公开(公告)号：US5396628A

公开(公告)日：1995-03-07

申请号：US24188

申请日：1993-02-26

申请人： Masaru Kitsuregawa ,  Shinya Fushimi

发明人： Masaru Kitsuregawa ,  Shinya Fushimi

IPC分类号： G06F12/00 ,  G06F9/50 ,  G06F15/17 ,  G06F17/30 ,  G06F13/38

CPC分类号： G06F9/5083

摘要： A data distributing method and an apparatus employing such method are disclosed, wherein a memory group stores the cumulative value of weighted values indicating data processing load of each kind of data or work unit outputted from a coupling unit. A control circuit recognizes the kind of data that is inputted to each of two input lines of the coupling units, judges whether or not there is a deviation in distribution of data or work units which are transferred from a first memory group to a second memory group on the basis of the cumulative value stored in the memory groups that correspond to the kinds of data recognized, and changes over connection patterns of switch in the coupling unit so that any deviation is corrected, thereby equally distributing the data processing load of data or work units to the second memory group.

摘要翻译： 公开了一种使用这种方法的数据分配方法和装置，其中存储器组存储指示从耦合单元输出的每种数据或工作单元的数据处理负载的加权值的累积值。 控制电路识别输入到耦合单元的两个输入线中的每一个的数据种类，判断是否存在从第一存储器组传送到第二存储器组的数据或工作单元的分布偏差 基于存储在存储组中的与识别的数据的种类相对应的累积值，并且改变耦合单元中的开关的连接模式，从而校正任何偏差，从而均匀分布数据或工作的数据处理负载 单位到第二个内存组。

公开(公告)号：US5237683A

公开(公告)日：1993-08-17

申请号：US591700

申请日：1990-10-02

申请人： Masaru Kitsuregawa ,  Shinya Fushimi

发明人： Masaru Kitsuregawa ,  Shinya Fushimi

IPC分类号： G06F7/00 ,  G06F7/24 ,  G06F9/50 ,  G06F15/173

CPC分类号： G06F9/505 ,  G06F15/17393 ,  G06F7/00 ,  G06F7/24

摘要： A data distributing method and an apparatus employing such method are disclosed, wherein a counter group counts and stores a cumulative number of data or work units outputted from a coupling unit for each kind of data. A control circuit recognizes the kind of data that is inputted to each of two input lines of the coupling unit, judges whether or not there is a deviation of distribution of data or work units which are transferred from a first group of devices to a second group of devices on the basis of the counts of the counters that correspond to the kinds of data recognized, and changes over connection patterns of switch in the coupling unit so that any deviation is corrected thereby equally distributing data or work units to the second group of devices.

公开(公告)号：US5603028A

公开(公告)日：1997-02-11

申请号：US381524

申请日：1995-01-31

申请人： Masaru Kitsuregawa ,  Shinya Fushimi

发明人： Masaru Kitsuregawa ,  Shinya Fushimi

IPC分类号： G06F9/50 ,  G06F13/38

CPC分类号： G06F9/5083

摘要： A data distribution apparatus and method for distributing data from a first group of devices to a second group of devices through a series of controlled coupling units to evenly distribute processing load associated with the data among the second group of devices. The coupling units have memory for storing values relating to an accumulated processing load of data distributed through the coupling unit. The coupling units distribute data and/or descriptive indicators representing data based on kinds of data, such as job classes, and processing loads that are previously estimated. By distributing based on processing load, a plurality of processes can be performed nearly simultaneously without excess waiting.

摘要翻译： 一种用于通过一系列受控耦合单元将数据从第一组设备分发到第二组设备的数据分配设备和方法，以在第二组设备之间均匀地分配与数据相关联的处理负载。 耦合单元具有用于存储与通过耦合单元分布的数据的累积处理负载有关的值的存储器。 耦合单元基于诸如作业类别和先前估计的处理负载的数据种类来分布表示数据的数据和/或描述性指示符。 通过基于处理负载进行分配，可以几乎同时执行多个处理，而不会过多等待。

公开(公告)号：US5079736A

公开(公告)日：1992-01-07

申请号：US357128

申请日：1989-05-26

申请人： Masaru Kitsuregawa ,  Shinya Fushimi

发明人： Masaru Kitsuregawa ,  Shinya Fushimi

IPC分类号： G06F7/24

CPC分类号： G06F7/24 ,  G06F2207/222 ,  Y10S707/99937

摘要： A control data generator for a sort processor includes a control data output unit which consists of a storage unit for storing information about the length of input data and a control data generation unit responsive to the stored information to generate control data for switching each sort processor between the first function and the second function, whereby control data is generated without using any programs.

公开(公告)号：US09639576B2

公开(公告)日：2017-05-02

申请号：US14397030

申请日：2012-04-27

申请人： Seisuke Tokuda ,  Akira Shimizu ,  Michiko Yoshida ,  Shinji Fujiwara ,  Kazuhiko Mogi ,  Masaru Kitsuregawa ,  Kazuo Goda

发明人： Seisuke Tokuda ,  Akira Shimizu ,  Michiko Yoshida ,  Shinji Fujiwara ,  Kazuhiko Mogi ,  Masaru Kitsuregawa ,  Kazuo Goda

IPC分类号： G06F17/30

CPC分类号： G06F17/30463 ,  G06F17/30483

摘要： A database management system (DBMS) generates a query execution plan including information representing one or more database (DB) operations necessary for executing a query, and executes the query in accordance with the query execution plan. In the execution of the query, the DBMS dynamically generates tasks for executing the DB operations and executes the dynamically generated tasks. The query execution plan includes a plurality of query blocks, which are sets of one or more DB operations. When newly generating a task, the DBMS executes determination processing of simultaneous-task-generation number. The determination processing of simultaneous-task-generation number is to calculate, targeting each of the query blocks, the number of simultaneous task generation, which is the number of tasks simultaneously generatable as tasks for executing the query block. The number of the dynamically generated tasks is equal to or smaller than the number of simultaneous task generation.

公开(公告)号：US20150113535A1

公开(公告)日：2015-04-23

申请号：US14404550

申请日：2012-05-31

申请人： Kazuo Goda ,  Hiroyuki Yamada ,  Masaru Kitsuregawa ,  Nobuo Kawamura ,  Shinji Fujiwara ,  Kazuhiko Mogi

发明人： Kazuo Goda ,  Hiroyuki Yamada ,  Masaru Kitsuregawa ,  Nobuo Kawamura ,  Shinji Fujiwara ,  Kazuhiko Mogi

IPC分类号： G06F9/46 ,  G06F9/54

CPC分类号： G06F9/466 ,  G06F9/4843 ,  G06F9/54 ,  G06F17/30445 ,  G06F17/30477

摘要： A parallel data processing system includes a parallel data processing execution unit for reading a data from a data set including a first data set that includes a plurality of first data and a second data set that includes a plurality of second data and executing processing. The parallel data processing execution unit (A) reads the first data from the first data set, and acquires a first value from the first data based on first format information acquired from an application, (B) generates one or more threads for respectively reading one or more second data corresponding to the first value from the second data set based on first reference information acquired from the application, (C) executes (A) and (B) on one or more first data in the first data set, and (D) executes a plurality of the threads in parallel.

摘要翻译： 并行数据处理系统包括并行数据处理执行单元，用于从包括多个第一数据的第一数据集和包括多个第二数据和执行处理的第二数据集的数据集读取数据。 并行数据处理执行单元（A）从第一数据集读取第一数据，并根据从应用获得的第一格式信息从第一数据获取第一值，（B）生成一个或多个线程，分别读取一个 （C）对第一数据集中的一个或多个第一数据执行（A）和（B），和（D）对应于来自第二数据集的第一值的第二数据; ）并行地执行多个线程。

公开(公告)号：US20150112965A1

公开(公告)日：2015-04-23

申请号：US14397030

申请日：2012-04-27

申请人： Seisuke Tokuda ,  Akira Shimizu ,  Michiko Yoshida ,  Shinji Fujiwara ,  Kazuhiko Mogi ,  Masaru Kitsuregawa ,  Kazuo Goda

发明人： Seisuke Tokuda ,  Akira Shimizu ,  Michiko Yoshida ,  Shinji Fujiwara ,  Kazuhiko Mogi ,  Masaru Kitsuregawa ,  Kazuo Goda

IPC分类号： G06F17/30

CPC分类号： G06F17/30463 ,  G06F17/30483

摘要： A database management system (DBMS) generates a query execution plan including information representing one or more database (DB) operations necessary for executing a query, and executes the query in accordance with the query execution plan. In the execution of the query, the DBMS dynamically generates tasks for executing the DB operations and executes the dynamically generated tasks. The query execution plan includes a plurality of query blocks, which are sets of one or more DB operations. When newly generating a task, the DBMS executes determination processing of simultaneous-task-generation number. The determination processing of simultaneous-task-generation number is to calculate, targeting each of the query blocks, the number of simultaneous task generation, which is the number of tasks simultaneously generatable as tasks for executing the query block. The number of the dynamically generated tasks is equal to or smaller than the number of simultaneous task generation.

摘要翻译： 数据库管理系统（DBMS）生成查询执行计划，包括表示执行查询所需的一个或多个数据库（DB）操作的信息，并根据查询执行计划执行查询。 在执行查询时，DBMS动态生成用于执行DB操作的任务，并执行动态生成的任务。 查询执行计划包括多个查询块，其是一个或多个DB操作的集合。 当新生成任务时，DBMS执行同时任务生成号码的确定处理。 同时任务生成号码的确定处理是针对每个查询块来计算同时任务生成的次数，其是同时生成作为执行查询块的任务的任务数量。 动态生成的任务的数量等于或小于同时任务生成的次数。

公开(公告)号：US08041707B2

公开(公告)日：2011-10-18

申请号：US12897243

申请日：2010-10-04

申请人： Masaru Kitsuregawa ,  Kazuo Goda

发明人： Masaru Kitsuregawa ,  Kazuo Goda

IPC分类号： G06F7/00

CPC分类号： G06F17/30474 ,  G06F17/30433 ,  G06F17/30463 ,  G06F17/30513

摘要： A database management system has a query interface for receiving a query and a query executor for executing the received query. The query executor dynamically generates a task, and executes a plurality of tasks in parallel. In execution of each task, each time data is required to be read from a database, the query executor generates a task for acquiring the data, and in execution of the generated task, issues a data read request for reading the data from the database, to thereby shorten a time taken to execute each task.

摘要翻译： 数据库管理系统具有用于接收查询的查询接口和用于执行接收到的查询的查询执行器。 查询执行器动态生成任务，并行执行多个任务。 在每个任务的执行中，每当需要从数据库读取数据时，查询执行器生成用于获取数据的任务，并且在执行生成的任务时，发出用于从数据库读取数据的数据读取请求， 从而缩短执行每个任务所需的时间。

公开(公告)号：US07734616B2

公开(公告)日：2010-06-08

申请号：US11182281

申请日：2005-07-14

申请人： Kazuhiko Mogi ,  Takashi Oeda ,  Masaru Kitsuregawa

发明人： Kazuhiko Mogi ,  Takashi Oeda ,  Masaru Kitsuregawa

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/3048 ,  Y10S707/99933 ,  Y10S707/99943

摘要： A storage system for providing a preferable data access performance by performing controls considering database management system (DBMS) execution information or database process priorities, by acquiring static configurational information of a DBMS by means of a DBMS information acquisition and communication program, a DBMS information communication section, and a host information setting program; acquiring DBMS execution information by means of a query plan acquisition program, the DBMS information communication section, and a process performance management program; acquiring information on priorities of database processes given by the process performance management program; and storing them in disk I/O management information with process priorities, DBMS execution information, and DBMS data information, in which cache control section in a storage system control program controls a data cache by referring to the above information.

摘要翻译： 一种存储系统，其通过采用DBMS信息获取和通信程序获取DBMS的静态配置信息，通过DBMS信息获取和通信程序获取DBMS的静态配置信息，通过执行考虑到数据库管理系统（DBMS）执行信息或数据库处理优先级的控制来提供优选的数据访问性能 部分和主机信息设置程序; 通过查询计划获取程序，DBMS信息通信部分和过程执行管理程序获取DBMS执行信息; 获取过程绩效管理计划给出的数据库流程优先级信息; 并将它们存储在具有进程优先级的数据I / O管理信息，DBMS执行信息和DBMS数据信息中，其中存储系统控制程序中的高速缓存控制部分通过参考上述信息来控制数据高速缓存。

公开(公告)号：US20070022100A1

公开(公告)日：2007-01-25

申请号：US11490172

申请日：2006-07-21

申请人： Masaru Kitsuregawa ,  Kazuo Goda

发明人： Masaru Kitsuregawa ,  Kazuo Goda

IPC分类号： G06F17/30

CPC分类号： G06F17/30474 ,  G06F17/30433 ,  G06F17/30463 ,  G06F17/30513

摘要： A database management system has a query interface for receiving a query and a query executor for executing the received query. The query executor dynamically generates a task, and executes a plurality of tasks in parallel. In execution of each task, each time data is required to be read from a database, the query executor generates a task for acquiring the data, and in execution of the generated task, issues a data read request for reading the data from the database, to thereby shorten a time taken to execute each task.

摘要翻译： 数据库管理系统具有用于接收查询的查询接口和用于执行接收到的查询的查询执行器。 查询执行器动态生成任务，并行执行多个任务。 在每个任务的执行中，每当需要从数据库读取数据时，查询执行器生成用于获取数据的任务，并且在执行生成的任务时，发出用于从数据库读取数据的数据读取请求， 从而缩短执行每个任务所需的时间。