公开(公告)号：JP2006134170A

公开(公告)日：2006-05-25

申请号：JP2004324004

申请日：2004-11-08

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： KOCHIYA KIYOKUNI ,  OGASAWARA TAKESHI ,  KOMATSU HIDEAKI

IPC: G06F9/48

CPC classification number: G06F9/46

Abstract: PROBLEM TO BE SOLVED: To more promptly calculate than before the generation frequency of events generated while each central processing unit executes each thread by a thread and by a central processing unit in a system having a plurality of central processing units.
SOLUTION: An information processor has a generation frequency counter counting the generation frequencies of respective events in a plurality of central processing units. The storage region for thread of each thread records the cumulative generation frequency of the events in executing the thread by the central processing unit by associating the thread with each central processing unit. The storage region for thread of each thread records the value of the generation frequency counter in the central processing unit at a point of time starting the execution of the thread by the central processing unit. A difference value obtained by subtracting the frequency when starting the thread from the value of the generation frequency counter of the central processing unit is added to the cumulative generation frequency of the event corresponding to the central processing unit in the storage region for thread of the thread at the time of completing the execution of the thread.
COPYRIGHT: (C)2006,JPO&NCIPI

Abstract translation: 要解决的问题：在每个中央处理单元通过线程执行每个线程的事件的生成频率和具有多个中央处理单元的系统中的中央处理单元之前，更加及时地计算出问题。 解决方案：信息处理器具有对多个中央处理单元中的各个事件的生成频率进行计数的生成频率计数器。 每个线程的线程的存储区域通过将线程与每个中央处理单元相关联来记录由中央处理单元执行线程的事件的累积生成频率。 每个线程的线程的存储区域在由中央处理单元开始执行线程的时间点处记录中央处理单元中的生成频率计数器的值。 通过从中央处理单元的生成频率计数器的值开始线程减去频率而获得的差值被添加到与线程的线程的存储区域中的对应于中央处理单元的事件的累积生成频率 在完成线程的执行时。 版权所有（C）2006，JPO＆NCIPI

公开(公告)号：JP2003256267A

公开(公告)日：2003-09-10

申请号：JP2002054611

申请日：2002-02-28

Applicant: IBM

Inventor： KOCHIYA KIYOKUNI

IPC: G06F12/02 ,  G06F9/46 ,  G06F12/00

Abstract: PROBLEM TO BE SOLVED: To provide a method for realizing a practical memory region search cache. SOLUTION: In the data processing method for carrying out memory search processing accompanied with the run of a program due to a computer under a multi-thread environment, the method is provided with a step for reading a corresponding entry in a cache table 30 stored in the memory on the basis of a prescribed search address, a step for reading a memory region body structure 40 pointed by a pointer registered in said entry from the memory on the basis of said pointer, and a step for processing said memory region body structure 40 as the searched result when the entry in the cache table 30 is not rewritten and the search address is positioned between the start address and the end address of said memory region body structure 40. COPYRIGHT: (C)2003,JPO

公开(公告)号：JP2003256215A

公开(公告)日：2003-09-10

申请号：JP2002051246

申请日：2002-02-27

Applicant: IBM

Inventor： KOSEKI SATOSHI ,  KOCHIYA KIYOKUNI

IPC: G06F9/45

Abstract: PROBLEM TO BE SOLVED: To improve the execution efficiency of compile processing by efficiently saving and restoring the contents of a register. SOLUTION: Whether or not predetermined variables in an execution program exist beyond predetermined function calling, and beyond what kind of the function calling do those variables exist is judged, and which of a volatile register, non-volatile register, and semi-volatile register should the above mentioned variables be allocated to is decided based on the judgement. Also, which of the registers should the variables existing beyond the function calling be allocated to is decided based on the execution frequency of the function at the time of executing an execution program. COPYRIGHT: (C)2003,JPO

公开(公告)号：JP2001265611A

公开(公告)日：2001-09-28

申请号：JP2000064718

申请日：2000-03-09

Applicant: IBM

Inventor： KOCHIYA KIYOKUNI ,  ONODERA TAMIYA

IPC: G06F12/00 ,  G06F9/46 ,  G06F12/02

Abstract: PROBLEM TO BE SOLVED: To reduce the loads of a system and to improve the entire performance by omitting a locking (synchronizing) processing when a thread accesses an object. SOLUTION: In this computer system provided with a data processing environment where the plural threads 131, 132 and 133 share and respectively access the objects 121, 122, 123 and 124, the objects 121, 122, 123 and 124 are provided with thread local flags 151, 152, 153 and 154 for indicating the presence/absence of thread locality. The threads 131, 132 and 133 access the objects 121, 122, 123 and 124 without performing the locking (synchronizing) processing depending on whether or not the thread local flags 151, 152, 153 and 154 in the objects 121, 122, 123 and 124 to access indicate the presence of the locality to the threads 131, 132 and 133.

公开(公告)号：JP2007183905A

公开(公告)日：2007-07-19

申请号：JP2006115275

申请日：2006-04-19

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： KOCHIYA KIYOKUNI ,  OGATA KAZUNORI ,  ONODERA TAMIYA

IPC: G06F9/44 ,  G06F12/00

Abstract: PROBLEM TO BE SOLVED: To provide a character string operation method for reducing the storage capacity of a storage part, a program, and an information processor.
SOLUTION: The information processor 1 for operating character strings is provided with: a storage part 30 for storing a character string group including a plurality of character strings each of which is constituted of a plurality of character data; a reference part 41 for referring to a specific character string from the character string group; a character data detection part 422 for detecting character data which are not referred to as the specific character string from the character string group; and a character data deletion part 423 for deleting the character data detected from the character string group.
COPYRIGHT: (C)2007,JPO&INPIT

Abstract translation: 要解决的问题：提供一种用于降低存储部件，程序和信息处理器的存储容量的字符串操作方法。 解决方案：用于操作字符串的信息处理器1设置有：存储部件30，用于存储包括由多个字符数据构成的多个字符串的字符串组; 用于从字符串组引用特定字符串的参考部分41; 字符数据检测部分422，用于从字符串组中检测不被称为特定字符串的字符数据; 以及字符数据删除部423，用于删除从字符串组检测到的字符数据。 版权所有（C）2007，JPO＆INPIT

公开(公告)号：JP2004152185A

公开(公告)日：2004-05-27

申请号：JP2002319006

申请日：2002-10-31

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： KOCHIYA KIYOKUNI ,  KOSEKI SATOSHI ,  ONODERA TAMIYA

IPC: G06F9/50 ,  G06F9/46 ,  G06F17/00

CPC classification number: G06F9/526

Abstract: PROBLEM TO BE SOLVED: To speed up acquisition of competitive resources while securing the exclusivity of the acquisition of the competitive resources when only a specific information processing part frequently acquires and releases the competitive resources. SOLUTION: The exclusive control unit 10 for allowing an information processing part to acquire the competitive resources exclusively of other information processing parts is equipped with a plurality of non-priority information processing parts 160 for acquiring exclusively one another non-priority exclusive rights which indicate a candidate of acquiring the competitive resources 50 by first processing and a priority information processing part 150 for acquiring the competitive resources 50 exclusively between itself and the non-priority information processing part 160 acquiring the non-priority exclusivity by second processing shorter in processing time than the first processing. COPYRIGHT: (C)2004,JPO

Abstract translation: 要解决的问题：只有在特定的信息处理部门经常获取和释放竞争资源时，才能加快竞争资源的获取，同时确保获得竞争资源的排他性。 解决方案：用于允许信息处理部分专门获取其他信息处理部分的竞争资源的排他控制单元10配备有多个非优先级信息处理部分160，用于仅获取另一个非优先权专有权 其指示通过第一处理获取竞争资源50的候选者和优先级信息处理部分150，用于通过在处理中较短的第二处理来获取独占于非优先级信息处理部分160的非优先级信息处理部分160之间的竞争资源50 时间比第一次处理。 版权所有（C）2004，JPO

公开(公告)号：JPH10254616A

公开(公告)日：1998-09-25

申请号：JP5315897

申请日：1997-03-07

Applicant: IBM

Inventor： KOCHIYA KIYOKUNI ,  ISHIKAWA HIROSHI

IPC: G06F3/038 ,  G05G9/047 ,  G06F3/033

Abstract: PROBLEM TO BE SOLVED: To enable clicking operation, etc., without making a shake even when operation is done in a groping way by providing a space between a stick and an in-horizontal-plane vector detecting mechanism and forming a physical dead zone of this space. SOLUTION: The upper end of the stick 1 rotates the joint part between a microswitch 9 and a fitting surface 7 as a fulcrum. The space from this stick 1 to a ring 3 is the physical provided dead zone. When the upper end of the stick 1 is slanted more, it comes into contact with the inside 3a of the ring 3. When the upper end of the stick 1 is further slanted, the force applied to the stick 1 in the slanting direction is applied to the ring 3. This force applied to the ring 3 is detected as strain by a sensor 11 fitted to a column 5 through the column 5. The output of the sensor 11 is converted into a signal of the direction and strength of the force. Thus, when the force is applied to the stick 1 exceeding the physical dead zone, the user feels physical response on fingers.

公开(公告)号：JP2009064217A

公开(公告)日：2009-03-26

申请号：JP2007231126

申请日：2007-09-06

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： ONODERA TAMIYA ,  KOCHIYA KIYOKUNI ,  OGATA KAZUNORI

IPC: G06F9/44 ,  G06F12/00

CPC classification number: G06F12/0276 ,  G06F9/4428

Abstract: PROBLEM TO BE SOLVED: To efficiently storing/managing an object.
SOLUTION: A system includes a storage device for storing classifiably the old object that is the object with a reference period lapsed after generated, and the new object that is the object with a reference period not lapsed after generated. The system: selects the new object with the reference period lapsed after generated, from the storage device; retrieves the old object having a content equal to that of the selected new object, from the storage device; stores the selected new object as a new old-object into the storage device, on condition of not being retrieved; integrates a reference to the selected new object with a reference to the retrieved old object, on condition of being retrieved; and changes the reference to the selected new object into a reference to the stored old object, on condition that the old object is stored.
COPYRIGHT: (C)2009,JPO&INPIT

Abstract translation: 要解决的问题：有效地存储/管理对象。 解决方案：系统包括存储装置，用于可分类地存储作为对象的旧对象，该对象具有在生成之后经过的参考时期，并且作为参考周期的对象的新对象在生成之后不会失效。 系统：从存储设备中选择生成后参考时间段的新对象; 从存储装置检索具有与所选择的新对象的内容相同的内容的旧对象; 在未被检索的情况下，将所选择的新对象作为新旧对象存储到存储设备中; 在被检索的情况下，将对所选新对象的引用与对所检索的旧对象的引用进行整合; 并且在存储旧对象的条件下，将对所选新对象的引用更改为对所存储的旧对象的引用。 版权所有（C）2009，JPO＆INPIT

公开(公告)号：JP2008112400A

公开(公告)日：2008-05-15

申请号：JP2006296299

申请日：2006-10-31

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation

Inventor： KOCHIYA KIYOKUNI ,  KOSEKI SATOSHI ,  ONODERA TAMIYA ,  JOHNSON GRAEME

IPC: G06F9/52

CPC classification number: G06F9/526 ,  G06F9/3004 ,  G06F9/30087 ,  G06F9/522

Abstract: PROBLEM TO BE SOLVED: To achieve efficient exclusive control without using an indivisible operation instruction or a memory barrier instruction.
SOLUTION: A system in this invention is provided with: a storage device having a first storage area for storing first information indicating the acquisition or trial of an exclusive right based on a first task and a second storage area for storing second information indicating the acquisition or trial of an exclusive right based on a second task; a first acquisition part for reading out the second storage area after issuing an instruction for writing the first information in the first storage area according to a request of the first task, and when the second information is not read out, replying an exclusive right acquisition success; and a second acquisition part for executing write reflection processing capable of referring to contents written in the first storage area by the first task from the second task, reading out the first storage area after completing the write reflection processing, and when the first information is not read out from the first storage area, replying the exclusive right acquisition success.
COPYRIGHT: (C)2008,JPO&INPIT

Abstract translation: 要解决的问题：在不使用不可分割的操作指令或存储器屏障指令的情况下实现高效的排他控制。 解决方案：本发明的系统具有：存储装置，具有第一存储区域，用于存储指示基于第一任务获取或试用排他权利的第一信息;以及第二存储区域，用于存储指示 基于第二项任务获得或审判专有权; 第一获取部分，用于根据第一任务的请求发出第一信息写入指令以读出第二存储区，并且当第二信息不被读出时，回答专有权获取成功 ; 以及第二获取部分，用于执行写入反射处理，其能够从第二任务中引用由第一任务写入第一存储区域中的内容，在完成写入反射处理之后读出第一存储区域，并且当第一信息不是 从第一个存储区读出，回答专有权获取成功。 版权所有（C）2008，JPO＆INPIT

公开(公告)号：JP2000076086A

公开(公告)日：2000-03-14

申请号：JP24449798

申请日：1998-08-31

Applicant: Internatl Business Mach Corp ,  インターナショナル・ビジネス・マシーンズ・コーポレイション

Inventor： ONODERA TAMIYA ,  KOCHIYA KIYOKUNI

IPC: G06F9/52 ,  G06F9/46 ,  G06F15/173 ,  G06F17/30

CPC classification number: G06F9/52 ,  Y10S707/99938

Abstract: PROBLEM TO BE SOLVED: To provide a compound lock method not to decelerate the processing speed of a high-frequency path for locking, accessing and unlocking an object.
SOLUTION: In a state of making plural sleds existent, when managing lock to the object by storing a bit showing the kind of lock and the identifier of a sled, which acquires lock corresponding to the lock of a first kind, or the identifier of lock of a second kind in a storage area provided corresponding to the object, this method executes a step for judging the bit showing the kind of lock for a certain object held by the first sled shows the lock of the first kind or not when the second sled tries to acquire the lock of a certain object and a step for putting up a competition bit when the bit shows the lock of the first kind.
COPYRIGHT: (C)2000,JPO

Abstract translation: 要解决的问题：提供一种不减速用于锁定，访问和解锁物体的高频路径的处理速度的复合锁定方法。 解决方案：在存在多个滑板的状态下，当通过存储显示锁的种类的位和与第一类的锁相对应的锁的标识符或锁定标识符来管理对象的锁定时 在与对象相对应的存储区域中的第二种类型的方法执行一个步骤，用于判断显示由第一滑架保持的某个对象的锁的种类的位表示当第二滑架 尝试获取某个对象的锁定，并且当该位显示第一种锁定时，设置一个竞争位的步骤。