状态标志指示非锁定颠簸状态，则收集计算机系统的锁争用信息; 根据锁争用信息确定计算机系统是否处于锁定状态; 如果确定计算机系统处于非锁定状态，则接受该在线请求。 通过使用根据本申请的实施例的管理方法，防止由计算机系统处于锁定状态的情况引起的处理器性能下降和空闲处理器资源的浪费，从而提高处理器资源的利用效率， 促进电脑系统的整体表现。
-
Patent Agency Ranking
公开(公告)号：US20240224300A1
公开(公告)日：2024-07-04
申请号：US18604903
申请日：2024-03-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Meng Jin , Yao Zhao , Jingyun Zhang , Dongzhe Sun , Yumin Li , Xudong Zhu , Hai Lian , Guanjun Ni , Xiaofeng Zhang
Abstract: A method includes: A basic application layer sends first information that includes a first business requirement and a first port to a basic service layer. The basic service layer sends second information that includes the first business requirement, a first broadcast business channel, and a logical channel type to an access layer. The first broadcast business channel is determined based on the first information. The access layer supports a first access technology that is determined, based on the first business requirement, from a plurality of access technologies supported by the access layer. The access layer sends a first mapping relationship that indicates the first broadcast business channel and a first logical channel to the basic service layer. The first logical channel is a logical channel that supports the first access technology and that is determined based on the second information.
-
公开(公告)号：US10153839B2
公开(公告)日：2018-12-11
申请号：US15581809
申请日：2017-04-28
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xiaofeng Zhang , Guikai Peng
IPC: H04B10/25 , H04L27/20 , H04L27/26 , H04B10/079 , H04L5/00 , H04B10/272 , H04J3/06
Abstract: A terminal device registration method and a device, where the method includes sending upstream registration window information to a terminal device, where the upstream registration window information indicates a starting position of an upstream registration window to the terminal device, receiving an upstream access signal sent by the terminal device from the starting position of the upstream registration window, where the upstream access signal includes a correlation sequence symbol and at least one orthogonal frequency division multiplexing (OFDM) symbol following the correlation sequence symbol, the correlation sequence symbol is constituted by a first sequence that meets a preset condition, and the at least one OFDM symbol modulates access information by means of differential phase modulation in a frequency domain, and performing upstream ranging according to the starting position of the upstream registration window and the correlation sequence symbol.
-
公开(公告)号：US20180145767A1
公开(公告)日：2018-05-24
申请号：US15857019
申请日：2017-12-28
Applicant: Huawei Technologies Co., Ltd.
Inventor： Liming Fang , Lei Zhou , Meng Sui , Xiaofeng Zhang
CPC classification number: H04B10/6162 , H04B10/2504 , H04B10/60 , H04J13/16
Abstract: An apparatus for despreading in an optical domain configured to split a received optical signal into a first optical signal and a second optical signal, perform phase deflection on the second optical signal, output a third optical signal, perform phase deflection on the first optical signal and the third optical signal, output a fourth optical signal and a fifth optical signal to a balanced receiver, and superimpose the fourth optical signal and the fifth optical signal to generate a first electrical signal. A multiplication operation in conventional code division multiple access (CDMA) despreading is transferred from an electrical domain to an optical domain such that a chip rate can be easily raised to 20 gigahertz (GHz) or even to 25 GHz, a maximum rate of 100 gigabits per second (Gbps) can be provided in a single wavelength, and a user requirement for high bandwidth can be met.
-
公开(公告)号：US20240107470A1
公开(公告)日：2024-03-28
申请号：US18254057
申请日：2021-11-22
Applicant: Huawei Technologies Co., Ltd.
Inventor： Sulin Yang , Xiaofeng Zhang
CPC classification number: H04W56/0015 , H04J3/0638 , H04J3/0682
Abstract: A time synchronization method includes obtaining a first BLUETOOTH packet from a master device, where the first BLUETOOTH packet carries first time stamp information, and the first time stamp information indicates a sending moment t1 that is of the first BLUETOOTH packet and that is determined based on a clock of the master device; and correcting a local time of a slave device based on the first time stamp information.
-
公开(公告)号：US10171175B2
公开(公告)日：2019-01-01
申请号：US15857019
申请日：2017-12-28
Applicant: Huawei Technologies Co., Ltd.
Inventor： Liming Fang , Lei Zhou , Meng Sui , Xiaofeng Zhang
Abstract: An apparatus for despreading in an optical domain configured to split a received optical signal into a first optical signal and a second optical signal, perform phase deflection on the second optical signal, output a third optical signal, perform phase deflection on the first optical signal and the third optical signal, output a fourth optical signal and a fifth optical signal to a balanced receiver, and superimpose the fourth optical signal and the fifth optical signal to generate a first electrical signal. A multiplication operation in conventional code division multiple access (CDMA) despreading is transferred from an electrical domain to an optical domain such that a chip rate can be easily raised to 20 gigahertz (GHz) or even to 25 GHz, a maximum rate of 100 gigabits per second (Gbps) can be provided in a single wavelength, and a user requirement for high bandwidth can be met.
-
-
-
-
-
-
-
-
-
Search Results
35
records
(took 0.018 seconds)
