Abstract: A current integration-based in-memory spiking neural network (SNN) uses charge-domain computation which is naturally compatible with working mechanisms of neurons. In one aspect, silicon-based SRAM cells are included in memory cells of a synaptic array, which can avoid non-idealities caused by resistive NVM materials. Additionally, a modified NVM cell is provided, which benefits from the in-memory SNN architecture design. When SRAM cells are used as memory cells in the synaptic array, post-neuron circuits are designed accordingly so that the in-memory SNN architecture can be used in computation with multi-bit synaptic weights by combining a programmable number of columns. Further, for computation with multi-bit synaptic weights, a circuit is designed to be time-multiplexed for resource sharing to achieve improved area and energy efficiency.

Abstract: A mixed-signal in-memory computing sub-cell only requires 9 transistors for 1-bit multiplication. A computing cell is constructed from a plurality of such sub-cells that share a common computing capacitor and a common transistor. A MAC array for performing MAC operations, includes a plurality of the computing cells each activating the sub-cells therein in a time-multiplexed manner. A differential version of the MAC array provides improved computation error tolerance and an in-memory mixed-signal computing module for digitalizing parallel analog outputs of the MAC array and for performing other tasks in the digital domain. An ADC block in the computing module makes full use of capacitors in the MAC array, allowing the computing module to have a reduced area and suffer from fewer computational errors.

Abstract: A packet forwarding method and apparatus, and a communication network, related to the field of communication technologies. In the solutions provided, a controller may obtain a correspondence between an application-aware identifier of a service flow and a network service required for transmitting the service flow, and deliver the correspondence to a network device. Further, when identifying the service flow as a service flow indicated by the application-aware identifier, the network device may directly forward a packet of the service flow by using the corresponding network service. The controller may establish and deliver the correspondence between the application-aware identifier and the network service, so that the network device can directly forward the service packet of the service flow based on the correspondence. Therefore, flexibility of forwarding the service packet is effectively improved.

Abstract: A data I/O processing method includes obtaining data requested consisting of a plurality of basic data blocks in sequence; grouping the data in sequence to obtain a plurality of segmented data blocks in sequence; sequentially determining whether each segmented data block has a time delay statistical record based on the time for completion of the operation processing of a previous basic data block; in response to the time delay statistical record being present in the segmented data block, setting a waiting time period according to the time delay statistical record; sequentially merging the basic data blocks, which have not been subjected to the operation processing, in the segmented data blocks within the waiting time period until the waiting time period is ended or the merged basic data blocks reach the size of the segmentation unit, and stopping merging; and sending the merged basic data blocks and performing the operation processing.

Abstract: This application provides a route refresh method, apparatus, and system, and relates to the field of communication technologies. In solutions provided in this application, a first network device can send a plurality of first routes to a second network device in a parallel transmission manner, and can send an end indication after determining that the second network device receives the plurality of first routes. Therefore, it can be ensured that in a parallel transmission scenario, the end indication does not reach the second network device earlier than the first routes. This can avoid a problem that a service flow is interrupted because the second network device untimely ages a route that is not refreshed in a routing table.

Abstract: Embodiments of this application disclose a route advertisement method and a device, to improve efficiency of generating a route advertisement message. The method is applied to a network including a first network device and a second network device, and the first network device and the second network device establish a user datagram protocol UDP-based border gateway protocol BGP connection. The method includes: The first network device obtains one or more route sending groups, where each route sending group includes one or more pieces of route information; the first network device separately generates at least one route advertisement message based on each route sending group, the route advertisement message includes the one or more pieces of route information in the route sending group corresponding to the route advertisement message; and the first network device sends the route advertisement message to the second network device through the BGP connection.

Abstract: A method and an apparatus for establishing a BGP peer, a device, and a system. A first network device sends a first packet to a second network device in a UDP manner, where the first packet is used to establish a BGP peer with the second network device; and if the first network device can receive a second packet sent by the second network device in the UDP manner, the first network device establishes a BGP peer relationship with the second network device in response to the received second packet.

Abstract: Distributed ledgered data is stored within a distributed persistent storage system comprising multiple persistent storage systems as distributed ledgered participants. In various embodiments, the distributed ledgered data is maintained using the native capabilities of a persistent storage system. The distributed ledgered data is replicated as persistent data objects in a “ledgered repository of objects” that are replicated at each of the persistent storage systems. Changes at one persistent storage system are recorded within a block in a distributed blockchain that is distributed across each of the other distributed ledgered participants. The other distributed ledgered participants read the changes from the blockchain and apply the changes to the respective replicas at each of the other distributed ledgered participants. Hence, this approach is referred to as blockchain apply. Blockchain apply may be used to replicate the repository objects of various forms of PSSs.

Abstract: The present invention discloses a wavelength-modulable spectrum generator as well as a system and method for measuring concentration of a gas component based thereon. The wavelength-modulable spectrum generator includes a filter plate, a to-be-measured gas box and a light intensity receiving plate. A plate surface of the filter plate is encircled with N filter holes, and a filter lens with a specific refractive index is correspondingly fixedly arranged in each filter hole. A light source mounting position is fixed to a side of an in-light surface of the filter plate. After any light source is mounted at the light source mounting position, lights of the light source irradiate the filter lens. A rotation and deflection driving mechanism is connected with an out-light surface of the filter plate and drives the filter plate to rotate or deflect along the axis according to a preset angle.

Abstract: Disclosed are methods and apparatuses to provide a redo repeater that allows for no data loss protection without the performance impact to the primary database even when a significant geographical distance separates the primary and standby databases. The Repeater is a lightweight entity that receives redo from the primary database with the purpose of redistributing that redo throughout the primary/standby system configuration. The Repeater able to extend no data loss protection and switchover functionality to terminal standby databases even though the primary database does not need to have a direct connection with those destinations.

Abstract: Distributed ledgered data is stored within a distributed persistent storage system comprising multiple persistent storage systems as distributed ledgered participants. In various embodiments, the distributed ledgered data is maintained using the native capabilities of a persistent storage system. The distributed ledgered data is replicated as persistent data objects in a “ledgered repository of objects” that are replicated at each of the persistent storage systems. Changes at one persistent storage system are recorded within a block in a distributed blockchain that is distributed across each of the other distributed ledgered participants. The other distributed ledgered participants read the changes from the blockchain and apply the changes to the respective replicas at each of the other distributed ledgered participants. Hence, this approach is referred to as blockchain apply. Blockchain apply may be used to replicate the repository objects of various forms of PSSs.

Abstract: The present invention discloses a wavelength-modulable spectrum generator as well as a system and method for measuring concentration of a gas component based thereon. The wavelength-modulable spectrum generator includes a filter plate, a to-be-measured gas box and a light intensity receiving plate. A plate surface of the filter plate is encircled with N filter holes, and a filter lens with a specific refractive index is correspondingly fixedly arranged in each filter hole. A light source mounting position is fixed to a side of an in-light surface of the filter plate. After any light source is mounted at the light source mounting position, lights of the light source irradiate the filter lens. A rotation and deflection driving mechanism is connected with an out-light surface of the filter plate and drives the filter plate to rotate or deflect along the axis according to a preset angle.

Abstract: Herein are techniques of zero data loss with asynchronously replicated redo logs. In an embodiment, a first server instance (FSI) of a plurality of server instances (PSI) of a primary database (PDB) sends, to a standby database (SDB) during an shutdown of FSI, a first recovery count (RC) and a remainder of an instance redo log (IRL). In response to recovering FSI, a second server instance of PSI increments a recovery counter to a second RC (SRC), publishes SRC to PSI, and sends SRC to SDB. After restarting FSI, FSI makes a change to contents of PDB, and stores, into IRL, a redo entry that defines the change. During failover, a database management system (DBMS) detects whether RCs associated with FSRL and SSRL are unanimous. If unanimous, DBMS fully rolls forward SDB by replaying FSRL and SSRL. Otherwise, DBMS limits replay and indicates that FSRL and SSRL might be inconsistent.

Abstract: Disclosed are methods and apparatuses to provide a redo repeater that allows for no data loss protection without the performance impact to the primary database even when a significant geographical distance separates the primary and standby databases. The Repeater is a lightweight entity that receives redo from the primary database with the purpose of redistributing that redo throughout the primary/standby system configuration. The Repeater able to extend no data loss protection and switchover functionality to terminal standby databases even though the primary database does not need to have a direct connection with those destinations.

Abstract: Disclosed are methods and apparatuses to provide a redo repeater that allows for no data loss protection without the performance impact to the primary database even when a significant geographical distance separates the primary and standby databases. The Repeater is a lightweight entity that receives redo from the primary database with the purpose of redistributing that redo throughout the primary/standby system configuration. The Repeater able to extend no data loss protection and switchover functionality to terminal standby databases even though the primary database does not need to have a direct connection with those destinations.

Abstract: Herein are techniques of zero data loss with asynchronously replicated redo logs. In an embodiment, a first server instance (FSI) of a plurality of server instances (PSI) of a primary database (PDB) sends, to a standby database (SDB) during an shutdown of FSI, a first recovery count (RC) and a remainder of an instance redo log (IRL). In response to recovering FSI, a second server instance of PSI increments a recovery counter to a second RC (SRC), publishes SRC to PSI, and sends SRC to SDB. After restarting FSI, FSI makes a change to contents of PDB, and stores, into IRL, a redo entry that defines the change. During failover, a database management system (DBMS) detects whether RCs associated with FSRL and SSRL are unanimous. If unanimous, DBMS fully rolls forward SDB by replaying FSRL and SSRL. Otherwise, DBMS limits replay and indicates that FSRL and SSRL might be inconsistent.

Abstract: In an exemplary embodiment of this disclosure, a system may include a first hypervisor, a second hypervisor, and a shared memory set. The first hypervisor and the second hypervisor run over a single logical partition. The shared memory set is accessible by both the first hypervisor and the second hypervisor, and the first hypervisor is configured to communicate with the second hypervisor by writing to the shared memory. The second hypervisor may provide support for hardware that is not supported by the first hypervisor, which hardware may be accessed by the first hypervisor through communications facilitated by use of the shared memory.

Abstract: Embodiments relate to a method for encapsulating a virtual server in a hypervisor subpartition of a single logical partition to provide additional hardware support and advanced virtualization functions. An aspect includes running a first hypervisor and one or more additional hypervisors over a single logical partition. A request to manage a virtual server is received at the first hypervisor. The request is then analyzed to determine what resources are necessary to manage the virtual server. Based on the analyzed request, one of the first hypervisor or the one or more additional hypervisors is selected to complete the request.

Abstract: Embodiments relate to a method for encapsulating a virtual server in a hypervisor subpartition of a single logical partition to provide additional hardware support and advanced virtualization functions. An aspect includes running a first hypervisor and one or more additional hypervisors over a single logical partition. A request to manage a virtual server is received at the first hypervisor. The request is then analyzed to determine what resources are necessary to manage the virtual server. Based on the analyzed request, one of the first hypervisor or the one or more additional hypervisors is selected to complete the request.

Abstract: Embodiments relate to a method for encapsulating a virtual server in a hypervisor subpartition of a single logical partition to provide additional hardware support and advanced virtualization functions. An aspect includes running a first hypervisor and one or more additional hypervisors over a single logical partition. A request to manage a virtual server is received at the first hypervisor. The request is then analyzed to determine what resources are necessary to manage the virtual server. Based on the analyzed request, one of the first hypervisor or the one or more additional hypervisors is selected to complete the request.