公开(公告)号：US5812811A

公开(公告)日：1998-09-22

申请号：US383331

申请日：1995-02-03

申请人： Pradeep Kumar Dubey ,  Charles Marshall Barton ,  Chiao-Mei Chuang ,  Linh Hue Lam ,  John Kevin O'Brien ,  Kathryn Mary O'Brien

发明人： Pradeep Kumar Dubey ,  Charles Marshall Barton ,  Chiao-Mei Chuang ,  Linh Hue Lam ,  John Kevin O'Brien ,  Kathryn Mary O'Brien

IPC分类号： G06F9/30 ,  G06F9/38 ,  G06F9/46

CPC分类号： G06F9/3009 ,  G06F9/3842 ,  G06F9/3851

摘要： A central processing unit (CPU) in a computer that permits speculative parallel execution of more than one instruction thread. The CPU uses Fork-Suspend instructions that are added to the instruction set of the CPU, and are inserted in a program prior to run-time to delineate potential future threads for parallel execution. The CPU has an instruction cache with one or more instruction cache ports, a bank of one or more program counters, a bank of one or more dispatchers, a thread management unit that handles inter-thread communications and discards future threads that violate dependencies, a set of architectural registers common to all threads, and a scheduler that schedules parallel execution of the instructions on one or more functional units in the CPU.

摘要翻译： 计算机中的中央处理单元（CPU），允许多个指令线程的推测并行执行。 CPU使用被添加到CPU的指令集中的Fork-Suspend指令，并在运行时插入到程序中，以描绘未来可能的并行线程。 CPU具有指令高速缓存，其具有一个或多个指令高速缓存端口，一个或多个程序计数器的存储体，一个或多个调度器的存储体，处理线程间通信的线程管理单元，并丢弃违反相关性的未来线程， 所有线程通用的一组架构寄存器，以及一个在CPU中的一个或多个功能单元上并行执行指令的调度程序。

公开(公告)号：US5761515A

公开(公告)日：1998-06-02

申请号：US616131

申请日：1996-03-14

申请人： Charles Marshall Barton, III ,  Pradeep Kumar Dubey ,  Jaime Humberto Moreno

发明人： Charles Marshall Barton, III ,  Pradeep Kumar Dubey ,  Jaime Humberto Moreno

IPC分类号： G06F9/32 ,  G06F9/38 ,  G06F9/45 ,  G06F12/00

CPC分类号： G06F8/4442 ,  G06F9/30047 ,  G06F9/322 ,  G06F9/383

摘要： In a computer system having a hierarchical memory, the problem of tolerating cache miss latency is solved by dynamically switching appropriately between two different code sequences, one optimized at compile-time, assuming a cache-hit, and the other optimized at compile-time, assuming a cache-miss. A method for processing instructions and data in a computer system including a hierarchical memory and a static instruction sequence including a memory access instruction and associated memory access latency specific code sequences, each code sequence optimized dependent on an execution of the memory access instruction causing one of a hit or a miss at a level of the memory hierarchy, includes the steps of: decoding and executing the memory access instruction and storing information indicating whether the execution of the memory access instruction caused the hit or the miss; and branching to a cache hit optimized code sequence when the information indicates the hit and a miss optimized code sequence when the information indicates the miss, responsive to the step of storing. Preferably, the memory access latency specific code sequences are associated with one or more identified critical miss-points. The step of branching may be responsive to an inserted branch instruction associated with the memory access instruction. The branch instruction may also specify a level of the cache memory upon which the step of branching is recommended.

摘要翻译： 在具有分层存储器的计算机系统中，容忍高速缓存未命中延迟的问题通过在两个不同的代码序列之间动态地切换来解决，一个在编译时优化，假设一个高速缓存命中，另一个在编译时被优化， 假设缓存未命中。 一种用于处理计算机系统中的指令和数据的方法，包括分层存储器和静态指令序列，所述分层存储器和静态指令序列包括存储器访问指令和相关联的存储访问延迟特定代码序列，每个代码序列根据存储器存取指令的执行而优化， 包括以下步骤：解码和执行存储器访问指令并存储指示存储器访问指令的执行是否导致命中或错过的信息; 并且当所述信息指示所述命中时，并且当所述信息指示所述遗漏时，分支到高速缓存命中优化代码序列，并响应于所述存储步骤。 优选地，存储器访问等待时间特定代码序列与一个或多个识别的关键错误点相关联。 分支的步骤可以响应于与存储器访问指令相关联的插入的分支指令。 分支指令还可以指定推荐分支步骤的缓存存储器的级别。

公开(公告)号：US06202141B1

公开(公告)日：2001-03-13

申请号：US09098063

申请日：1998-06-16

申请人： Keith Everett Diefendorff ,  Pradeep Kumar Dubey ,  Ronald Ray Hochsprung ,  Brett Olsson ,  Hunter Ledbetter Scales, III

发明人： Keith Everett Diefendorff ,  Pradeep Kumar Dubey ,  Ronald Ray Hochsprung ,  Brett Olsson ,  Hunter Ledbetter Scales, III

IPC分类号： G06F9302

CPC分类号： G06F9/30014 ,  G06F9/30025 ,  G06F9/30036

摘要： A vector multiplication mechanism is provided that partitions vector multiplication operation into even and odd paths. In an odd path, odd data elements of first and second source vectors are selected, and multiplication operation is performed between each of the selected odd data elements of the first source vector and corresponding one of the selected odd data elements of the second source vector. In an even path, even data elements of the source vectors are selected, and multiplication operation is performed between each of the selected even data elements of the first source vector and corresponding one of the selected even data elements of the second source vector. Elements of resultant data of the two paths are merged together in a merge operation. The vector multiplication mechanism of the present invention preferably uses a single general-purpose register to store the resultant data of the odd path and the even path. In addition, computational overhead of the merge operation is amortized over a series of vector operations.

摘要翻译： 提供了向量乘法机制，其将矢量乘法运算分为偶数和奇数路径。 在奇数路径中，选择第一和第二源向量的奇数数据元素，并且在第一源向量的所选择的奇数数据元素和第二源向量的所选奇数数据元素中的相应一个之间执行乘法运算。 在偶数路径中，选择源向量的偶数数据元素，并且在第一源向量的所选择的偶数数据元素和第二源向量的所选择的偶数数据元素中的对应一个之间执行乘法运算。 两个路径的结果数据的元素在合并操作中合并在一起。 本发明的向量乘法机构优选地使用单个通用寄存器来存储奇数路径和偶数路径的结果数据。 此外，合并操作的计算开销在一系列向量操作中进行分摊。

公开(公告)号：US06625330B1

公开(公告)日：2003-09-23

申请号：US09516142

申请日：2000-03-01

申请人： Pradeep Kumar Dubey ,  Sugata Ghosal ,  Ashutosh Kulshreshtha ,  Abhinanda Sarkar

发明人： Pradeep Kumar Dubey ,  Sugata Ghosal ,  Ashutosh Kulshreshtha ,  Abhinanda Sarkar

IPC分类号： G06K932

CPC分类号： G06K9/6204

摘要： A method of doing meaningful modifications on an image is presented. These modifications can then be used in variety of applications related to image shape manipulation and similar shape retrieval. The method extracts macrofeatures and microfeature from a given shape. Deformations are done on the macrofeatures only. These deformations are either predefined, or are taken from a deformation library, or are calculated from the shape itself, The microfeatures are then added to the deformed macrofeatures to get a deformed shape. The shape deformations then allow user's perception of shape similarity to be learned, which is reflected in the values of parameters in a parameterized shape similarity metric. The user can use one of the deformed shapes as the initial query point, instead of the shape he or she started with. The shape database compression is achieved by storing only the identification of a similar shape and value of global deformations which will generate this shape approximately, instead of storing every shape feature individually.

摘要翻译： 提出了对图像进行有意义的修改的方法。 然后，这些修改可用于与图像形状操纵和类似形状检索有关的各种应用。 该方法从给定的形状提取宏特征和微特征。 变形仅在宏观特征上进行。 这些变形是预定义的，或者是从变形库中获取的，或者是根据形状本身计算的。然后将微特征加到变形的宏观特征中以得到变形的形状。 形状变形然后允许用户对形状相似度的感知被学习，这反映在参数化形状相似性度量中的参数值中。 用户可以使用其中一个变形的形状作为初始查询点，而不是他或她开始的形状。 形状数据库压缩是通过仅存储将产生该形状的全局变形的类似形状和值的识别来实现的，而不是分别存储每个形状特征。

公开(公告)号：US06223320B1

公开(公告)日：2001-04-24

申请号：US09021516

申请日：1998-02-10

申请人： Pradeep Kumar Dubey ,  Marc Adam Kaplan ,  Sanjay Mukund Joshi

发明人： Pradeep Kumar Dubey ,  Marc Adam Kaplan ,  Sanjay Mukund Joshi

IPC分类号： H03M1300

CPC分类号： G06F9/30018 ,  G06F9/30032 ,  G06F9/30036 ,  G06F9/3004 ,  G06F9/345 ,  H03M13/091

摘要： An improved CRC generation mechanism for generating a CRC value of relevant data in a digital data stream is disclosed wherein relevant data in the data stream is identified and partitioned into a plurality of intervals. A CRC value is determined for each interval by partitioning the interval into a plurality of chunks, loading from persistent storage a table of CRC values for a range of chunks, determining a CRC value for each of the chunks with parallel table lookup operations on the table, and combining the CRC values for the chunks. The CRC values for each of the intervals is combined to generate the CRC for the relevant data. The parallel table look operation is preferably a vector permute instruction that is executed by a SIMD-style vector unit.

摘要翻译： 公开了一种用于在数字数据流中生成相关数据的CRC值的改进的CRC生成机制，其中识别数据流中的相关数据并将其划分为多个间隔。 通过将间隔划分成多个块来确定每个间隔的CRC值，从持久存储器加载块范围的CRC值表，使用表上的并行表查找操作确定每个块的CRC值 ，并组合块的CRC值。 每个间隔的CRC值被组合以产生相关数据的CRC。 平行表看法操作优选地是由SIMD式向量单元执行的向量置换指令。

公开(公告)号：US5724565A

公开(公告)日：1998-03-03

申请号：US383282

申请日：1995-02-03

申请人： Pradeep Kumar Dubey ,  Charles Roberts Moore ,  Terence Matthew Potter

发明人： Pradeep Kumar Dubey ,  Charles Roberts Moore ,  Terence Matthew Potter

IPC分类号： G06F9/46 ,  G06F9/30 ,  G06F9/38

CPC分类号： G06F9/3804 ,  G06F9/3836 ,  G06F9/3842 ,  G06F9/3851

摘要： A method and system are provided for processing instruction threads. Execution is initiated by a processing system of a first set of instructions including a particular instruction. The particular instruction includes an indication of a second set of instructions. In response to execution of the particular instruction and to the processing system being of a first type, the processing system continues executing the first set while initiating execution of the second set. In response to execution of the particular instruction and to the processing system being of a second type, the processing system continues executing the first set without initiating execution of the second set.

摘要翻译： 提供了一种用于处理指令线程的方法和系统。 执行由包括特定指令的第一组指令的处理系统发起。 特定指令包括第二组指令的指示。 响应于特定指令的执行和处理系统是第一类型，处理系统在启动第二组的执行的同时继续执行第一组。 响应于特定指令的执行和处理系统是第二类型，处理系统继续执行第一组而不启动第二组的执行。

公开(公告)号：US06925460B2

公开(公告)日：2005-08-02

申请号：US09815616

申请日：2001-03-23

申请人： Krishna Kummamuru ,  Raghuram Krishnapuram ,  Pradeep Kumar Dubey

发明人： Krishna Kummamuru ,  Raghuram Krishnapuram ,  Pradeep Kumar Dubey

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30719 ,  G06F17/3071 ,  Y10S707/99933 ,  Y10S707/99935

摘要： The present invention relates to a method, system and computer program product for clustering data points and its application to text summarization, customer profiling for web personalization and product cataloging.The method for clustering data points with defined quantified relationships between them comprises the steps of obtaining lead value for each data point either by deriving from said quantified relationships or as given input, ranking each data point in a lead value sequence list in descending order of lead value, assigning the first data point in said lead value sequence list as the leader of the first cluster, and considering each subsequent data point in said lead value sequence list as a leader of a new cluster if its relationship with the leaders of each of the previous clusters is less than a defined threshold value or as a member of one or more clusters where its relationship with the cluster leader is more than or equal to said threshold value. The said relationships between data points are symmetric or asymmetric. Similarly, system and computer program product have also been claimed.

摘要翻译： 本发明涉及用于聚类数据点的方法，系统和计算机程序产品及其应用于文本摘要，用于web个性化和产品编目的客户分析。 用于对其中具有定义的量化关系的数据点进行聚类的方法包括以下步骤：通过从所述量化关系导出或作为给定输入来获取每个数据点的引导值，以引导值序列表中的每个数据点按铅的降序排列 将所述引导值序列列表中的第一数据点分配为第一簇的引导符，并且如果其与每个的引导者的关系，则将所述引导值序列列表中的每个后续数据点视为新簇的引导者 先前的簇小于定义的阈值，或作为其与簇首的关系大于或等于所述阈值的一个或多个簇的成员。 数据点之间的关系是对称的或不对称的。 类似地，系统和计算机程序产品也被要求。

公开(公告)号：US06611834B1

公开(公告)日：2003-08-26

申请号：US09481359

申请日：2000-01-12

申请人： Gaurav Aggarwal ,  Deepavan Chakrabarti ,  Pradeep Kumar Dubey ,  Nitin Punamkumar Garq ,  Sugata Ghosal ,  Ashish Kumar Gupta ,  Ashutosh Kulshreshtha ,  Sreerama Kolluru Venkata Murthy

发明人： Gaurav Aggarwal ,  Deepavan Chakrabarti ,  Pradeep Kumar Dubey ,  Nitin Punamkumar Garq ,  Sugata Ghosal ,  Ashish Kumar Gupta ,  Ashutosh Kulshreshtha ,  Sreerama Kolluru Venkata Murthy

IPC分类号： G06F1730

CPC分类号： G06F17/30867 ,  G06F17/3056 ,  Y10S707/99932 ,  Y10S707/99933 ,  Y10S707/99952 ,  Y10S707/99953

摘要： A user at a client machine can customize components of a database search performed at a server. The user does this by sending executable code to the database server. Software code runs as middleware on the database server machine to communicate between the database server and the client and performs the functions of supplying the client with vital information required for generating code which will be used for customizing various processes of the database retrieval session. Typically, the server comprises a set of database servers and the middleware runs on each database server machine to communicate between the database servers and the client. The middleware provides a virtual machine on which the user-supplied code written in a virtual machine language is executed, giving a uniform interface across the set of database servers on which the same user-supplied code will be executed ensuring that the user-supplied code executes under database server specified access privileges.

摘要翻译： 客户端机器上的用户可以定制在服务器上执行的数据库搜索的组件。 用户通过向数据库服务器发送可执行代码来执行此操作。 软件代码作为数据库服务器机器上的中间件进行运行，以在数据库服务器和客户端之间进行通信，并执行为客户端提供生成代码所需的重要信息的功能，这些代码将用于定制数据库检索会话的各种进程。 通常，服务器包括一组数据库服务器，并且中间件在每个数据库服务器机器上运行，以在数据库服务器和客户端之间进行通信。 中间件提供了一个虚拟机，在其上执行以虚拟机语言编写的用户提供的代码，在整个数据库服务器集合中提供统一的接口，在该数据库服务器上将执行相同的用户提供的代码，确保用户提供的代码 在数据库服务器上执行指定的访问权限。

公开(公告)号：US06408293B1

公开(公告)日：2002-06-18

申请号：US09328968

申请日：1999-06-09

申请人： Gaurav Aggarwal ,  Pradeep Kumar Dubey ,  Sugata Ghosal ,  Ashutosh Kulshreshtha ,  Tumkur Venkatanarayana Rao Ravi

发明人： Gaurav Aggarwal ,  Pradeep Kumar Dubey ,  Sugata Ghosal ,  Ashutosh Kulshreshtha ,  Tumkur Venkatanarayana Rao Ravi

IPC分类号： G06F1730

CPC分类号： G06F17/30256 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943

摘要： A methodology of highly interactive intra-object relevance feedback is used to retrieve multimedia data from a database. The query object could consist of one or more images, images derived from video, a video sequence, or an audio clip. The query is adjusted using the information fed-back by the user about the relevance of previously extracted part(s) from the object itself, such that the adjusted query is a better approximation to the user's perception. The information fed-back by the user during intra-query modification is used for intra-object learning of the user's perception. The refined query is subsequently used for inter-object relevance feedback where data is retrieved from the database based on parameters learnt by intra-query object feedback mechanism, and the user provides feedback by ranking the retrieved objects in order of their relevance to him or her. In the system according to the invention, inter-object learning of user's perception is expedited by utilizing the learnt parameters in the intra-object relevance feedback. Furthermore, the methodology of the invention allows for building refined queries based on part(s) or sub-sequence(s) of the query object rather than the entire object itself, thereby reducing the number of irrelevant objects, retrieved from the database. The methodology allows synthesis and modification of the input query object itself in the event a query object is not directly available, and, also to learn the user's perception.

摘要翻译： 高度交互的对象内相关反馈的方法用于从数据库检索多媒体数据。 查询对象可以包括一个或多个图像，从视频，视频序列或音频剪辑导出的图像。 使用用户反馈的关于先前提取的部分与对象本身的相关性的信息来调整查询，使得经调整的查询更好地逼近用户的感知。 用户在查询修改期间反馈的信息用于用户感知的对象内学习。 精确查询随后用于对象间相关性反馈，其中基于由查询内对象反馈机制学习的参数从数据库检索数据，并且用户按照与他或她的相关性的顺序对所检索的对象进行排序来提供反馈 。 在根据本发明的系统中，通过利用对象内相关性反馈中的学习参数来加快用户感知的对象间学习。 此外，本发明的方法允许基于查询对象的部分或子序列而不是整个对象本身构建精简查询，从而减少从数据库检索的不相关对象的数量。 该方法允许在查询对象不直接可用的情况下对输入查询对象本身进行合成和修改，还可以了解用户的感知。

公开(公告)号：US06298365B1

公开(公告)日：2001-10-02

申请号：US09256375

申请日：1999-02-24

申请人： Pradeep Kumar Dubey ,  Brett Olsson ,  Ronald Ray Hochsprung ,  Hunter Ledbetter Scales, III ,  Keith Everett Diefendorff

发明人： Pradeep Kumar Dubey ,  Brett Olsson ,  Ronald Ray Hochsprung ,  Hunter Ledbetter Scales, III ,  Keith Everett Diefendorff

IPC分类号： G06F738

CPC分类号： G06F7/026 ,  G06F7/483

摘要： The invention relates to a method of using a “bounds” comparator scheme and to a “bounds” comparator circuit. The method of using this scheme or comparator circuit allows a quick and easy test to characterize, utilizing a single floating-point bounds comparison function, the location of a point with respect to pre-defined end- points. The single floating-point bounds comparison function represents an additional instruction to be incorporated within computer instruction set architectures when performing trivial acceptance testing during the generation of three-dimensional images or graphics.

摘要翻译： 本发明涉及使用“边界”比较器方案和“边界”比较器电路的方法。 使用该方案或比较器电路的方法允许使用单个浮点边界比较函数来表征相对于预定义端点的点的位置的快速和容易的测试。 单个浮点边界比较函数表示在三维图像或图形的生成期间执行微不足道的验收测试时要结合在计算机指令集架构中的附加指令。