公开(公告)号：US07536468B2

公开(公告)日：2009-05-19

申请号：US10875471

申请日：2004-06-24

申请人： Robert S. Blackmore ,  Xin Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram ,  Hanhong Xue

发明人： Robert S. Blackmore ,  Xin Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram ,  Hanhong Xue

IPC分类号： G06F15/16 ,  H04L12/28

CPC分类号： H04L51/18 ,  H04L69/22

摘要： A protocol interface is provided for an active message protocol of a computing environment and a client process employing the active message protocol. The protocol interface includes an interface to a header handler function associated with the client process. The interface to the header handler function has parameters to be passed by and a parameter to be returned to the active message protocol when processing a message received through the active message protocol. The parameters to be passed include current message state information and current message type information for the received message. These parameters facilitate message-specific decisions by the header handler function about processing data of the message by the active message protocol. The parameter to be returned to the active message protocol instructs the active message protocol how to process the received message other than just where to store the message.

摘要翻译： 为计算环境的活动消息协议和采用活动消息协议的客户端进程提供协议接口。 协议接口包括与客户端进程相关联的报头处理函数的接口。 在处理通过活动消息协议接收的消息时，头处理程序函数的接口具有要传递的参数和要返回到活动消息协议的参数。 要传递的参数包括接收到的消息的当前消息状态信息和当前消息类型信息。 这些参数有助于报头处理函数关于通过活动消息协议处理消息的数据的消息特定决定。 要返回到活动消息协议的参数指示活动消息协议如何处理接收到的消息，而不仅仅是存储消息的位置。

公开(公告)号：US08116210B2

公开(公告)日：2012-02-14

申请号：US12126371

申请日：2008-05-23

申请人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

发明人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

IPC分类号： G01R31/08 ,  G06F11/00

CPC分类号： B60R25/1003

摘要： Epoch numbers are maintained in a pair wise fashion at a plurality of communication endpoints to provide communication consistency and recovery from a range of failure conditions including total or partial node failure and subsequent recovery. Once an epoch state inconsistency is recognized, negotiation procedures provide an effective mechanism to reestablish valid communication links without the need to employ global variables which inherently possess greater transmission and overhead requirements needed to maintain communications. Renegotiation of recognizably valid epoch numbers occurs on a pair wise basis.

摘要翻译： 在多个通信端点以成对方式保持时代号，以从包括全部或部分节点故障和随后恢复的一系列故障条件提供通信一致性和恢复。 一旦识别出时代状态不一致，谈判程序就提供了有效的机制来重新建立有效的通信链路，而不需要使用固有地拥有维持通信所需的更大的传输和开销要求的全局变量。 可识别的有效时代数的重新协商是以双重依据为基础进行的。

公开(公告)号：US07379444B2

公开(公告)日：2008-05-27

申请号：US10351823

申请日：2003-01-27

申请人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

发明人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

IPC分类号： H04L1/12 ,  H04L12/26

CPC分类号： H04L29/06 ,  H04L67/10 ,  H04L69/329 ,  H04L69/40

摘要： Epoch numbers are maintained in a pair wise fashion at a plurality of communication endpoints to provide communication consistency and recovery from a range of failure conditions including total or partial node failure and subsequent recovery. Once an epoch state inconsistency is recognized, negotiation procedures provide an effective mechanism to reestablish valid communication links without the need to employ global variables which inherently possess greater transmission and overhead requirements needed to maintain communications. Renegotiation of recognizably valid epoch numbers occurs on a pair wise basis.

摘要翻译： 在多个通信端点以成对方式保持时代号，以从包括全部或部分节点故障和随后恢复的一系列故障条件提供通信一致性和恢复。 一旦识别出时代状态不一致，谈判程序就提供了有效的机制来重新建立有效的通信链路，而不需要使用固有地拥有维持通信所需的更大的传输和开销要求的全局变量。 可识别的有效时代数的重新协商是以双重依据为基础进行的。

公开(公告)号：US20080225702A1

公开(公告)日：2008-09-18

申请号：US12126371

申请日：2008-05-23

申请人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

发明人： Robert S. Blackmore ,  Amy X. Chen ,  Scott D. Epter ,  Chulho Kim ,  Rajeev Sivaram

IPC分类号： G06F11/00

CPC分类号： B60R25/1003

摘要： Epoch numbers are maintained in a pair wise fashion at a plurality of communication endpoints to provide communication consistency and recovery from a range of failure conditions including total or partial node failure and subsequent recovery. Once an epoch state inconsistency is recognized, negotiation procedures provide an effective mechanism to reestablish valid communication links without the need to employ global variables which inherently possess greater transmission and overhead requirements needed to maintain communications. Renegotiation of recognizably valid epoch numbers occurs on a pair wise basis.

摘要翻译： 在多个通信端点以成对方式保持时代号，以从包括全部或部分节点故障和随后恢复的一系列故障条件提供通信一致性和恢复。 一旦识别出时代状态不一致，谈判程序就提供了有效的机制来重新建立有效的通信链路，而不需要使用固有地拥有维持通信所需的更大的传输和开销要求的全局变量。 可识别的有效时代数的重新协商是以双重依据为基础进行的。

公开(公告)号：US20110078410A1

公开(公告)日：2011-03-31

申请号：US11457921

申请日：2006-07-17

申请人： Robert S. Blackmore ,  Rama K. Govindaraju ,  Peter H. Hochschild ,  Chulho Kim ,  Rajeev Sivaram ,  Richard R. Treumann ,  Hanhong Xue

发明人： Robert S. Blackmore ,  Rama K. Govindaraju ,  Peter H. Hochschild ,  Chulho Kim ,  Rajeev Sivaram ,  Richard R. Treumann ,  Hanhong Xue

IPC分类号： G06F12/00 ,  G06F15/76 ,  G06F9/02

CPC分类号： G06F15/17375

摘要： Disclosed are a method of and system for multiple party communications in a processing system including multiple processing subsystems. Each of the processing subsystems includes a central processing unit and one or more network adapters for connecting said each processing subsystem to the other processing subsystems. A multitude of nodes are established or created, and each of these nodes is associated with one of the processing subsystems. A first aspect of the invention involves pipelined communication using RDMA among three nodes, where the first node breaks up a large communication into multiple parts and sends these parts one after the other to the second node using RDMA, and the second node in turn absorbs and forwards each of these parts to a third node before all parts of the communication arrive from the first node.

摘要翻译： 公开了一种包括多个处理子系统的处理系统中的多方通信的方法和系统。 每个处理子系统包括中央处理单元和用于将所述每个处理子系统连接到其他处理子系统的一个或多个网络适配器。 建立或创建多个节点，并且这些节点中的每一个都与处理子系统之一相关联。 本发明的第一方面涉及在三个节点之间使用RDMA的流水线通信，其中第一节点将大型通信分解成多个部分，并且使用RDMA将这些部分一个接一个地发送到第二节点，并且第二节点依次吸收和 在通信的所有部分从第一节点到达之前，将这些部分中的每一个转发到第三节点。

公开(公告)号：US07454491B2

公开(公告)日：2008-11-18

申请号：US10965597

申请日：2004-10-14

申请人： Robert S. Blackmore ,  Xin Amy Chen ,  Chulho Kim ,  Rajeev Sivaram ,  Richard R. Treumann ,  Hanhong Xue

发明人： Robert S. Blackmore ,  Xin Amy Chen ,  Chulho Kim ,  Rajeev Sivaram ,  Richard R. Treumann ,  Hanhong Xue

IPC分类号： G06F15/16

CPC分类号： H04L67/10 ,  H04L69/06 ,  H04L69/328

摘要： A method and system for transferring noncontiguous messages group including assembling a set of data into a series of transmission packets, packaging a description of the layout of the transmission packets into description packets and then places each description packet into a local buffer while maintaining a count of the number of description packets, transfers each description packet into a transmit buffer for transmission to at least one receiving node, identifies the data packets, and forwards each data packet to the transmit buffer for transmission to the at least one receiving node. The receiving node receives the transmission packets, identifies each packet as a description packet or data packet, places the description packets in a local buffer for storage until the description is complete, places each description packet into a user data buffer, stores data packets in a local queue until the description is complete, then transfers the data packets to the user buffer.

摘要翻译： 一种用于传送不连续消息组的方法和系统，包括将一组数据组合成一系列传输分组，将传输分组的布局的描述打包成描述分组，然后将每个描述分组放置到本地缓冲器中，同时保持计数 描述分组的数量将每个描述分组传送到用于发送到至少一个接收节点的发送缓冲器，识别数据分组，并将每个数据分组转发到发送缓冲器以传输到至少一个接收节点。 接收节点接收传输分组，将每个分组标识为描述分组或数据分组，将描述分组置于本地缓冲区中进行存储，直到描述完成，将每个描述分组放入用户数据缓冲区，将数据分组存储在 本地队列直到描述完成，然后将数据包传送到用户缓冲区。

公开(公告)号：US20060069788A1

公开(公告)日：2006-03-30

申请号：US10875471

申请日：2004-06-24

申请人： Robert Blackmore ,  Xin Chen ,  Scott Epter ,  Chulho Kim ,  Rajeev Sivaram ,  Hanhong Xue

发明人： Robert Blackmore ,  Xin Chen ,  Scott Epter ,  Chulho Kim ,  Rajeev Sivaram ,  Hanhong Xue

IPC分类号： G06F15/16

CPC分类号： H04L51/18 ,  H04L69/22

摘要： A protocol interface is provided for an active message protocol of a computing environment and a client process employing the active message protocol. The protocol interface includes an interface to a header handler function associated with the client process. The interface to the header handler function has parameters to be passed by and a parameter to be returned to the active message protocol when processing a message received through the active message protocol. The parameters to be passed include current message state information and current message type information for the received message. These parameters facilitate message-specific decisions by the header handler function about processing data of the message by the active message protocol. The parameter to be returned to the active message protocol instructs the active message protocol how to process the received message other than just where to store the message.

公开(公告)号：US20060085518A1

公开(公告)日：2006-04-20

申请号：US10965597

申请日：2004-10-14

申请人： Robert Blackmore ,  Xin Chen ,  Chulho Kim ,  Rajeev Sivaram ,  Richard Treumann ,  Hanhong Xue

发明人： Robert Blackmore ,  Xin Chen ,  Chulho Kim ,  Rajeev Sivaram ,  Richard Treumann ,  Hanhong Xue

IPC分类号： G06F15/16

CPC分类号： H04L67/10 ,  H04L69/06 ,  H04L69/328

摘要： A method and system for transferring noncontiguous messages group including assembling a set of data into a series of transmission packets, packaging a description of the layout of the transmission packets into description packets and then places each description packet into a local buffer while maintaining a count of the number of description packets, transfers each description packet into a transmit buffer for transmission to at least one receiving node, identifies the data packets, and forwards each data packet to the transmit buffer for transmission to the at least one receiving node. The receiving node receives the transmission packets, identifies each packet as a description packet or data packet, places the description packets in a local buffer for storage until the description is complete, places each description packet into a user data buffer, stores data packets in a local queue until the description is complete, then transfers the data packets to the user buffer.

摘要翻译： 一种用于传送不连续消息组的方法和系统，包括将一组数据组合成一系列传输分组，将传输分组的布局的描述打包成描述分组，然后将每个描述分组放置到本地缓冲器中，同时保持计数 描述分组的数量将每个描述分组传送到用于发送到至少一个接收节点的发送缓冲器，识别数据分组，并将每个数据分组转发到发送缓冲器以传输到至少一个接收节点。 接收节点接收传输分组，将每个分组标识为描述分组或数据分组，将描述分组置于本地缓冲区中进行存储，直到描述完成，将每个描述分组放入用户数据缓冲区，将数据分组存储在 本地队列直到描述完成，然后将数据包传送到用户缓冲区。

公开(公告)号：US07231638B2

公开(公告)日：2007-06-12

申请号：US10308734

申请日：2002-12-03

申请人： Robert S. Blackmore ,  Amy Xin Chen ,  Rama K. Govindaraju ,  Chulho Kim ,  Hanhong Xue

发明人： Robert S. Blackmore ,  Amy Xin Chen ,  Rama K. Govindaraju ,  Chulho Kim ,  Hanhong Xue

IPC分类号： G06F15/167 ,  G06F12/00 ,  G06F12/06

CPC分类号： G06F9/544

摘要： A method is provided for sharing and/or transporting data within a single node of a multi-node data processing. The method avoids the necessity of making more than one copy of the data to be shared or transported. The method is tunable based on the size of the data segment involved. A shared memory area between tasks running in different address spaces on the node is used to coordinate the process and for task to task communication. The increase in efficiency provided by the intranodal process described herein also provides advantages to the internodal communication process since more CPU cycles are available for that aspect of system operation.

摘要翻译： 提供了一种用于在多节点数据处理的单个节点内共享和/或传送数据的方法。 该方法避免了要共享或传输数据的多个副本的必要性。 该方法可以根据所涉及的数据段的大小进行调整。 在节点上运行不同地址空间的任务之间的共享内存区域用于协调进程和任务进行任务通信。 由于更多的CPU周期可用于系统操作的这一方面，由本文描述的内部结合处理提供的效率的提高也为节点间通信过程提供了优点。

公开(公告)号：US20060075067A1

公开(公告)日：2006-04-06

申请号：US11017359

申请日：2004-12-20

申请人： Robert Blackmore ,  Piyush Chaudhary ,  Jason Goscinski ,  Rama Govindaraju ,  Donald Grice ,  Peter Hochschild ,  John Houston ,  Chulho Kim ,  Steven Martin ,  Rajeev Sivaram ,  Hanhong Xue

发明人： Robert Blackmore ,  Piyush Chaudhary ,  Jason Goscinski ,  Rama Govindaraju ,  Donald Grice ,  Peter Hochschild ,  John Houston ,  Chulho Kim ,  Steven Martin ,  Rajeev Sivaram ,  Hanhong Xue

IPC分类号： G06F15/16

CPC分类号： H04L69/16 ,  G06F12/1081 ,  H04L69/166

摘要： In a multinode data processing system in which nodes exchange information over a network or through a switch, a structure and mechanism are provided which enables data packets to be sent and received in any order. Normally, if in-order transmission and receipt are required, then transmission over a single path is essential to insure proper reassembly. However, the present mechanism avoids this necessity and permits Remote Direct Memory Access (RDMA) operations to be carried out simultaneously over multiple paths. This provides a data striping mode of operation in which data transfers can be carried out much faster since packets of single or multiple RDMA messages can be portioned and transferred over several paths simultaneously, thus providing the ability to utilize the full system bandwidth that is available.

摘要翻译： 在节点通过网络交换信息或通过交换机交换信息的多节点数据处理系统中，提供了能够以任何顺序发送和接收数据分组的结构和机制。 通常，如果需要按顺序传输和接收，则通过单个路径的传输对于确保适当的重新组装是至关重要的。 然而，本机制避免了这种必要性，并且允许在多个路径上同时执行远程直接存储器访问（RDMA）操作。 这提供了数据条带化操作模式，其中数据传输可以执行得更快，因为单个或多个RDMA消息的分组可以同时分配和传输多个路径，从而提供利用可用的全部系统带宽的能力。