会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明专利
    • Microcontroller and control system
    • 微控制器和控制系统
    • JP2009110353A
    • 2009-05-21
    • JP2007282959
    • 2007-10-31
    • Hitachi Ltd株式会社日立製作所
    • KATO NAOKIYAMADA TETSUYAARAKAWA FUMIOYAMADA HIROMICHIOBO SHIGERUISHIKAWA MAKOTO
    • G06F7/76
    • G06F9/30025G06F7/483G06F9/3001H03M7/24
    • PROBLEM TO BE SOLVED: To suppress an increase in code amount by a program code for performing floating-point arithmetic, especially by its variable, and to reduce a processing overhead for converting fixed-point data into floating-point data. SOLUTION: The microcontroller (1) has: a floating-point converter (32) for inputting integer data and corresponding decimal point position data as fixed-point data to a control system and converting the input data into floating-point data by obtaining a fraction part, an exponent part, and a sign of a floating type from the input data; and a floating-point arithmetic logic unit (38) for receiving the output of the floating-point converter and calculating the floating-point data. The floating-point converter acquires the exponent part by performing addition and subtraction of the decimal point position data (ESP2) and the shift amount of the fraction part to the integer data. COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:通过用于执行浮点运算的程序代码,特别是通过其变量来抑制代码量的增加,并且减少用于将定点数据转换为浮点数据的处理开销。 微控制器(1)具有:浮点转换器(32),用于将整数数据和对应的小数点位置数据作为定点数据输入到控制系统,并将输入数据转换为浮点数据 从输入数据中获取浮动类型的分数部分,指数部分和符号; 以及用于接收浮点转换器的输出并计算浮点数据的浮点算术逻辑单元(38)。 浮点转换器通过对小数点位置数据(ESP2)的加减运算和分数部分的移位量进行整数取得指数部分。 版权所有(C)2009,JPO&INPIT
    • 2. 发明专利
    • Data processor
    • 数据处理器
    • JP2008139964A
    • 2008-06-19
    • JP2006323537
    • 2006-11-30
    • Hitachi Ltd株式会社日立製作所
    • ARAKAWA FUMIO
    • G06F9/38
    • G06F9/3867G06F9/30105G06F9/30181G06F9/325G06F9/381G06F9/3828G06F9/3885G06F9/3891
    • PROBLEM TO BE SOLVED: To provide a highly efficient and high performance processor for achieving efficient data transfer between a plurality of instruction flows, and for dividing a program into a plurality of instruction flows for execution. SOLUTION: A data processor having normal functions is configured as the integrated body of processors (CPU1 and CPU2) which define an instruction having the write instruction of another instruction flow into a reference register and an instruction having a reference register invalidation instruction, and execute a plurality of simple instruction flows. In executing the instruction having the write instruction of the other instruction flow into the reference register, whether or not a write register is invalid is confirmed, and when the write register is not invalid, writing is not executed until it becomes invalid, and when the write register is invalid, writing is executed. The instruction having the reference register invalidation instruction is executed, the register which has finished reference is invalidated. Furthermore, when the reference register is invalid, the execution of the reference instruction is suppressed until it becomes valid. COPYRIGHT: (C)2008,JPO&INPIT
    • 要解决的问题:提供一种高效率和高性能的处理器,用于实现多个指令流之间的有效数据传输,并且用于将程序划分为多个指令流以供执行。 解决方案:具有正常功能的数据处理器被配置为处理器(CPU1和CPU2)的集成体,其将具有另一指令流的写指令的指令定义到参考寄存器中,以及具有参考寄存器无效指令的指令, 并执行多个简单的指令流。 在将具有其他指令流的写入指令执行到参考寄存器中的指令中,确认写入寄存器是否无效,并且当写入寄存器不为无效时,直到无效之后才执行写入,并且当 写入寄存器无效,写入被执行。 执行具有参考寄存器无效指令的指令,已完成引用的寄存器无效。 此外,当参考寄存器无效时,参考指令的执行被抑制直到其变为有效。 版权所有(C)2008,JPO&INPIT
    • 4. 发明专利
    • Distributed control system
    • 分布式控制系统
    • JP2006134203A
    • 2006-05-25
    • JP2004324679
    • 2004-11-09
    • Hitachi Ltd株式会社日立製作所
    • KATO NAOKIARAKAWA FUMIO
    • G06F9/48G06F9/50G06F11/20G06F11/34
    • G05B19/0421G05B2219/25229G05B2219/25231
    • PROBLEM TO BE SOLVED: To provide a load distributed system for efficiently driving each control unit in addition to ensuring real time and improving failure proof in addition to ensuring the real time, as a distributed control system in which a plurality of control units are connected. SOLUTION: Each task is given a deadline to be a request time until task completion or information on cycle at which the task is activated and, in accordance with the deadline or task cycle, a control unit for executing the task is selected. A first control circuit is connected to a sensor and actuator with a dedicated path in which a high-speed response time is easily ensured and another control circuit is connected to the sensor and actuator with a network. When the first control circuit is normally operated and has sufficient processing capability, the first control circuit is used for control, whereas it has a failure or insufficient processing capability, other control circuits are used. COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:除了确保实时以外,除了确保实时以外,还提供一种用于有效地驱动每个控制单元的负载分布式系统,作为其中多个控制单元 被连接。 解决方案:每个任务都有一个截止期限,作为完成任务之前的请求时间或任务被激活的周期信息,并根据最后期限或任务周期选择用于执行任务的控制单元。 第一控制电路连接到传感器和致动器,其具有容易确保高速响应时间的专用路径,并且另一控制电路通过网络连接到传感器和致动器。 当第一控制电路正常工作并且具有足够的处理能力时,第一控制电路用于控制,而其具有故障或处理能力不足,则使用其它控制电路。 版权所有(C)2006,JPO&NCIPI
    • 5. 发明专利
    • Data processing unit and semiconductor device
    • 数据处理单元和半导体器件
    • JP2005338986A
    • 2005-12-08
    • JP2004154232
    • 2004-05-25
    • Hitachi Ltd株式会社日立製作所
    • ARAKAWA FUMIO
    • G06F1/28G06F1/30G06F1/32G06F15/78H01L21/822H01L27/04
    • G06F1/3203G06F1/3287G06F9/3836G06F9/3869Y02D10/171
    • PROBLEM TO BE SOLVED: To allow a semiconductor device having a plurality of modules to exhibit the appropriate performance of each module, while managing power on the basis of distributed management, and managing the power permitted for a chip as a whole. SOLUTION: A predetermined power consumption value is defined for each module. The predetermined power consumption value is an amount defined, while the permissible power values of the plurality of modules are taken into consideration. Each of the modules reports the difference between the predetermined power consumption value and the value of actually consumed power to other modules as the amount of extra power. Each of the modules can process data for an amount below the predetermined power consumption value, even without using the extra power coming from the other modules, so as to avoid deadlock. When the amount of extra power is reported from the other modules, the amount of power equal to the predetermined power consumption value and the amount of extra power are set as the amount of power consumable for data processing. COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:为了允许具有多个模块的半导体器件在分散管理的基础上管理电力,并且管理整体上的芯片所允许的功率,表现出每个模块的适当性能。

      解决方案:为每个模块定义预定的功耗值。 预定功耗值是限定的量,同时考虑多个模块的容许功率值。 每个模块报告预定功耗值与其他模块的实际消耗功率的值之间的差异作为额外功率的量。 即使没有使用来自其他模块的额外功率,每个模块也可以处理低于预定功耗值的数据,以避免死锁。 当从其他模块报告额外功率的量时,将等于预定功耗值的功率量和额外功率量设置为用于数据处理的功耗量。 版权所有(C)2006,JPO&NCIPI

    • 8. 发明专利
    • JPH05233271A
    • 1993-09-10
    • JP3315692
    • 1992-02-20
    • HITACHI LTD
    • ARAKAWA FUMIONARITA SUSUMUUCHIYAMA KUNIO
    • G06F9/38G06F9/22G06F9/28G06F9/30G06F9/318
    • PURPOSE:To provide a data processor capable of efficiently processing both of a reference instruction and a high function instruction. CONSTITUTION:When two reference instructions are supplied to instruction decoders 21, 22, instruction execution parts 51, 52 simultaneously execute the two reference instructions based upon decoded outputs from the decoders 21, 22 without using a microprgram ROM 30. When a high function instruction is supplied to one decoder 21, one execution part 51 selects the output of one decoder 21 and executes processing without using a microinstruction outputted from the ROM 30 in the 1st processing, and in the 2nd processing, the execution part 51 executes processing by selecting the microinstruction from the ROM 30. Since necessity of using the ROM 30 is eliminated at the time of executing the reference instruction, the capacity and the area of the ROM and power consumption corresponding to the reference instruction can be reduced.
    • 9. 发明专利
    • Distributed control system
    • 分布式控制系统
    • JP2007034359A
    • 2007-02-08
    • JP2005212238
    • 2005-07-22
    • Hitachi Ltd株式会社日立製作所
    • HYODO AKIHIKOKATO NAOKIARAKAWA FUMIO
    • G06F9/50G06F9/48
    • G05B19/042B60W2050/0297G05B2219/25229G05B2219/2637G06F9/4856G06F9/5033G06F9/5044
    • PROBLEM TO BE SOLVED: To provide a distributed control system in which a plurality of controllers are connected to one another by a network and which is capable of transferring tasks, for execution on other controllers, with properties specific for the controllers, where input and output processes are required or data stored in specific controllers are used.
      SOLUTION: To execute the transfer tasks specific for the controllers for execution on the other controllers, the transferring controller is provided with functions of collecting input data and context information in a storage area and transferring them to a destination controller, in addition to its original functions. The destination controller is provided with, functions of storing the data sent from the transferring controller in the storage area, performing computations, and returns the results to the transferring controller. The program of the task performing computation processes is included in both the destination controller and the transferring controller, and the destination controller determines a reference address using an appropriate method for processing the task.
      COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供一种分布式控制系统,其中多个控制器通过网络彼此连接,并且能够以特定于控制器的特性在其他控制器上传送任务以执行任务,其中 需要输入和输出过程或使用存储在特定控制器中的数据。

      解决方案:为了执行特定于控制器在其他控制器上执行的传输任务,转移控制器具有在存储区域中收集输入数据和上下文信息并将其传送到目的地控制器的功能, 其原有功能。 目的地控制器设置有将从传送控制器发送的数据存储在存储区域中的功能,执行计算,并将结果返回给传送控制器。 执行计算处理的任务的程序包括在目的地控制器和传送控制器中,并且目的地控制器使用用于处理该任务的适当方法来确定参考地址。 版权所有(C)2007,JPO&INPIT

    • 10. 发明专利
    • ARITHMETIC UNIT AND INFORMATION PROCESSOR USING THE ARITHMETIC UNIT
    • JP2003177911A
    • 2003-06-27
    • JP2001379549
    • 2001-12-13
    • HITACHI LTD
    • YAMADA TETSUYAARAKAWA FUMIO
    • G06F7/00G06F9/30
    • PROBLEM TO BE SOLVED: To provide a computing unit which can decrease the number of bits used for operation. SOLUTION: Operation data are provided with an additional bit representing size information and according to the size information, operation is carried out with minimum data width. Two input data are divided into high-order and low-order parts and size bits S1 and S2 are provided by the data units. When only low-order sides of both the two input data are effective, input data and carry-in CIU of a high-order side adder 107 are fixed to stop the high-order side adder from consuming electric power. Only the low-order side of one input data is effective and the high-order and low-order sides of the other input data are effective, the code of the effective data of the lower-order side are expanded to equalize the data widths of the two inputs to each other and the operation is carried out. When the high-order and low-order sides of the two input data are both effective, the operation is performed by using high-order and low-order computing units 107 and 108. Consequently, it is decided whether high-order and low-order sides are effective or ineffective by the data units to perform operations always with the minimum effective data width and the power consumption is made less than that of conventional computing units which always use the maximum width. COPYRIGHT: (C)2003,JPO