Device and method for enhancing item access bandwidth and atomic operation

    公开(公告)号:US10545867B2

    公开(公告)日:2020-01-28

    申请号:US15739243

    申请日:2016-05-10

    Abstract: A device, method, and a data storage medium, configured to enhance an item access bandwidth and atomic operation are provided. The device comprises: a comparison module, a cache, and a distribution module; wherein the comparison module is configured to receive a query request from a service side, determine whether an address pointed to by the query request and an item address stored in the cache are identical. If so, and a valid identifier vld is valid, the comparison module is configured to directly return the item data stored in the cache to the service side without initiating a request for looking up an off-chip memory, so as to reduce a frequency of accessing the off-chip memory. If not, the comparison module is configured to initiate a request for looking up the off-chip memory, so as to process, according to a first preconfigured rule, item data returned by the off-chip memory.

    Processor and task processing method therefor, and storage medium

    公开(公告)号:US10481957B2

    公开(公告)日:2019-11-19

    申请号:US15763996

    申请日:2016-07-01

    Inventor: Bo Wen Qingxin Cao

    Abstract: A processor and a task processing method therefor, and a storage medium. The method comprises: a scalar calculation module executing parameter calculation of a current task, and storing a parameter obtained through calculation in a PBUF; when the parameter calculation of the current task is completed, executing a first instruction or second instruction for inter-core synchronization, and storing the first instruction or the second instruction in the PBUF (301); a vector calculation module reading the parameter from the PBUF, storing the read parameter in a shadow register; when the first instruction or the second instruction is read from the PBUF, storing all the modified parameters in the shadow register in a work register within a period (302); and the vector calculation module executing vector calculation of the current task according to the parameter in the work register (303).

    IO interface level shift circuit, IO interface level shift method and storage medium

    公开(公告)号:US10200042B2

    公开(公告)日:2019-02-05

    申请号:US15519241

    申请日:2015-04-14

    Inventor: Hailiang Cui

    Abstract: Provided is an IO interface level shift circuit, comprising: an intermediate level generation circuit (11) and a level shift circuit (12). The intermediate level generation circuit is configured to provide an intermediate level Vdd_io of an IO interface. The level shift circuit is configured to convert an external logical signal into a signal in an internal power domain of a chip according to the intermediate level Vdd_io of the IO interface. Also provided are an IO interface level shift method and a storage medium. The interface level shift circuit enables level shift on an external IO signal at any level in a voltage withstanding domain of a device without adding a power domain suitable for an external IO level in the circuit.

    Closed-loop clock calibration method, terminal and computer storage medium

    公开(公告)号:US10172093B2

    公开(公告)日:2019-01-01

    申请号:US15545035

    申请日:2015-07-22

    Abstract: Disclosed is a closed-loop clock calibration method, comprising: performing clock calibration according to a calibration factor of an nth calibration period within the nth calibration period, and obtaining a calibration error of the nth calibration period; and according to the calibration error and calibration factor of the nth calibration period, obtaining a calibration factor of an (n+1)th calibration period, n being a positive integer. Also disclosed are a terminal and a computer storage medium.

    Data Processing Method and Processor based on 3072-Point Fast Fourier Transformation, and Storage Medium

    公开(公告)号:US20180165250A1

    公开(公告)日:2018-06-14

    申请号:US15561980

    申请日:2016-06-12

    CPC classification number: G06F17/142 G06F17/14 H04B3/542

    Abstract: A method for processing data based on 3072-point Fast Fourier Transform (FFT) and a processor based on 3072-point FFT are provided. The method for processing data based on 3072-point FFT includes: storing 3072-point data into a data storage module according to a predetermined mapping relationship (101); reading 16 data in parallel from the data storage module for performing 3-point DFT operation, and storing results into the data storage module in situ after completion of the operation (102); and reading 32 data in parallel from the data storage module for performing 1024-point DFT operation and storing results into the data storage module in situ after completion of the operation until the FFT of 3072-point data is completed (103).

    LINK CONTROL METHOD AND APPARATUS
    79.
    发明申请

    公开(公告)号:US20180145912A1

    公开(公告)日:2018-05-24

    申请号:US15519666

    申请日:2015-04-09

    CPC classification number: H04L47/12 H04L45/125 H04L49/15 H04L49/1515

    Abstract: Disclosed are a link control method and apparatus. The method includes that: link information and/or machine frame information in a system is acquired; and link control is performed according to the acquired link information and/or machine frame information. According to the technical solutions described in the disclosure, the problems of local congestion and packet loss in a three-level asymmetrical switching system can be effectively solved, the traffic level of the system is ensured, and the performance of the system is improved.

    TRANSMISSION CHECKING METHOD, NODE, SYSTEM AND COMPUTER STORAGE MEDIUM

    公开(公告)号:US20180138922A1

    公开(公告)日:2018-05-17

    申请号:US15574718

    申请日:2016-06-01

    Inventor: Xinliang Liu

    Abstract: Disclosed in the embodiments of the disclosure are a transmission checking method, node, system and computer storage medium. The method comprises: transmitting, by a SERializer/DESerializer (SERDES) transmitter, a first synchronization frame to a SERDES receiver; after the SERDES receiver receives the first synchronization frame, transmitting a second synchronization frame to the SERDES transmitter; and after the SERDES transmitter receives the second synchronization frame, transmitting a third synchronization frame to the SERDES receiver, such that the SERDES transmitter and the SERDES receiver can determine that a transmitting path and a receiving path of the SERDES transmitter and the SERDES receiver are in a normal state respectively.

Patent Agency Ranking