Maintaining dynamic count of FIFO contents in multiple clock domains
    1.
    发明授权
    Maintaining dynamic count of FIFO contents in multiple clock domains 有权
    维护多个时钟域中FIFO内容的动态计数

    公开(公告)号:US07646668B2

    公开(公告)日:2010-01-12

    申请号:US12058964

    申请日:2008-03-31

    IPC分类号: G11C8/00

    CPC分类号: G06F5/06

    摘要: Disclosed is a system that generates a write count value for indicating whether data can be read from a FIFO and a system that generates a read count value for indicating whether data can be written to a FIFO. Each of these systems operates in two separate clock domains. In the system that generates a write count value, write strobes are stored in parallel in a register in a first clock domain. The plurality of synchronizers trigger on a rising edge of the write strobe that is stored in the parallel register and generate an increment pulse in a second clock domain. An up/down counter reads the increment pulse in parallel and increments the up/down counter in parallel. A decrement signal from a read strobe decrements the up/down counter. The output of the counter is fed to a register that provides a write counter value to handshake logic that indicates whether data can be read from a FIFO without underflowing the FIFO.

    摘要翻译: 公开了一种生成用于指示是否能够从FIFO读取数据的写入计数值的系统以及生成用于指示数据是否可以写入FIFO的读取计数值的系统。 这些系统中的每一个都在两个独立的时钟域中运行。 在产生写入计数值的系统中,写选通存储在第一时钟域中的寄存器中。 多个同步器在存储在并行寄存器中的写选通脉冲的上升沿触发,并在第二时钟域产生增量脉冲。 上/下计数器并行读取增量脉冲并并行增/减计数器。 来自读取选通的递减信号递减上/下计数器。 计数器的输出被馈送到寄存器,该寄存器为握手逻辑提供写计数值,该指令指示是否可以从FIFO读取数据,而不会使FIFO下溢。

    MAINTAINING DYNAMIC COUNT OF FIFO CONTENTS IN MULTIPLE CLOCK DOMAINS
    2.
    发明申请
    MAINTAINING DYNAMIC COUNT OF FIFO CONTENTS IN MULTIPLE CLOCK DOMAINS 有权
    维护多个时钟域内的FIFO内容的动态计数

    公开(公告)号:US20090244993A1

    公开(公告)日:2009-10-01

    申请号:US12058964

    申请日:2008-03-31

    IPC分类号: G11C7/00

    CPC分类号: G06F5/06

    摘要: Disclosed is a system that generates a write count value for indicating whether data can be read from a FIFO and a system that generates a read count value for indicating whether data can be written to a FIFO. Each of these systems operates in two separate clock domains. In the system that generates a write count value, write strobes are stored in parallel in a register in a first clock domain. The plurality of synchronizers trigger on a rising edge of the write strobe that is stored in the parallel register and generate an increment pulse in a second clock domain. An up/down counter reads the increment pulse in parallel and increments the up/down counter in parallel. A decrement signal from a read strobe decrements the up/down counter. The output of the counter is fed to a register that provides a write counter value to handshake logic that indicates whether data can be read from a FIFO without underflowing the FIFO.

    摘要翻译: 公开了一种生成用于指示是否能够从FIFO读取数据的写入计数值的系统以及生成用于指示数据是否可以写入FIFO的读取计数值的系统。 这些系统中的每一个都在两个独立的时钟域中运行。 在产生写入计数值的系统中,写选通存储在第一时钟域中的寄存器中。 多个同步器在存储在并行寄存器中的写选通脉冲的上升沿触发,并在第二时钟域产生增量脉冲。 上/下计数器并行读取增量脉冲并并行增/减计数器。 来自读取选通的递减信号递减上/下计数器。 计数器的输出被馈送到寄存器,该寄存器为握手逻辑提供写计数值,该指令指示是否可以从FIFO读取数据,而不会使FIFO下溢。

    Reduction of latency in store and forward architectures utilizing multiple internal bus protocols
    3.
    发明授权
    Reduction of latency in store and forward architectures utilizing multiple internal bus protocols 有权
    使用多个内部总线协议减少存储和转发架构中的延迟

    公开(公告)号:US07991927B2

    公开(公告)日:2011-08-02

    申请号:US12058984

    申请日:2008-03-31

    IPC分类号: G06F13/38

    CPC分类号: G06F13/161

    摘要: Disclosed is a store and forward device that reduces latency. The store and forward device allows front end devices having various transfer protocols to be connected in a single path through a RAM, while reducing latency. Front end devices that transfer data on a piecemeal basis are required to transfer all of the data to a RAM prior to downloading data to a back end. Front end devices that transfer data in a single download begin the transfer of data out of a RAM as soon as a threshold value is reached. Hence, the latency associated with downloading all of the data into a RAM 118 and then transferring all of the data out of the RAM is eliminated.

    摘要翻译: 公开了一种减少延迟的存储和转发设备。 存储和转发设备允许具有各种传输协议的前端设备通过RAM连接在单个路径中,同时减少等待时间。 在将数据下载到后端之前,需要以零碎的方式传输数据的前端设备将所有数据传输到RAM。 一旦达到阈值,在单个下载中传输数据的前端设备开始将数据从RAM传送出去。 因此,消除了将所有数据下载到RAM 118中然后将所有数据从RAM中传出的相关延迟。

    REDUCTION OF LATENCY IN STORE AND FORWARD ARCHITECTURES UTILIZING MULTIPLE INTERNAL BUS PROTOCOLS
    4.
    发明申请
    REDUCTION OF LATENCY IN STORE AND FORWARD ARCHITECTURES UTILIZING MULTIPLE INTERNAL BUS PROTOCOLS 有权
    使用多个内部总线协议的存储和前向架构减少停机

    公开(公告)号:US20090248968A1

    公开(公告)日:2009-10-01

    申请号:US12058984

    申请日:2008-03-31

    IPC分类号: G06F12/00

    CPC分类号: G06F13/161

    摘要: Disclosed is a store and forward device that reduces latency. The store and forward device allows front end devices having various transfer protocols to be connected in a single path through a RAM, while reducing latency. Front end devices that transfer data on a piecemeal basis are required to transfer all of the data to a RAM prior to downloading data to a back end. Front end devices that transfer data in a single download begin the transfer of data out of a RAM as soon as a threshold value is reached. Hence, the latency associated with downloading all of the data into a RAM 118 and then transferring all of the data out of the RAM is eliminated.

    摘要翻译: 公开了一种减少延迟的存储和转发设备。 存储和转发设备允许具有各种传输协议的前端设备通过RAM连接在单个路径中,同时减少等待时间。 在将数据下载到后端之前,需要以零碎的方式传输数据的前端设备将所有数据传输到RAM。 一旦达到阈值,在单个下载中传输数据的前端设备开始将数据从RAM传送出去。 因此,消除了将所有数据下载到RAM 118中然后将所有数据从RAM中传出的相关延迟。