-
公开(公告)号:US06799317B1
公开(公告)日:2004-09-28
申请号:US09604310
申请日:2000-06-27
IPC分类号: G06F300
CPC分类号: G06F9/544 , G06F9/4812
摘要: A method for transparently handling messages originating from local shared memory and from an external source. A device driver allows the local sender to identify and wake up a waiting receiver task thread, simulating a packet arrival hardware interrupt. Upon awakening, the receiver task thread examines both shared memory and hardware message queues. The method can use a software routine that simulates handling of an occurrence of a hardware interrupt. The method invokes a local notify system service module that passes a window number identifying a receiving task. The method invokes a wake thread module that passes awakens a thread associated with the window number, and examines the shared memory buffer for receipt of the local source message. The method then copies the local source message from the shared memory buffer to the receiving task.
摘要翻译: 一种透明地处理源自本地共享内存和来自外部源的消息的方法。 设备驱动程序允许本地发送方识别和唤醒等待的接收者任务线程,模拟数据包到达硬件中断。 唤醒后,接收者任务线程检查共享内存和硬件消息队列。 该方法可以使用模拟处理硬件中断发生的软件程序。 该方法调用传递标识接收任务的窗口号的本地通知系统服务模块。 该方法调用唤醒线程模块,该模块通过唤醒与窗口号相关联的线程,并检查共享内存缓冲区以接收本地源消息。 该方法然后将本地源消息从共享内存缓冲区复制到接收任务。
-
公开(公告)号:US07065765B2
公开(公告)日:2006-06-20
申请号:US10004553
申请日:2001-12-05
IPC分类号: G06F9/46
CPC分类号: G06F9/526 , G06F9/542 , G06F2209/543
摘要: Event handling in multinode data processing networks, in which data structures are shared between nodes and are subject to concurrent requests for access, is facilitated through the use of a separate small data structure (bit array or linked list) which permits an event handler to hand off the task of accessing the data structure to an event handler which is already accessing data from the same data structure. This eliminates the need for locking arrangements and/or the use of special coordinating event handlers.
-
公开(公告)号:US07813369B2
公开(公告)日:2010-10-12
申请号:US11017406
申请日:2004-12-20
申请人: Robert S. Blackmore , Fu Chung Chang , Piyush Chaudhary , Kevin J. Gildea , Jason E. Goscinski , Rama K. Govindaraju , Donald G. Grice , Leonard W. Helmer, Jr. , Patricia E. Heywood , Peter H. Hochschild , John S. Houston , Chulho Kim , Steven J. Martin
发明人: Robert S. Blackmore , Fu Chung Chang , Piyush Chaudhary , Kevin J. Gildea , Jason E. Goscinski , Rama K. Govindaraju , Donald G. Grice , Leonard W. Helmer, Jr. , Patricia E. Heywood , Peter H. Hochschild , John S. Houston , Chulho Kim , Steven J. Martin
IPC分类号: G06F13/14
CPC分类号: H04L67/1097
摘要: In a multinode data processing system in which nodes exchange information over a network or through a switch, a structure and mechanism is provided within the realm of Remote Direct Memory Access (RDMA) operations in which DMA operations are present on one side of the transfer but not the other. On the side in which the transfer is not carried out in DMA fashion, transfer processing is carried out under program control; this is in contrast to the transfer on the DMA side which is characteristically carried out in hardware. Usage of these combination processes is useful in programming situations where RDMA is carried out to or from contiguous locations in memory on one side and where memory locations on the other side is noncontiguous. This split mode of transfer is provided both for read and for write operations.
摘要翻译: 在其中节点通过网络或通过交换机交换信息的多节点数据处理系统中,在远程直接存储器访问(RDMA)操作的领域内提供了结构和机制,其中DMA操作存在于传输的一侧,但是 不是其他的 在DMA方式不进行传输的一方,传送处理在程序控制下进行; 这与在硬件上进行特征性的DMA侧的传输相反。 这些组合过程的使用对于在一侧执行RDMA到存储器中的连续位置并且另一侧上的存储器位置不连续地执行RDMA的编程情况是有用的。 这种分离传输模式为读取和写入操作都提供。
-
公开(公告)号:US07552232B2
公开(公告)日:2009-06-23
申请号:US10692496
申请日:2003-10-24
申请人: Leonard W. Helmer, Jr. , Patricia E. Heywood , Paul DiNicola , Steven J. Martin , Gregory Salyer , Carol L. Soto
发明人: Leonard W. Helmer, Jr. , Patricia E. Heywood , Paul DiNicola , Steven J. Martin , Gregory Salyer , Carol L. Soto
IPC分类号: G06F15/16
CPC分类号: G06F15/17
摘要: A system and method that utilizes a dedicated transmission queue to enable expedited transmission of data messages to adaptive “nearest neighbor” nodes within a cluster. Packet descriptors are pre-fetched by the communications adapter hardware during the transmission of the preceding data element and setup for the next transmission is performed in parallel with the transmission of the preceding data element. Data elements of a fixed length that is equal to the cache line size of the communication hardware can optionally be used to provide optimized transfer between computer memory and communications hardware. The data receiving processing can also be optimized to recognize and handle cache line size data elements.
摘要翻译: 一种使用专用传输队列来实现数据消息到集群内的自适应“最近邻”节点的快速传输的系统和方法。 在传输前面的数据元素期间,通信适配器硬件预取数据包描述符,并且与先前数据元素的传输并行执行用于下一个传输的建立。 可以可选地使用等于通信硬件的高速缓存行大小的固定长度的数据元素来提供计算机存储器和通信硬件之间的优化传输。 数据接收处理也可以被优化以识别和处理高速缓存行大小的数据元素。
-
-
-