会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 4. 发明授权
    • Method for invalidating cache lines on a sharing list
    • 在共享列表上使缓存行无效的方法
    • US06226714B1
    • 2001-05-01
    • US09121603
    • 1998-07-09
    • Robert J. SafranekMichael A. Driscoll
    • Robert J. SafranekMichael A. Driscoll
    • G06F1208
    • G06F12/0813G06F12/0808G06F12/0824
    • A method of invalidating cache lines on an SCI sharing list by forwarding an invalidate request from node to node of a multiprocessor computer, such as a distributed shared memory (DSM) or non-uniform memory access (NUMA) machine. From the node at the head of the list, an invalidate request is sent to a succeeding node on the list. In response to receiving the invalidate request, the succeeding node checks the state of its cache line to determine whether it is the tail of the list and also invalidates the cache line. If the succeeding node is not the tail of the list, it forwards the invalidate request to the next succeeding node on the list. This next succeeding and other succeeding nodes then repeat the steps of invalidating the cache line and forwarding the invalidate request until the node that is the tail of the list is reached. The tail node responds by sending an invalidate response to the node at the head of the sharing list.
    • 通过从多处理器计算机(例如分布式共享存储器(DSM)或非均匀存储器访问(NUMA))机器的节点转发无效请求来使SCI共享列表上的高速缓存行无效的方法。 从列表头部的节点,将无效请求发送到列表中的后续节点。 响应于接收到无效请求,后续节点检查其高速缓存行的状态以确定它是否是列表的尾部,并且还使高速缓存行无效。 如果后续节点不是列表的尾部,则将无效请求转发到列表中的下一个后续节点。 接下来的后续节点和其他后续节点将重复执行无效高速缓存行并转发无效请求的步骤,直到达到列表尾部的节点为止。 尾节点通过向共享列表头部的节点发送无效响应来进行响应。