公开(公告)号：US07242682B1

公开(公告)日：2007-07-10

申请号：US10267378

申请日：2002-10-09

申请人： Timothy John Mueggenberg ,  Christopher J. Van Krevelen ,  Atiq Ahamad

发明人： Timothy John Mueggenberg ,  Christopher J. Van Krevelen ,  Atiq Ahamad

IPC分类号： H04L12/28

CPC分类号： H04L67/1097 ,  H04L29/1233 ,  H04L61/25 ,  H04L67/2819 ,  H04L69/22

摘要： A hardware frame modifier apparatus where the functions of the virtual device and virtual host are combined so that a single processor may perform them is provided. The hardware frame modifier apparatus may virtualize command and status frames without a store and forward operation. The modified command and status frames are sent to the physical host and physical device. The hardware frame modifier apparatus used a virtual table, updated by the virtual device/virtual host, to determine the appropriate mapping of the logical storage device of the frames to a physical storage device. Based on this mapping, the hardware frame modifier changes the frame header to direct the frame directly to the physical storage device and to determine the appropriate conversion of command and status type. In this way, the number of store and forward operations required to send data frames to, or read from, the physical storage devices is reduced or eliminated, thus reducing the delay or latency.

摘要翻译： 提供了虚拟设备和虚拟主机的功能组合以便单个处理器执行它们的硬件帧修改设备。 硬件帧修改装置可以在没有存储和转发操作的情况下虚拟化命令和状态帧。 修改的命令和状态帧发送到物理主机和物理设备。 硬件帧修改装置使用由虚拟设备/虚拟主机更新的虚拟表，以确定帧的逻辑存储设备到物理存储设备的适当映射。 基于该映射，硬件帧修改器改变帧头，将帧直接引导到物理存储设备，并确定命令和状态类型的适当转换。 以这种方式，减少或消除向物理存储设备发送数据帧或从其读取所需的存储和转发操作的数量，从而减少延迟或延迟。

公开(公告)号：US06230229B1

公开(公告)日：2001-05-08

申请号：US08994527

申请日：1997-12-19

申请人： Christopher J. Van Krevelen ,  Reed S. Nelson ,  Don J. Hodapp, Jr. ,  John D. Hamre

发明人： Christopher J. Van Krevelen ,  Reed S. Nelson ,  Don J. Hodapp, Jr. ,  John D. Hamre

IPC分类号： G06F1300

CPC分类号： G06F13/36

摘要： A method and system for transmitting data among a plurality of cards in a crossbar interconnect network having a plurality of cards each having source paths and destination paths utilizes a plurality of source arbitrators and a plurality of destination arbitrators each associated with the cards. The source arbitrators generate connection request commands from the source paths requesting access to a desired destination path and broadcasts the request for receipt by all of the destination arbitrators. The destination arbitrator associated with the desired destination path captures the connection request command and processes the command based on whether or not the desired destination path is busy. If the desired destination path is not busy, the destination arbitrator generates a connection command requesting a connection be made between the source path and the desired destination path. If the desired destination path is busy, the destination arbitrator stores the connection request command in one of a plurality of buffers until the desired destination path becomes available.

摘要翻译： 用于在具有多个具有源路径和目的地路径的多个卡的交叉网络互连网络中的多个卡之间传输数据的方法和系统利用多个源仲裁器和每个与该卡相关联的多个目的地仲裁器。 源仲裁器从源路径生成请求访问所需目的地路径的连接请求命令，并广播所有目的地仲裁器接收的请求。 与期望的目的地路径相关联的目的地仲裁器捕获连接请求命令，并基于所需的目的地路径是否正在忙碌来处理该命令。 如果所需的目的地路径不忙，则目的地仲裁器产生请求在源路径和期望的目的地路径之间进行连接的连接命令。 如果所需的目的地路径正忙，则目的地仲裁器将连接请求命令存储在多个缓冲器之一中，直到所需的目的地路径变得可用。