Methods and apparatus for cache intervention
    42.
    发明授权
    Methods and apparatus for cache intervention 有权
    缓存干预的方法和设备

    公开(公告)号:US07100001B2

    公开(公告)日:2006-08-29

    申请号:US10073492

    申请日:2002-02-11

    IPC分类号: G06F12/00

    CPC分类号: G06F12/0831 Y02D10/13

    摘要: Methods and apparatus for cache-to-cache block transfers (i.e., intervention) when the state of the transferred block is in a non-modified state (e.g., “exclusive” or “shared”) are provided. In one embodiment, a first cache holds the memory block in an “exclusive” state prior to the transfer. When a processor associated with a second cache attempts to read the block from a main memory, the first cache intervenes and supplies the block to the second cache. The state of the block in the first cache changes from “exclusive” to “shared.” In another embodiment, a processor associated with a third cache attempts to read the block from the main memory while the first cache and the second both hold the block in the “shared” state. Either the first cache or the second cache wins an arbitration and supplies the block to the third cache.

    摘要翻译: 提供了当传送块的状态处于非修改状态(例如,“独占”或“共享”)时用于高速缓存到高速缓存块传送(即干预)的方法和装置。 在一个实施例中,第一高速缓存在传输之前将存储块保持在“独占”状态。 当与第二高速缓存相关联的处理器尝试从主存储器读取块时,第一缓存介入并将块提供给第二高速缓存。 第一个缓存中的块状态从“独占”变为“共享”。 在另一个实施例中,与第三高速缓存相关联的处理器尝试从主存储器读取块,而第一高速缓存和第二高速缓冲存储器将第二缓存器保持在“共享”状态。 第一缓存或第二高速缓存赢得仲裁,并将块提供给第三高速缓存。

    Semaphore mechanism for a data processing system
    43.
    发明授权
    Semaphore mechanism for a data processing system 失效
    数据处理系统的信号量机制

    公开(公告)号:US5394551A

    公开(公告)日:1995-02-28

    申请号:US954575

    申请日:1992-09-30

    CPC分类号: G06F9/52

    摘要: In a data processing system a number of processing nodes share resources. Access to the shared resources is controlled by semaphores, each node having a local copy of all the semaphores. Nodes may acquire ownership of semaphores. When a node requires a semaphore operation on a particular semaphore, a semaphore message is broadcast to all the nodes instructing them to perform the semaphore operation on their local copies of the semaphore. If the semaphore is unowned, the node must suspend the semaphore operation until the message returns, so as to ensure correct chronology for the semaphore operation. If, however, the semaphore owned by this node, the node can perform the semaphore operation without waiting for the message to return. This speeds up the semaphore mechanism. If the semaphore is owned by another node, that other node relinquishes ownership so that the semaphore operation can be performed.

    摘要翻译: 在数据处理系统中,许多处理节点共享资源。 共享资源的访问由信号量控制,每个节点都具有所有信号量的本地副本。 节点可能获得信号量的所有权。 当节点需要在特定信号量上进行信号量操作时,将向所有节点广播信号量消息,指示它们对信号量的本地副本执行信号量操作。 如果信号量不存在,则节点必须暂停信号量操作,直到消息返回,以确保信号量操作的正确年表。 然而,如果该节点拥有的信号量,则节点可以执行信号量操作,而不等待消息返回。 这加快了信号量机制。 如果信号量由另一个节点拥有,则该另一个节点放弃所有权,以便可以执行信号量操作。