公开(公告)号：JP2012089104A

公开(公告)日：2012-05-10

申请号：JP2011063882

申请日：2011-03-23

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： KAWAHARA AKIRA

IPC: G06F11/28 ,  G06F11/34

CPC classification number: G06F11/3457 ,  G06F9/455 ,  G06F11/2273 ,  G06F11/3612 ,  G06F12/16 ,  G06Q10/0637

Abstract: PROBLEM TO BE SOLVED: To obtain the estimation of a step execution time by expressing a behavior at an application level by an event-driven simulation and statistically approximating memory access timings of a smaller granularity.SOLUTION: A memory access detection module 316 in a referenced integrated system 310 detects an access of an application 312 to memory of a platform 314. A measurement module 330 puts data, which is detected by the memory access detection module 316 and whose beginning and end are delimited by a beginning/end-of-step detection module 318, into a form of an execution trace, and transfers it to a modeling/simulation system 320. A calculation module 324 estimates values such as an execution time and memory band usage rate using the data received from the measurement module 330.

Abstract translation: 要解决的问题：为了通过事件驱动模拟表达应用程度的行为以及统计地近似较小粒度的存储器访问定时来获得步骤执行时间的估计。 参考的集成系统310中的存储器访问检测模块316检测应用程序312对平台314的存储器的访问。测量模块330放置由存储器访问检测模块316检测到的数据，并且其 开始和结束由开始/结束步骤检测模块318限定为执行跟踪的形式，并将其传送到建模/仿真系统320.计算模块324估计诸如执行时间和存储器之类的值 使用从测量模块330接收的数据的频带使用率。版权所有：（C）2012，JPO和INPIT

公开(公告)号：JP2012085276A

公开(公告)日：2012-04-26

申请号：JP2011180340

申请日：2011-08-22

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： JOHN MICHAEL BOWIE ,  RANGANATHAN MARIAPPAN ,  NASIR SHAMIM UNISA

IPC: H04L9/32 ,  G06F17/21 ,  G06F21/24

CPC classification number: H04L9/3247 ,  G06F21/64 ,  H04L9/0643 ,  H04N2201/3235

Abstract: PROBLEM TO BE SOLVED: To provide a computer-implemented method, computer program, and apparatus for creating a digital signature for a composite resource document.SOLUTION: A method for creating a digital signature comprises the steps of: receiving a composite resource document containing at least one resource; obtaining an updated manifest resource, which lists all resources in the composite resource document; indicating a set of zero, one, or more resources to be subtracted from the list of resources in the composite resource document to create a generated signature reference list of identified resources to be signed; generating a hash token using the resources identified in the generated signature reference list to form a signature hash token; and encrypting the signature hash token with a secret key.

Abstract translation: 要解决的问题：提供一种用于为复合资源文档创建数字签名的计算机实现的方法，计算机程序和装置。 解决方案：一种用于创建数字签名的方法，包括以下步骤：接收包含至少一个资源的复合资源文档; 获取更新的清单资源，其列出复合资源文档中的所有资源; 指示要从复合资源文档中的资源列表中减去的一组零个，一个或多个资源，以创建所标识的待签名资源的生成的签名参考列表; 使用在所生成的签名参考列表中标识的资源来生成哈希标记以形成签名哈希标记; 并用秘密密钥加密签名散列令牌。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012084062A

公开(公告)日：2012-04-26

申请号：JP2010231622

申请日：2010-10-14

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： YOSHIDA ISSEI

IPC: G06F19/00

CPC classification number: G06F17/30539

Abstract: PROBLEM TO BE SOLVED: To provide technique for efficiently extracting only a meaningful frequent item set.SOLUTION: An analysis system 120 includes: a determination unit 330 which determines a new item set to be examined in the same order with a search of a tree of item sets in the descending order with depth priority; a frequent appearance determination unit 335 which registers the appearance frequency of the new item set in a table on condition that the appearance frequency is equal to or larger than a predetermined threshold; a correlation determination unit 340 which determines whether each of the items in the new item set correlates with a subset of the remaining items, excluding the new item, in the new item set by using values in the table in response to the registration; and a registration unit 345 which registers the new item set in a set of meaning frequent item sets on condition that a result of determination of each of all the items in the new item set is affirmative.

Abstract translation: 要解决的问题：提供有效提取有意义的频繁项集的技术。 解决方案：分析系统120包括：确定单元330，其以具有深度优先级的降序搜索项目集合树，以相同的顺序确定要检查的新项目集; 频繁出现确定单元335，其在出现频率等于或大于预定阈值的条件下将新项目集的出现频率登记在表中; 相关确定单元340，其通过响应于该注册使用表中的值来确定新项目组中的每个项目是否与新项目集合中的新项目的剩余项目的子集相关联; 以及注册单元345，其在新项目集中的所有项目中的每个项目的确定结果为肯定的条件下将新项目集合登记在一组意义上的频繁项集中。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012069041A

公开(公告)日：2012-04-05

申请号：JP2010214942

申请日：2010-09-27

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： NOGAYAMA TAKAHIDE ,  ISHO TOSHIO

IPC: G06F13/00

CPC classification number: G06F17/3089 ,  G06F17/30887

Abstract: PROBLEM TO BE SOLVED: To provide a response time improvement technique that is applicable even to many pages and a complicated web pace including scripts, functions, images, etc.SOLUTION: Dependence between components of a web page to be improved in response time is extracted, and homogeneous components are connected to each other. The connected components have information on component size updated. Then, a candidate for a file to be searched for is generated, an estimated loading time of the generated file candidate is calculated, and the web page is analyzed to generate dependence and inclusion relation in the form of table 0-1. Further, read-in relation (x) is generated in the form of table 0-1, and an integer programming problem is formulated so as to minimize the sum of downloading times of the page and file, and solved by a solver. A library file is reconstituted and generated from an obtained solution, and links of respective pages to a library file are rewritten into links to the newly generated library file.

Abstract translation: 要解决的问题：提供适用于许多页面的响应时间改进技术和包括脚本，功能，图像等的复杂的网络步骤。解决方案：网页的组件之间的依赖关系 提取响应时间的改善，并且均匀的组件彼此连接。 连接的组件有更新的组件大小的信息。 然后，生成要搜索的文件的候选者，计算所生成的候选文件的估计加载时间，分析网页以生成表0-1的形式的依赖关系和包含关系。 此外，以表0-1的形式生成读入关系（x），并且制定整数规划问题，以便最小化页面和文件的下载时间的总和并由求解器解决。 从获得的解决方案重构和生成库文件，并将各个页面的链接到库文件重写为链接到新生成的库文件。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012059353A

公开(公告)日：2012-03-22

申请号：JP2011230322

申请日：2011-10-20

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： CHERUBINI GIOVANNI ,  ELEFTHERIOU EVANGELOS S ,  JEN JERIT ,  HUTCHINS ROBERT ALLEN

IPC: G11B27/10 ,  G11B5/584 ,  G11B27/19

CPC classification number: G11B5/59688

Abstract: PROBLEM TO BE SOLVED: To provide a fully synchronous servo channel for a data tape drive.SOLUTION: A fully synchronous servo channel for a data tape drive is provided by including: initial acquisition of synchronous servo channel parameters; generation of a timing basis for signal interpolation; generation of a tape velocity estimate and a y-position estimate; and an optimum detection of longitudinal position (LPOS) symbols.

Abstract translation: 要解决的问题：为数据磁带驱动器提供完全同步的伺服通道。 解决方案：数据磁带驱动器的完全同步伺服通道包括：初始采集同步伺服通道参数; 生成信号插值的定时基础; 产生磁带速度估计和y位置估计; 以及纵向位置（LPOS）符号的最佳检测。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012054555A

公开(公告)日：2012-03-15

申请号：JP2011187435

申请日：2011-08-30

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： RICKY S AMOS ,  BOYD DIANE C ,  CYRIL CABRAL JR ,  RICHARD D KAPLAN ,  JAKUB T KEDZIERSKI ,  VICTOR KU ,  LEE WOO-HYEONG ,  LI YING ,  MOCUTA ANDA C ,  NARAYANAN VIJAY ,  ANNE L ZEUGEN ,  SERENDRA MAHESWARAN

IPC: H01L21/8238 ,  H01L21/28 ,  H01L21/336 ,  H01L21/339 ,  H01L21/60 ,  H01L27/092 ,  H01L29/417 ,  H01L29/423 ,  H01L29/49 ,  H01L29/78 ,  H01L29/786

CPC classification number: H01L21/76897 ,  H01L21/28052 ,  H01L21/28097 ,  H01L21/823835 ,  H01L29/66545 ,  H01L29/6656

Abstract: PROBLEM TO BE SOLVED: To provide a complementary metal oxide semiconductor integration process that allows a plurality of silicide metal gates to be prepared on a gate dielectric.SOLUTION: There is provided a CMOS silicide metal gate integration method capable of eliminating a demerit of generation of variations in the height of poly Si gate stock which varies a silicide metal gate phase. The integration method minimizes the complexity of the process, thereby restraining the manufacturing cost of a CMOS transistor from increasing.

Abstract translation: 要解决的问题：提供允许在栅极电介质上制备多个硅化物金属栅极的互补金属氧化物半导体集成工艺。 解决方案：提供了一种CMOS硅化物金属栅极集成方法，其能够消除改变硅化物金属栅极相的多晶硅栅极原料的高度变化的缺点。 该集成方法最小化了工艺的复杂性，从而抑制了CMOS晶体管的制造成本增加。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012053679A

公开(公告)日：2012-03-15

申请号：JP2010195944

申请日：2010-09-01

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： ISHIZAKI KAZUAKI

IPC: G06F9/45 ,  G06F9/44

CPC classification number: G06F8/4441

Abstract: PROBLEM TO BE SOLVED: To provide a device and method for improving the speed of access to a variable (symbol) which is frequently performed during the execution of a program described in a dynamic language.SOLUTION: This device includes: a range specification part 401 for specifying a range in which access to a symbol in a program can be made common; an instruction generation part 402 for performing access to a symbol table by using a key and generating a plurality of instructions including an instruction to acquire an address of a symbol entry and store the address in an address storage part; an instruction extraction part 403 for extracting the instruction from the specified range; and an instruction determination part 404 for determining whether or not the extracted instruction is an instruction to perform access to the symbol. When the extracted instruction is the instruction to perform access to the symbol, the instruction generation part 402 generates the instruction to perform access to the symbol by using the stored address of the symbol entry, the instruction being generated to enable access to the symbol without confirming the existence of the symbol, or to confirm the existence of the symbol quickly, when the symbol exists.

Abstract translation: 要解决的问题：提供一种用于提高对在动态语言描述的程序的执行期间频繁执行的变量（符号）的访问速度的设备和方法。 解决方案：该装置包括：范围指定部分401，用于指定可以使对程序中的符号进行通用的范围; 指令生成部402，用于通过使用密钥执行对符号表的访问，并生成包括获取符号条目的地址的指令的多个指令，并将该地址存储在地址存储部分中; 用于从指定范围中提取指令的指令提取部分403; 以及用于确定所提取的指令是否是执行对该符号的访问的指令的指令确定部分404。 当提取的指令是执行对符号的访问的指令时，指令生成部分402通过使用存储的符号条目的地址产生对符号进行访问的指令，该指令被产生以使得能够访问该符号而不确认 符号的存在，或者当符号存在时，快速确认符号的存在。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012053566A

公开(公告)日：2012-03-15

申请号：JP2010194224

申请日：2010-08-31

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

Inventor： TACHIBORI MICHIAKI ,  KAWACHIYA KIYOKUNI ,  INGLIS DEREK ,  ONODERA TAMIYA

IPC: G06F9/44 ,  G06F9/45

CPC classification number: G06F8/4443 ,  G06F9/45516

Abstract: PROBLEM TO BE SOLVED: To efficiently achieve in-lining for code optimization.SOLUTION: When a method is a supposition multimethod, a distribution of types in execution of a group of actual arguments is inspected by type inference and profiling. If appearance of the group of actual arguments deviates, the method is specialized for the group of types of high frequency, and the method and the group of types are cached as a key. A code at a call source is optimized so as to call the specialized method by performing run-time inspection for several groups of types of high frequency. When the code of the specialized method is small enough, in-lining is achieved.

Abstract translation: 要解决的问题：有效地实现代码优化的内联。

解决方案：当一种方法是假设多方法时，通过类型推断和分析来检查实际参数组执行中的类型分布。 如果实际参数组的出现偏差，则该方法专门针对高频类型的组，并且方法和类型组被缓存为关键。 优化呼叫源上的代码，以便通过对几组高频类型执行运行时检查来调用专门的方法。 当专门方法的代码足够小时，可以实现内衬。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012043409A

公开(公告)日：2012-03-01

申请号：JP2011138024

申请日：2011-06-22

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： JOHN MATTHEW SANTOSOSSO ,  MICHAEL JOHN BRANSON

IPC: G06F9/50

CPC classification number: G06F17/30563

Abstract: PROBLEM TO BE SOLVED: To provide a computer-implementing method, a system, and a computer program for processing a data stream.SOLUTION: The present invention provides techniques for selectively removing runtime data from a stream-based application in an aspect that reduces an impact of any delay caused by processing of the runtime data in the stream-based application. In addition to removing the runtime data from a primary processing path of the stream-based application, the runtime data can be processed in an alternate manner, either by using alternate processing resources or by delaying the processing of the runtime data.

Abstract translation: 要解决的问题：提供一种用于处理数据流的计算机实现方法，系统和计算机程序。 解决方案：本发明提供了用于在减少由基于流的应用中的运行时数据的处理引起的任何延迟的影响的方面中从基于流的应用中选择性地去除运行时数据的技术。 除了从基于流的应用的主处理路径去除运行时数据之外，可以通过使用备用处理资源或通过延迟运行时间数据的处理以备选方式来处理运行时数据。 版权所有（C）2012，JPO＆INPIT

公开(公告)号：JP2012038231A

公开(公告)日：2012-02-23

申请号：JP2010180043

申请日：2010-08-11

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： KAWAHITO MOTOHIRO ,  ALI SHAKE ,  VIJAY SUNDARESAN

IPC: G06F9/45

CPC classification number: G06F8/443

Abstract: PROBLEM TO BE SOLVED: To replace memory accesses with register accesses in order to improve performance in computer resources.SOLUTION: Memory accesses to a stack area saving the values of respective registers are replaced with local variable accesses. On condition that SPs are not escaping, the memory accesses via the SPs which are not escaping are replaced with the local variable accesses. Call numbers are imparted to respective call instructions and in-lined codes in response to the in-lining of the codes to be called by the call instructions included in a binary code. When the SPs are escaping, the memory accesses belonging to the call numbers imparted to the instructions causing escaping and the ancestor call numbers of the call numbers are prohibited to be replaced with the local variable accesses among the memory accesses where the escaping SPs are defined as base addresses. In the meantime, the remaining memory accesses without prohibition are replaced with the local variable accesses.

Abstract translation: 要解决的问题：使用寄存器访问替换存储器访问，以提高计算机资源的性能。

解决方案：存储器访问堆栈区域，保存各个寄存器的值被替换为局部变量访问。 在SP没有转义的情况下，通过不转义的SP进行的存储器访问被替换为局部变量访问。 响应于包含在二进制代码中的呼叫指令要呼叫的代码的内联，呼叫号码被赋予相应的呼叫指令和内联的代码。 当SP转出时，属于呼叫号码的存储器访问，导致转义，并且呼叫号码的祖先呼叫号码被禁止替换为存储器访问之间的本地变量访问，其中转义的SP被定义为 基地址。 同时，没有禁止的剩余存储器访问被替换为局部变量访问。 版权所有（C）2012，JPO＆INPIT