Apparatus and method for maintaining cache coherency, and multiprocessor apparatus using the method
    12.
    发明授权
    Apparatus and method for maintaining cache coherency, and multiprocessor apparatus using the method 有权
    用于维护高速缓存一致性的装置和方法,以及使用该方法的多处理器装置

    公开(公告)号:US09372795B2

    公开(公告)日:2016-06-21

    申请号:US14030543

    申请日:2013-09-18

    Inventor: Jin Ho Han

    CPC classification number: G06F12/0815 G06F12/0831

    Abstract: Provided are an apparatus and method for maintaining cache coherency, and a multiprocessor apparatus using the method. The multiprocessor apparatus includes a main memory, a plurality of processors, a plurality of cache memories that are connected to each of the plurality of processors, a memory bus that is connected to the plurality of cache memories and the main memory, and a coherency bus that is connected to the plurality of cache memories to transmit coherency related information between caches. Accordingly, a bandwidth shortage phenomenon may be reduced in an on-chip communication structure, which occurs when using a communication structure between a memory and a cache, and communication for coherency between caches may be simplified.

    Abstract translation: 提供了一种用于维持高速缓存一致性的装置和方法,以及使用该方法的多处理器装置。 多处理器装置包括主存储器,多个处理器,连接到多个处理器中的每一个的多个高速缓存存储器,连接到多个高速缓存存储器和主存储器的存储器总线,以及一个一致性总线 其连接到多个高速缓冲存储器以在高速缓存之间传送相关性信息。 因此,在使用存储器和高速缓存之间的通信结构时发生的片上通信结构中可能会减少带宽短缺现象,并且可以简化高速缓存之间的一致性的通信。

    Apparatus and method for ZQ calibration of data transmission driving circuit in memory chip package of multi-memory die structure

    公开(公告)号:US12266400B2

    公开(公告)日:2025-04-01

    申请号:US17983016

    申请日:2022-11-08

    Abstract: A method for ZQ calibration for a data transmission driving circuit of each memory die in a memory chip package in which memory dies are stacked, includes generating a reference current through a reference resistor connected between a power terminal supplying a power voltage of the data transmission driving circuit and a ground terminal and a first transistor that is diode-connected; supplying first currents corresponding to the reference currents to a pull-up driver of each memory die; performing ZQ calibration of a pull-up driver of a corresponding memory die by comparing a first voltage formed by each first current with a reference voltage formed by the reference current in each of the plurality of memory dies; and performing ZQ calibration of a pull-down driver of the corresponding memory die based on an output impedance of the ZQ calibrated pull-up driver in each of the memory dies.

    Cache for artificial intelligence processor

    公开(公告)号:US11341066B2

    公开(公告)日:2022-05-24

    申请号:US17119387

    申请日:2020-12-11

    Abstract: Disclosed is a cache including a dataflow controller for transmitting first data to a first processor and receiving second data from the first processor, an external direct memory access (DMA) controller for receiving the first data from an external memory to transmit the first data to the dataflow controller and receiving the second data from the dataflow controller to transmit the second data to the external memory, a scratchpad memory for storing the first data or the second data transmitted between the dataflow controller and the external DMA controller, a compression/decompression device for compressing data to be transmitted from the scratchpad memory to the external memory and decompressing data transmitted from the external memory to the scratchpad memory, and a transfer state buffer for storing transfer state information associated with data transfer between the dataflow controller and the external DMA controller.

    Processor for detecting and preventing recognition error

    公开(公告)号:US10983878B2

    公开(公告)日:2021-04-20

    申请号:US16694913

    申请日:2019-11-25

    Abstract: Provided is an image recognition processor. The image recognition processor includes a plurality of nano cores each configured to perform a pattern recognition operation and arranged in rows and columns, an instruction memory configured to provide instructions to the plurality of nano cores in a row unit, a feature memory configured to provide input features to the plurality of nano cores in a row unit, a kernel memory configured to provide a kernel coefficient to the plurality of nano cores in a column unit, and a difference checker configured to receive a result of the pattern recognition operation of each of the plurality of nano cores, detect whether there is an error by referring to the received result, and provide a fault tolerance function that allows an error below a predefined level.

    Cache control apparatus and method
    17.
    发明授权

    公开(公告)号:US09824017B2

    公开(公告)日:2017-11-21

    申请号:US14253349

    申请日:2014-04-15

    CPC classification number: G06F12/0875 G06F12/0831 G06F12/0833

    Abstract: Provided is a cache control apparatus and method that, when a plurality of processors read a program from the same memory in a chip, maintain coherency of data and an instruction generated by a cache memory. The cache control apparatus includes a coherency controller client configured to include an MESI register, which is included in an instruction cache, and stores at least one of a modified state, an exclusive state, a shared state, and an invalid state for each line of the instruction cache, and a coherency interface connected to the coherency controller and configured to transmit and receive broadcast address information, read or write information, and hit or miss information of another cache to and from the instruction cache.

Patent Agency Ranking