SCALABLE SYNCHRONIZATION OF NETWORK DEVICES
    21.
    发明公开

    公开(公告)号:US20240031121A1

    公开(公告)日:2024-01-25

    申请号:US17871937

    申请日:2022-07-24

    CPC classification number: H04L7/0012

    Abstract: In one embodiment, a communication system includes network devices, each comprising a network interface to receive at least one data stream, a given network device being configured to recover a remote clock from the at least one data stream received by the given network device, a frequency synthesizer to generate a clock signal and output the clock signal to each of the network devices, wherein the given network device is configured to find a clock frequency differential between the clock signal and the recovered remote clock, and provide a control signal to the frequency synthesizer responsively to the clock frequency differential, the control signal causes the frequency synthesizer to adjust the clock signal so as to iteratively reduce an absolute value of the clock frequency differential between the clock signal and the recovered remote clock.

    Hardware Clock with Built-In Accuracy Check

    公开(公告)号:US20220224500A1

    公开(公告)日:2022-07-14

    申请号:US17148605

    申请日:2021-01-14

    Abstract: A network device includes one or more ports for connecting to a communication network, packet processing circuitry and clock circuitry. The packet processing circuitry is configured to communicate packets over the communication network via the ports. The clock circuitry includes a hardware clock configured to indicate a network time used for synchronizing network devices in the communication network, and a built-in accuracy test circuit configured to check an accuracy of the hardware clock.

    Atomic Updates of Versioned Data Structures
    28.
    发明申请

    公开(公告)号:US20190095475A1

    公开(公告)日:2019-03-28

    申请号:US15716729

    申请日:2017-09-27

    Abstract: Described embodiments include an apparatus that includes circuitry, configured to facilitate writing to a shared memory, and a processor. The processor is configured to compute a local current-version number by incrementing a shared current-version number that is stored in the shared memory. The processor is further configured to, subsequently to computing the local current-version number, using the circuitry, atomically write at least part of the local current-version number to a portion of the shared memory that is referenced by the local current-version number. The processor is further configured to, subsequently to atomically writing the at least part of the local current-version number, store data in the shared memory in association with the at least part of the local current-version number, and subsequently to storing the data, atomically overwrite the shared current-version number with the local current-version number. Other embodiments are also described.

    INTELLIGENT EXPOSURE OF HARDWARE LATENCY STATISTICS WITHIN AN ELECTRONIC DEVICE OR SYSTEM

    公开(公告)号:US20250036503A1

    公开(公告)日:2025-01-30

    申请号:US18916370

    申请日:2024-10-15

    Abstract: A method includes presenting, by a processing device, in a user interface of a display device, a set of menu items associated with a plurality of criteria and detecting one or more input signals from one or more selections of the set of menu items. The method includes creating a command that includes one or more criteria corresponding to selected options of the plurality of criteria derived from the one or more input signals. The method includes sending, by the processing device, the command to a network adapter device to trigger a polling operation to be performed that causes internal logic of the network adapter device to sample event data associated with a latency of data packets sent by a hardware process that is specific to the one or more criteria.

    Intelligent exposure of hardware latency statistics within an electronic device or system

    公开(公告)号:US12158795B2

    公开(公告)日:2024-12-03

    申请号:US18074751

    申请日:2022-12-05

    Abstract: A device includes a hardware block to perform a hardware process and internal logic coupled between a processing device, which executes instructions, and the hardware block. The internal logic can one of measure execution time or count clock cycles of at least a portion of the hardware process. The internal logic can further, in response to the measured execution time or the counted clock cycles satisfying a predetermined condition, provide data associated with the one of the execution time measurement or the clock cycles count to the processing device, the data being statistically indicative of a latency of data packets sent by the hardware process over a total time the hardware process executes.

Patent Agency Ranking