公开(公告)号：US07650374B1

公开(公告)日：2010-01-19

申请号：US10996103

申请日：2004-11-23

Applicant: Nils Gura ,  Lawrence A. Spracklen

Inventor： Nils Gura ,  Lawrence A. Spracklen

IPC: G06F7/52

CPC classification number: G06F7/53

Abstract: Multiple-precision hybrid multiplication is a technique that takes advantage of row-wise multiplication and column-wise multiplication. To generate a product for multiple-precision operands, partial products of the multiple-precision operands are accumulated in accordance with a hybrid of column-wise multiplication and row-wise multiplication. The partial products accumulated are of partial rows. The partiality of the row-wise partial products is defined by a parameter.

Abstract translation: 多精度混合乘法是一种利用逐行乘法和逐列乘法的技术。 为了生成多精度操作数的乘积，根据列逐行乘法和逐行乘法的混合，累加多个精度操作数的部分乘积。 累积的部分积是部分行。 行方向部分乘积的偏差由参数定义。

公开(公告)号：US07646984B1

公开(公告)日：2010-01-12

申请号：US11728915

申请日：2007-03-26

Applicant: Ronald Ho ,  John E. Cunningham ,  Ashok V. Krishnamoorthy ,  Robert J. Drost

Inventor： Ronald Ho ,  John E. Cunningham ,  Ashok V. Krishnamoorthy ,  Robert J. Drost

IPC: H04B10/12

CPC classification number: G06F1/105

Abstract: Embodiments of an integrated circuit are described. This integrated circuit includes: a clock-generator circuit configured to provide a clock signal; an optical clock path coupled to the clock-generator circuit; and a latch coupled to the optical clock path. This optical clock path is configured to distribute an optical signal corresponding to the clock signal. Furthermore, the optical clock path is configured to optically set a skew value for the optical signal, and is configured to selectively gate distribution of the optical signal to the latch based on activity of the latch. Note that the selective gating is performed optically.

Abstract translation: 描述集成电路的实施例。 该集成电路包括：时钟发生器电路，被配置为提供时钟信号; 耦合到时钟发生器电路的光时钟通路; 以及耦合到光时钟路径的锁存器。 该光时钟路径被配置为分配对应于时钟信号的光信号。 此外，光时钟路径被配置为光学地设置光信号的偏斜值，并且被配置为基于锁存器的活动来选择性地将光信号分配到锁存器。 注意，选择性门控是光学执行的。

公开(公告)号：US07644014B2

公开(公告)日：2010-01-05

申请号：US09982214

申请日：2001-10-17

Applicant: Sridatta Viswanath ,  Yafeng Li

Inventor： Sridatta Viswanath ,  Yafeng Li

IPC: G06F17/60

CPC classification number: G06Q30/06 ,  G06Q10/087 ,  G06Q30/0633 ,  G06Q30/0635 ,  G06Q30/0641

Abstract: In an electronic procurement system having a portal server, an Extensible Markup Language (XML) content integration and transformation method and system. The XML content integration and transformation system includes logic for retrieving an “Open Buying on the Internet (OBI)” compliant XML file from a database which is then formatted in response to an electronic purchasing request over the Internet. In one embodiment of the present invention, the client aware XML content transformation system receives an OBI XML file and uses this information to automatically search for data objects related to the OBI XML file content from a database on the Internet and translates the content into a format suitable for internal processing by the XML content integration and transformation logic and delivers it to the purchasing requisitioner over the Internet.

Abstract translation: 在具有门户服务器，可扩展标记语言（XML）内容集成和转换方法和系统的电子采购系统中。 XML内容集成和转换系统包括从数据库中检索“符合互联网（OBI）开放购买”XML文件的逻辑，该数据库随后通过因特网响应电子购买请求进行格式化。 在本发明的一个实施例中，客户端感知XML内容变换系统接收OBI XML文件并使用该信息来自互联网上的数据库自动搜索与OBI XML文件内容相关的数据对象，并将内容翻译成格式 适用于XML内容集成和转换逻辑的内部处理，并通过互联网将其提交给采购申请人。

公开(公告)号：US20090328065A1

公开(公告)日：2009-12-31

申请号：US12165334

申请日：2008-06-30

Applicant: Michael J. Wookey

Inventor： Michael J. Wookey

IPC: G06F3/00

CPC classification number: G06F9/5055 ,  H04L41/0233

Abstract: A method for job delegation including receiving a job from a user by a first management object, identifying a target system for the job using a data model in the first management object and a job delegation policy, where the data model comprises an object representing the target system, and determining a first nexthop for the target system, where the first nexthop is a second management object. The method also includes placing the job on a queue corresponding to the second management object, where the queue is located in the first management object, receiving the job by the second management object, locating the target system and a driver corresponding to the target system using the second management object, and executing the job using the driver corresponding to the target system.

Abstract translation: 一种用于作业授权的方法，包括由第一管理对象从用户接收作业，使用第一管理对象中的数据模型识别作业的目标系统，以及作业委托策略，其中数据模型包括表示目标的对象 系统，并且确定目标系统的第一下一跳，其中第一下一跳是第二管理对象。 该方法还包括将作业放置在与第二管理对象对应的队列上，其中队列位于第一管理对象中，由第二管理对象接收作业，使用目标系统定位目标系统和与目标系统相对应的驱动程序 第二管理对象，并使用与目标系统相对应的驱动程序来执行作业。

公开(公告)号：US20090327666A1

公开(公告)日：2009-12-31

申请号：US12145657

申请日：2008-06-25

Applicant: Mario I. Wolczko ,  Gregory M. Wright ,  Matthew L. Seidl

Inventor： Mario I. Wolczko ,  Gregory M. Wright ,  Matthew L. Seidl

IPC: G06F9/30

CPC classification number: G06F9/30032 ,  G06F9/30105 ,  G06F9/30112 ,  G06F9/3013 ,  G06F9/30134 ,  G06F9/3016 ,  G06F9/30167 ,  G06F9/30192

Abstract: A method for managing data, including obtaining a first instruction for moving a first data item from a first source to a first destination, determining a data type of the first data item, determining a data type supported by the first destination, comparing the data type of the first data item with the data type supported by the first destination to test a validity of the first instruction, and moving the first data item from the first source to the first destination based on the validity of the first instruction.

Abstract translation: 一种用于管理数据的方法，包括获得用于将第一数据项从第一源移动到第一目的地的第一指令，确定第一数据项的数据类型，确定由第一目的地支持的数据类型，比较数据类型 具有由第一目的地支持的数据类型的第一数据项以测试第一指令的有效性，以及基于第一指令的有效性将第一数据项从第一源移动到第一目的地。

公开(公告)号：US20090327374A1

公开(公告)日：2009-12-31

申请号：US12165024

申请日：2008-06-30

Applicant: Gregory M. Wright ,  Mario I. Wolczko

Inventor： Gregory M. Wright ,  Mario I. Wolczko

IPC: G06F17/30

CPC classification number: G06F12/0269

Abstract: One embodiment of the present invention provides a system that facilitates performing concurrent garbage collection. Note that the system uses hardware-supported GC barriers. During operation, the system executes a first mutator thread. While executing the first mutator thread, the system performs a garbage-collection operation using a garbage-collector thread. Performing the garbage-collection operation involves: discovering a live object in a from-space, which is being collected; creating a copy of the live object to a to-space, where live objects are copied to during garbage collection; and replacing the live object in the from-space with a forwarding pointer which points to a location of the copy of the live object in the to-space. Note that in some embodiments, the system marks cache lines comprising the live object in from-space as “forwarded,” which prevents any mutator threads from touching the cache lines. Additionally, in some embodiments, the system determines if the first mutator thread holds any additional references to the from-space. If so, the system leaves the first mutator thread marked as “dirty,” wherein dirty is the initial state for mutator threads. If not, the system marks the first mutator thread as “clean.”

Abstract translation: 本发明的一个实施例提供了一种便于执行并发垃圾收集的系统。 请注意，系统使用硬件支持的GC屏障。 在运行过程中，系统执行第一个mutator线程。 在执行第一个mutator线程时，系统使用垃圾回收器线程执行垃圾回收操作。 执行垃圾收集操作包括：从正在收集的空间中发现一个活动对象; 将活动对象的副本创建到空间，其中活动对象在垃圾收集期间被复制; 并使用指向空间中的活动对象的副本的位置的转发指针来替换空间中的活动对象。 注意，在一些实施例中，系统将包含从空间中的活动对象的高速缓存行标记为“转发”，其防止任何突变程序线程接触高速缓存行。 此外，在一些实施例中，系统确定第一突变体线程是否保持对从空间的任何附加引用。 如果是这样，系统会将第一个mutator线程标记为“dirty”，其中dirty是mutator线程的初始状态。 如果没有，系统将第一个mutator线程标记为“干净”。

公开(公告)号：US20090323690A1

公开(公告)日：2009-12-31

申请号：US12164360

申请日：2008-06-30

Applicant: Yunsong Lu ,  Kais Belgaied

Inventor： Yunsong Lu ,  Kais Belgaied

IPC: H04L12/56

CPC classification number: H04L47/2441 ,  H04L47/125 ,  H04L49/90 ,  H04L49/9063

Abstract: A method for processing packets. The method includes receiving a first packet by a network interface card (NIC) from a network, determining, using a first classification level, a first receive ring group (RRG) for the first packet, determining, using a second level classification, a first receive ring (RR) in the first RRG for the first packet, sending the first packet to the first RR, and sending the first packet from the first RR to a host operatively connected to the network interface card, wherein the first packet is received by a first virtual network interface card (VNIC) associated with the first RRG, where the first RRG is located in the NIC.

Abstract translation: 一种处理数据包的方法。 该方法包括：通过网络接口卡（NIC）从网络接收第一分组，使用第一分类级确定第一分组的第一接收环组（RRG），使用第二级分类确定第一分组 在所述第一RRG中接收所述第一分组的响铃（RR），将所述第一分组发送到所述第一RR，以及将所述第一分组从所述第一RR发送到可操作地连接到所述网络接口卡的主机，其中，所述第一分组由 与第一RRG相关联的第一虚拟网络接口卡（VNIC），其中第一RRG位于NIC中。

公开(公告)号：US07640591B1

公开(公告)日：2009-12-29

申请号：US11112328

申请日：2005-04-22

Applicant: Sunay Tripathi ,  Nicolas G. Droux ,  Yuzo Watanabe

Inventor： Sunay Tripathi ,  Nicolas G. Droux ,  Yuzo Watanabe

IPC: G06F11/00 ,  G06F11/30

CPC classification number: H04L63/1416 ,  H04L63/1458

Abstract: A method for controlling a denial of service attack involves receiving a plurality of packets from a network, identifying an attacking host based on a severity level of the denial of service attack from the network, wherein the attacking host is identified by an identifying attack characteristic associated with one of the plurality of packets associated with the attacking host, analyzing each of the plurality of packets by a classifier to determine to which of a plurality of temporary data structures each of the plurality of packet is forwarded, forwarding each of the plurality of packets associated with the identifying attack characteristic to one of the plurality of temporary data structures matching the severity level of the denial of service attack as determined by the classifier, requesting a number of packets from the one of the plurality of temporary data structures matching the severity level by the virtual serialization queue, and forwarding the number of packets to the virtual serialization queue.

Abstract translation: 用于控制拒绝服务攻击的方法包括从网络接收多个分组，基于来自网络的拒绝服务攻击的严重性级别识别攻击主机，其中攻击主机通过相关联的识别攻击特征来识别 与所述攻击主机相关联的所述多个分组中的一个分组，通过分类器分析所述多个分组中的每一个，以确定所述多个分组中的每一个被转发到多个临时数据结构中的哪一个，转发所述多个分组中的每个分组 与所述多个临时数据结构中的一个临时数据结构中的一个临时数据结构相关联，所述临时数据结构与由所述分类器确定的所述拒绝服务攻击的严重性级别匹配，请求从所述多个临时数据结构中的一个临时数据结构匹配严重性级别 通过虚拟序列化队列，并将数据包的数量转发到virtua l序列化队列

公开(公告)号：US07640544B2

公开(公告)日：2009-12-29

申请号：US10996508

申请日：2004-11-23

Applicant: Christine H. Flood ,  David L. Detlefs ,  Nir N. Shavit ,  Xiaolan Zhang ,  Ole Agesen

Inventor： Christine H. Flood ,  David L. Detlefs ,  Nir N. Shavit ,  Xiaolan Zhang ,  Ole Agesen

IPC: G06F9/455 ,  G06F9/46 ,  G06F12/00 ,  G06F13/00

CPC classification number: G06F12/0276 ,  Y10S707/99953 ,  Y10S707/99957

Abstract: A multiprocessor, multi-program, stop-the-world garbage collection program is described. The system initially over partitions the root sources, and then iteratively employs static and dynamic work balancing. Garbage collection threads compete dynamically for the initial partitions. Work stealing double-ended queues, where contention is reduced, are described to provide dynamic load balancing among the threads. Contention is resolved by using atomic instructions. The heap is broken into a young and an old generation where parallel semi-space copying is used to collect the young generation and parallel mark-compacting the old generation. Speed and efficiency of collection is enhanced by use of card tables and linking objects, and overflow conditions are efficiently handled by linking using class pointers. A garbage collection termination employs a global status word.

Abstract translation: 描述了一个多处理器，多程序，停止世界的垃圾收集程序。 系统最初对根源进行分区，然后迭代地采用静态和动态的工作平衡。 垃圾收集线程可以动态竞争初始分区。 被描述为在线程之间提供动态负载平衡的工作窃取双端队列，其中争用减少。 竞争通过使用原子指令来解决。 堆被打破成一个年轻和老一代，平行的半空间复制用于收集年轻一代和平行的标记压实老一代。 通过使用卡表和链接对象来增强收集的速度和效率，并且通过使用类指针进行链接来有效地处理溢出条件。 垃圾收集终端采用全局状态字。

公开(公告)号：US07640489B2

公开(公告)日：2009-12-29

申请号：US09921224

申请日：2001-08-01

Applicant: Matthias Breuer

Inventor： Matthias Breuer

IPC: G06N3/00

CPC classification number: G06F17/246

Abstract: Methods, systems, and articles of manufacture consistent with the present invention enable a user to input data into a document having cells arranged in columns and rows. A first of the cells and a second of the cells each have an original content. The original content of the first cell is overridden with a first user inputted value. The cells are recalculated based on the first user inputted value. After recalculating the cells based on the first user inputted value, the original content of the second cell is overridden with a second user inputted value. The cells are recalculated based on the second user inputted value. The original content of the first cell is automatically restored based on a user input such that the second user inputted value is maintained in the second cell.