89results about How to "Reduce Interrupt Latency" patented technology

In one embodiment, an interrupt controller may implement an interrupt distribution scheme for distributing interrupts among multiple processors. The scheme may take into account various processor state in determining which processor should receive a given interrupt. For example, the processor state may include whether or not the processor is in a sleep state, whether or not interrupts are enabled, whether or not the processor has responded to previous interrupts, etc. The interrupt controller may implement timeout mechanisms to detect that an interrupt is being delayed (e.g. after being offered to a processor). The interrupt may be re-evaluated at the expiration of a timeout, and potentially offered to another processor. The interrupt controller may be configured to automatically, and atomically, mask an interrupt in response to delivering an interrupt vector for the interrupt to a responding processor.

An interrupt processing technique is provided where an interrupt message is sent to an interrupt controller of a processor in response to an interrupt request from an individual device. The interrupt message comprises a memory address and interrupt status information. The memory address is specifically allocated to the device that has issued the interrupt request. The interrupt status information indicates an interrupt status of the device. An interrupt table that is stored in the memory is updated by the interrupt controller using the interrupt status information comprised in the interrupt message. The interrupt table holds device specific interrupt statuses. Updating the interrupt table comprises addressing the memory using the memory address in the interrupt message.

Disclosed are management method, device and equipment for mobile switching. When applied to a source auxiliary base station, the management method comprises the steps of sending a switching request message to the target base station when it is determined to switch set user equipment to a target base station which is different from the source auxiliary base station; using signaling radio bearer (SCG SRB) on the source auxiliary base station side to issue a switching command message to the UE when the switching request confirmation message sent by the target base station is received, and triggering the UE to carry out random access attempt on serving cells under the target base station. In the embodiment of the invention, a secondary node (SN) can also partially participate in switching management of the UE, so that signaling expenditure and data interruption delay of the whole switching process are reduced, and the RRM processing load related to UE mobility management, such as a RRM measurement algorithm, a switching execution and the like, by master node (MN) is reduced.

This invention discloses a method to realize switching, applying to the network including at least two evolution base stations and Access Gateway, and user terminals switches from source to target base station, which includes: after switching preparatory stage, the sources evolution base station informs Access Gateway to stop sending it data. The source evolution base station sends the order of switching to user terminals and judges whether there is more data needed to send in its own cache, if so, the source evolution base station transmits its own cache data to the target one for continuous switching, and if not, conducts the follow-up switching processing.

A method of processing data comprising: processing a function using a processor operable to perform a plurality of functions, the processor having interrupts enabled; receiving an interrupt at the processor; suspending processing of the function; accessing at least one control parameter, the at least one control parameter indicating whether processing of the function should be resumed from the point where it was interrupted or whether the function should be repeated following the interrupt; following completion of the interrupt continuing processing of the function either at a start of the function or at a point at which it was interrupted dependent upon the control parameter. A function being an application, a thread, a system software routine, or multiple processing steps defined by software.

The invention discloses a method for the fault treatment of an access session control server, which comprises the following steps that: a user data server performs fault detection of the access session controller server in a network; when the user data server detects that the access session control server goes wrong, the user data server selects at least one access session control server not goingwrong; and the selected access session control server performs access treatment of the original user bound to the access session control server going wrong. The invention also discloses the user dataserver, the access session control server and a network system. The method, the user data server, the access session control server and the network system can discover the faults of the access session control server in the network in time, and switch services to other access session control servers not going wrong in the network, reduce the service delay, improve the user experience, can fully utilize the access session control server in the network to perform the access treatment on the user, and have high utilization rate of network resources, flexible capacity configuration and good expandability.

The invention discloses a method for dynamically distributing isomerism storage resources on an instruction parcel based on a virtual memory mechanism, wherein the storage resources on the instruction parcel comprising command Cache and command SPM are fully utilized. In the invention, time slot analyzing method is adopted to analyze the time and space distribution hit and missing by command Cache caused by high frequency to obtain time slot access map of the command Cache and perform mathematical abstraction to the time slot access map. According to energy consumption target function and performance target function, the program command parts needing optimization in different time slots are selected by utilizing integer non-linear programming method, different program phases are divided by utilizing a clock module, and when clock is suspended, command pages with optimizing value are dynamically remapped into a command SPM memory by utilizing a command SPM controller, thus avoiding additional access and memory caused by command Cache conflict and obtaining energy consumption gain from once access energy consumption difference of Cache and SPM. In the method, isomerism storage on instruction parcel is fully utilized, thus reducing system energy consumption and improving system performance.

The present invention provides a data processing apparatus and method for saving return state. The data processing apparatus comprises a processing unit for executing data processing instructions, the processing unit having a plurality of modes of operation, with each mode of operation having a corresponding stack for storing data associated with that mode. The processing unit is responsive to a return state data processing instruction to write return state data of the processing unit from its current mode of operation to a stack corresponding to a different mode of operation to the current mode of operation. This approach significantly reduces code size and improves interrupt latency over known prior art techniques.

An interrupt processing technique is provided where an interrupt message is sent to an interrupt controller of a processor in response to an interrupt request from an individual device. The interrupt message comprises a memory address and interrupt status information. The memory address is specifically allocated to the device that has issued the interrupt request. The interrupt status information indicates an interrupt status of the device. An interrupt table that is stored in the memory is updated by the interrupt controller using the interrupt status information comprised in the interrupt message. The interrupt table holds device specific interrupt statuses. Updating the interrupt table comprises addressing the memory using the memory address in the interrupt message.

A system and a method for reducing interrupt latency is described. The system includes a first interrupt source configured to generate a first interrupt, a second interrupt source configured to generate a second interrupt, and a processor. The processor includes a shadow set that stores data used to service the first interrupt. The processor receives the second interrupt and receives a designation of the shadow set to service the second interrupt. The processor determines, based on a dedicated bit, whether the shadow set is used to service the first interrupt upon receiving the second interrupt.

Disclosed is a hybrid virtualization method for an interrupt controller in nested virtualized environment, which can reduce guest interrupt latency. A hybrid virtualization method includes operating a Virtual Machine Manager (VMM) which enables a program executed on a host and a program executed on a guest to be simultaneously used, providing, by the VMM, a virtual interrupt configuration register to the guest, and selectively utilizing full virtualization and partial virtualization. Full virtualization is used when guests which are running simultaneously request the same interrupt. In this case, the interrupt is trapped by the VMM before being injected to the different guests. Partial virtualization allows a guest to directly handle incoming interrupt and avoids expensive traps to the hypervisor to reduce the latency. This virtualization technique can be used by any kind of VMM which is physical hypervisor or virtual hypervisor for processing interrupts of their respective guests.

The invention discloses a direct interrupt submitting method based on a hardware-assisted technique and virtual CPU running states. The method is characterized by comprising the steps that after SRIOV direct allocation equipment generates a physical interrupt for a virtual machine through an MSI / MSI-X mechanism, the physical interrupt is directly submitted to a virtual CPU which runs currently or is dispatched firstly by analyzing running states and historical running data of all current virtual CPUs of the virtual machine through an APICv hardware technique and a Posted Interrupt hardware technique on the condition that a VM exit is not caused, therefore, a context exchange load brought by the VM exit and an interrupt time delay caused by ununiform virtual CPU dispatching are avoided, the interrupt processing efficiency in a virtual environment is effectively improved, and the overall performance is promoted.

A handover method of a target base station is disclosed in the present invention, including: after a source base station to which a terminal belongs transmitting a handover request message to at least one alternate target base station, every alternate target base station notifying the source base station of a load state parameter, and the source base station determining one target base station according to the load state parameter of every alternate target base station and indicating the terminal to perform handover to the target base station. A base station is also provided in the present invention, including: a handover request transmission module, a handover request response reception module, a target base station determination module and a handover request response transmission module. The present invention avoids the re-request process of the base station when the handover request fails, and can improve the handover success ratio.

The invention discloses a method of transferring multicast data, a method for updating a multicast tree, a system and a device thereof, the main technical solution comprise: a first Mobile Access Gateway (MAG) receives pre-handover message transmitted from a Multicast Source before it handovers from the current accessed first MAG to the second MAG; the first MAG according to the second MAG ID carried in the pre-handover message, establishes a bidirectional tunnel with the second MAG; and the first MAG multicasts multicast data from a Multicast Source, based on the established bidirectional tunnel and the definitive post-handover multicast mode which is the multicast mode adopted by the Multicast Source after handovers to the second MAG. Adopting the technical solution, by previously establishing bidirectional tunnel, the first MAG transfers multicast data by the established directional tunnel when performing binding, updating and authenticating between the Multicast Source and the second MAG, which reduces the interruption delay of multicast service due to the switching among MAGs by Multicast Source.

The invention relates to a resource management method, a base station and a system, and belongs to the technical field of communication. The method in the embodiment of the invention comprises the following steps that: the base station receives first uplink data or first acknowledgment information sent by user equipment (UE); the base station decodes the first uplink data or first acknowledgment information according to the format of periodic indication information contained in the first uplink data or first acknowledgment information; and if the first uplink data or first acknowledgment information is successfully decoded, the base station determines that the first uplink data or first acknowledgment information contains the periodic indication information and puts periodic resources corresponding to the periodic indication information contained in the first uplink data or first acknowledgment information into effect. Through the technical scheme, the problem that data is wrongly retransmitted because the base station and the UE put the periodic resources corresponding to the periodic indication information into effect asynchronously in the prior art is solved, so that interrupt time delay is reduced.

An inter-cell switching method comprises the following steps: when a wireless network controller determines to switch user equipment from a service Node B to an object Node B, the wireless network controller notifies an activation time to the service Node B and the object Node B; the service Node B determines a specified time quantum; when the time of a time quantum specified in advance relative to the activation time arrives, the service Node B notifies the wireless network controller to stop transmitting data to the service Node B, and dispatches the data stored in the buffer area of the service Node B to the user equipment; when the activation time arrives, the service Node B empties the data stored in the buffer area and correlative to the user equipment, and the object Node B provides the user equipment with data. In addition, the invention also discloses an inter-cell switching device. The inter-cell switching method, which can reduce data retransmission to a large extent, ensures normal receiving of data of UE during switching and reduces data interruption time delay, thereby meeting the requirements of realtime service for QoS.

In one embodiment, an interrupt controller may implement an interrupt distribution scheme for distributing interrupts among multiple processors. The scheme may take into account various processor state in determining which processor should receive a given interrupt. For example, the processor state may include whether or not the processor is in a sleep state, whether or not interrupts are enabled, whether or not the processor has responded to previous interrupts, etc. The interrupt controller may implement timeout mechanisms to detect that an interrupt is being delayed (e.g. after being offered to a processor). The interrupt may be re-evaluated at the expiration of a timeout, and potentially offered to another processor. The interrupt controller may be configured to automatically, and atomically, mask an interrupt in response to delivering an interrupt vector for the interrupt to a responding processor.

The invention discloses a downlink data sending method and a base station, wherein the method comprises the following steps that: uplink dedicated information sent by user equipment (UE) corresponding to a user entity is received by the user entity of a base station user plane, and the uplink dedicated information is used for indicating that the UE is successfully accessed to the base station; according to triggering of the uplink dedicated information, the downlink data is dispatched and sent to the UE by the user entity of the base station user plane. By means of the invention, the effects of decreasing interrupt delay of the user plane during a switchover process and improving user experience during the switchover process can be achieved.

The invention provides a Xen-based VCPU multi-core real-time scheduling algorithm. The Xen-based VCPU multi-core real-time scheduling algorithm is characterized in that a static priority is distributed for all operating systems on a Xen platform, VCPUs which belong to the same operating system have identical static priority, and VCPUs with high static priority in the systems can respond in priority; one interruption identification is maintained for each VCPU in real time and used for recording the number of unfinished interruption so as to guarantee that the VCPU which urgently needs responding interruption responds in priority, and accordingly the responding speed of the real-time operating systems on the Xen platform to interruption and task switching, and instantaneity is enhanced.

In one embodiment, an interrupt controller may implement an interrupt distribution scheme for distributing interrupts among multiple processors. The scheme may take into account various processor state in determining which processor should receive a given interrupt. For example, the processor state may include whether or not the processor is in a sleep state, whether or not interrupts are enabled, whether or not the processor has responded to previous interrupts, etc. The interrupt controller may implement timeout mechanisms to detect that an interrupt is being delayed (e.g. after being offered to a processor). The interrupt may be re-evaluated at the expiration of a timeout, and potentially offered to another processor. The interrupt controller may be configured to automatically, and atomically, mask an interrupt in response to delivering an interrupt vector for the interrupt to a responding processor.

The present invention provides a processing method of the layer-three switching and the system, including the steps as follows: gaining the information at the network side which generates at the terminal or needs generating the layer-three switching; informing the terminal generate or need generating layer-three switching; gaining a new IP address of the service network. The present invention can shorten the time delay of the L3 switching, reduce the wireless hollow flow rate and accelerates the process of terminal finding the L3 switching, remarkably shortening the break time delay of the services and comparatively improving the network performance and service life in a large scale.

The embodiment of the invention provides a switching management method for a 5G ultra-dense network. The method comprises the steps: starting an inactive timer for a terminal which has no uplink and downlink data transmission and is in a connection state, and stopping timing when the uplink and downlink data transmission of the terminal is detected; determining whether the terminal has a switchingrequirement or not under the condition that the inactive timer is not overtime; in response to a switching demand of the terminal, judging whether the inactive timer stops timing or not; under the condition that the inactive timer does not stop timing, switching processing or state conversion processing is carried out on the terminal according to the data arrival probability of the terminal before timeout of the inactive timer, the switching cost of the terminal and the state conversion cost; and under the condition that the inactive timer stops timing, performing switching processing or state conversion processing on the terminal according to the switching cost and the state conversion cost of the terminal. According to the embodiment of the invention, unnecessary switching is avoided, and the switching frequency and interruption time delay in the 5G ultra-dense network are reduced.

In one embodiment, an interrupt controller may implement an interrupt distribution scheme for distributing interrupts among multiple processors. The scheme may take into account various processor state in determining which processor should receive a given interrupt. For example, the processor state may include whether or not the processor is in a sleep state, whether or not interrupts are enabled, whether or not the processor has responded to previous interrupts, etc. The interrupt controller may implement timeout mechanisms to detect that an interrupt is being delayed (e.g. after being offered to a processor). The interrupt may be re-evaluated at the expiration of a timeout, and potentially offered to another processor. The interrupt controller may be configured to automatically, and atomically, mask an interrupt in response to delivering an interrupt vector for the interrupt to a responding processor.

Disclosed in the present application are a method and apparatus for notification of group communication information. The method of the present application comprises: base stations exchange information concerning the MBSFN area to which the respective serving cells of the base stations belong; on the basis of the neighboring cells of a current serving cell of a terminal and the received MBSFN area information, a base station sends to the terminal the MBSFN area information of the neighboring cells of the current serving cell of the terminal, the terminal being a terminal served by the current serving cell. Use of the present invention enables notification of group communication information on the basis of MBMS network architecture, thus providing a guarantee to the requirement of service continuity for group communication.

The invention provides a cell control method and device. The method comprises the following steps: controlling a terminal to measure a neighbor cell of a service cell when a T310 timer at a terminal side is started; and determining a fact that the terminal is failed in wireless link occurrence according to the signal of the service cell or the signal of the neighbor cell in the running period of the T310 timer. When the T310 timer is started, the terminal not only measures the service cell but also measures the neighbor cell before the wireless link occurrence is failed, and the speed of judging whether the wireless link is failed is improved; furthermore, the time of reselecting the cell by the terminal is shortened after the wireless link is failed in virtue of the measurement information of the neighbor cell before the wireless link is failed.

The invention provides a protection method for X2 interface switching, which comprises the following steps: S202. an X2 Interface Application Protocol receives a user equipment context release message of an X2 interface control surface, or a Packet Data Convergence Protocol reversely completes one of multiple messages and waits for another message; and S204. an endmarker protection timer is arranged in a target base station through the Packet Data Convergence Protocol, and then started. The method and system provided by the invention solve the problem of redundant cache data, shorten the time delay of the switching service interruption, and enhance the user experience.

The embodiment of the invention relates to the technical field of wireless communication, in particular to a method, system and device for transmitting data in the process of switching access points. The method, system and device for transmitting data are used for solving the problem in the prior art that under the condition of a heterogeneous network, and when the access points are switched, interruption and time delay of a data surface can be increased. The method of the embodiment comprises that a user device determines that all or part of a DRB is reshuffled from one cell to another cell under the condition that RRC connection is not changed, in the process that access point switching is conducted by the user device, data are transmitted through an original data radio bearer, wherein the original data radio bearer is used in the end before access point switching of the data surface. Due to the fact that in the process that access point switching is conducted by the user device, the data are transmitted through the original data radio bearer, so that the interruption and time delay of the data surface when the access points are switched under the condition of the heterogeneous network is reduced, and switching efficiency is further improved, and data transmission time is shortened.

The embodiment of the invention provides a user equipment capability determination method and a node, relates to the technical field of communication, and is used for solving the problem that existingconventional switching UE maintains data connection at a source node and a target node at the same time. The method comprises the steps that in the switching preparation process, a target node receives first information from a source node, wherein the first information comprises at least one of the following information: second information and third information, the second information is used forindicating the available first UE capability allocated to a destination node by the source node in the dual-connection mode, and the third information is used for indicating all capabilities of the UE; and determining the available second UE capability of the destination node according to the first information. The present invention is applied to a scenario in which UE switches from a source nodeto a destination node.

Systems and method for reducing interrupt latency time in a multi-threaded processor. A first interrupt controller is coupled to the multi-threaded processor. A second interrupt controller is configured to communicate a first interrupt and a first vector identifier to the first interrupt controller, wherein the first interrupt controller is configured to process the first interrupt and the first vector identifier and send the processed interrupt to a thread in the multi-threaded processor. Logic is configured to determine when the multi-threaded processor is ready to receive a second interrupt. A dedicated line is used to communicate an indication to the second interrupt controller that the multi-threaded processor is ready to receive the second interrupt.