公开(公告)号：US20060045108A1

公开(公告)日：2006-03-02

申请号：US11017406

申请日：2004-12-20

申请人： Robert Blackmore ,  Fu Chang ,  Piyush Chaudhary ,  Kevin Gildea ,  Jason Goscinski ,  Rama Govindaraju ,  Donald Grice ,  Leonard Helmer ,  Patricia Heywood ,  Peter Hochschild ,  John Houston ,  Chulho Kim ,  Steven Martin

发明人： Robert Blackmore ,  Fu Chang ,  Piyush Chaudhary ,  Kevin Gildea ,  Jason Goscinski ,  Rama Govindaraju ,  Donald Grice ,  Leonard Helmer ,  Patricia Heywood ,  Peter Hochschild ,  John Houston ,  Chulho Kim ,  Steven Martin

IPC分类号： H04L12/56

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：US20060075057A1

公开(公告)日：2006-04-06

申请号：US10929943

申请日：2004-08-30

申请人： Kevin Gildea ,  Rama Govindaraju ,  Donald Grice ,  Peter Hochschild ,  Fu Chung Chang

发明人： Kevin Gildea ,  Rama Govindaraju ,  Donald Grice ,  Peter Hochschild ,  Fu Chung Chang

IPC分类号： G06F15/167

CPC分类号： H04L67/1097 ,  H04L67/18

摘要： A remote direct memory access (RDMA) system is provided in which data is transferred over a network by DMA between from a memory of a first node of a multi-processor system having a plurality of nodes connected by a network and a memory of a second node of the multi-processor system. The system includes a first network adapter at the first node, operable to transmit data stored in the memory of the first node to a second node in a plurality of portions in fulfillment of a DMA request. The first network adapter is operable to transmit each portion together with identifying information and information identifying a location for storing the transmitted portion in the memory of the second node, such that each portion is capable of being received independently by the second node according to the identifying information. Each portion is further capable of being stored in the memory of the second node at the location identified by the location identifying information.

摘要翻译： 提供了一种远程直接存储器访问（RDMA）系统，其中通过DMA在具有由网络连接的多个节点的多处理器系统的第一节点的存储器和第二个存储器连接的存储器之间的网络上通过网络传送数据 多处理器系统的节点。 该系统包括第一节点处的第一网络适配器，可操作以在DMA请求的多个部分中将存储在第一节点的存储器中的数据发送到多个部分中的第二节点。 第一网络适配器可操作以将每个部分与识别信息和信息一起发送，识别信息和信息标识用于存储第二节点的存储器中的发送部分的位置，使得每个部分能够由第二节点独立地根据识别 信息。 每个部分还能够在由位置识别信息标识的位置处存储在第二节点的存储器中。

公开(公告)号：US20070097875A1

公开(公告)日：2007-05-03

申请号：US11264529

申请日：2005-11-01

申请人： Carl Bender ,  Fu Chang ,  Kevin Gildea ,  Rama Govindaraju ,  Jay Herring ,  Peter Hochschild ,  Richard Swetz

发明人： Carl Bender ,  Fu Chang ,  Kevin Gildea ,  Rama Govindaraju ,  Jay Herring ,  Peter Hochschild ,  Richard Swetz

IPC分类号： H04L12/26

CPC分类号： H04L29/06 ,  H04L1/0057 ,  H04L1/0061 ,  H04L1/0079 ,  H04L69/326 ,  H04L2001/0092

摘要： In order to solve the problem of the detection of the arrival of duplicate data packets in an interconnected, multinode data processing system, each data packet is provided with a field of r bits that are randomly generated for each data packet. However, one of the packets is provided with a field that is computed from the other randomly generated field entries in a checksum computation which yields a selected nonzero checksum value. A running checksum at the receiver is used to determine whether or not, after the receipt of the specified number, k, of data packets, a duplicate packet has been received.

摘要翻译： 为了解决在互连的多节点数据处理系统中检测到重复数据分组的问题的问题，每个数据分组被提供有为每个数据分组随机生成的r比特的字段。 然而，其中一个分组被提供有一个字段，该字段是在产生选定的非零校验和值的校验和计算中的其他随机生成的字段条目中计算的。 在接收机上运行的校验和用于确定在接收到数据包的指定数量k之后是否已经接收到重复分组。

公开(公告)号：US20050097300A1

公开(公告)日：2005-05-05

申请号：US10697859

申请日：2003-10-30

申请人： Kevin Gildea ,  Rama Govindaraju ,  Peter Hochschild

发明人： Kevin Gildea ,  Rama Govindaraju ,  Peter Hochschild

IPC分类号： G06F9/50 ,  G06F15/00

CPC分类号： G06F9/5066 ,  G06F2209/509

摘要： A dedicated collective offload engine provides collective processing of data from processing nodes in a distributed computing environment. The dedicated collective offload engine and the processing nodes are coupled to a switch fabric. A result is produced by the collective offload engine based on the collective processing of the data, and is forwarded to at least one processing node. Collective processing is facilitated by communication among a plurality of dedicated collective offload engines via the switch fabric or via a private channel disposed between the collective offload engines.

摘要翻译： 专用的集体卸载引擎在分布式计算环境中提供来自处理节点的数据的集体处理。 专用集体卸载引擎和处理节点耦合到交换结构。 结果是由集体卸载引擎基于数据的集合处理产生的，并被转发到至少一个处理节点。 通过经由交换结构的多个专用集合卸载发动机之间的通信或经由设置在集体卸载发动机之间的专用通道进行通信来促进集体处理。

公开(公告)号：US20170329740A1

公开(公告)日：2017-11-16

申请号：US15155955

申请日：2016-05-16

申请人： Catherine H. Crawford ,  Kevin Gildea ,  Mark R. Nutter

发明人： Catherine H. Crawford ,  Kevin Gildea ,  Mark R. Nutter

IPC分类号： G06F15/173 ,  H04L29/08 ,  G06F12/0802

摘要： A method and system of storing and retrieving data in a computer system are disclosed. In an embodiment, the method comprises storing a data object at a specified location in a first data store, storing in a second data store first information identifying said specified location, retrieving the data object from a defined location in the first data store, obtaining second information identifying the defined location in the first data store, and comparing the second information to the first information to determine if the first information and the second information identify a same location in the first data store. In embodiments of the invention, the method further comprises when the second information and the first information identify different locations in the first data store, generating a fault signal to indicate that the location of the data object in the first data store has changed.