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
    • BUTTERFLY ARITHMETIC CIRCUIT
    • JPS6373473A
    • 1988-04-04
    • JP21843686
    • 1986-09-17
    • TOSHIBA CORP
    • YAGUCHI TOSHIYUKI
    • G06F17/14F02B75/02
    • PURPOSE:To shorten the time required for butterfly arithmetic of 1/2 word length by adopting the constitution of both a multiplier and an ALU that can divide arithmetic into high-order and low-order bits. CONSTITUTION:At the time of arithmetic mode of 1/2 word length data a multiplier MPY and arithmetic circuits ALU1 and 2 divide their arithmetic operations into high-order n/2 bits XH and YH and low-order n/2 bits XL and YL respectively. In other words, the high-order n/2 bits of XH.YH are inputted to the most significant n/2 bit of the multiplication result 2n of the multiplier MPY together with the high-order n/2 bits of XL.YL inputted to the next n/2 bit, the low-order n/2 bits of XH.YH inputted to the following n/2 bit, and the low-order n/2 bits of XL.YL inputted to the least significant n/2 bit respectively. In the circuits ALU1 and 2 the arithmetic result of XH.YH is inputted to the high-order n/2 bit of the arithmetic (n) bits together with the arithmetic result of XL.YL supplied to the low-order n/2 bit respectively. Thus it is possible to carry out the butterfly arithmetic of 1/2 word length in a 1-butterfly/2-cycle way and therefore to shorten the butterfly arithmetic time.
    • 2. 发明专利
    • Data location converter
    • JP2004021932A
    • 2004-01-22
    • JP2002180293
    • 2002-06-20
    • Toshiba Corp株式会社東芝
    • IZUMIYAMA HIDEOMIAKEMI KAZUHIROYAGUCHI TOSHIYUKI
    • G06F12/02
    • PROBLEM TO BE SOLVED: To omit an alignment process of pieces of data in a CPU, and provide high speed calculation and a high speed rearranging process or the like of the pieces of data in the CPU.
      SOLUTION: The data location converter is disposed between the CPU capable of processing data in parallel and a memory storing predetermined data in each address. It is provided with an address comparator comparing address signals inputted from the CPU and outputting a rearrangement control signal when particular addresses are assigned, a memory control part reading a plurality of pieces of data stored in the addresses when the rearrangement control signal is supplied and controlling the pieces of data read from the assigned addresses of the memory along with their addresses, and a rearranging process part executing a realignment process of data by address rearrangement and predetermined calculation to the plurality of pieces of data read from the assigned addresses of the memory via the memory control part on the basis of the rearrangement control signal.
      COPYRIGHT: (C)2004,JPO
    • 3. 发明专利
    • MICROPROCESSOR
    • JPH08101820A
    • 1996-04-16
    • JP23780394
    • 1994-09-30
    • TOSHIBA CORP
    • FUJIMURA HIRONORIYAGUCHI TOSHIYUKI
    • G06F1/32G06F9/30G06F15/78
    • PURPOSE: To make a circuit not operate at a data pass part and reduce the power consumption by keeping on supplying a control signal which is supplied so far to the data pass part when no operation is performed mat the data pass part. CONSTITUTION: When no operation is performed at the data pass part 4 (at NOP time), a signal CC=0 is inputted as the control signal of a latch 12 according to the decoding result of an instruction by an instruction decoding part 1, so the C latch performs no latching operation. Consequently, the instruction decoding part 1 outputs control signals CLI and CLO=0 so that neither of output latches 5 and 7 performs latching operation while the control signal CO=A is outputted to the data pass part 4. Therefore, the input data DI and control signal CO never change at the data pass part 4, so no switching is done. Consequently, when the data pass part 4 performs no operation, the data pass part 4 does not operate and the power consumption is reducible.
    • 8. 发明专利
    • TEST FACILITATING CIRCUIT
    • JPH01227973A
    • 1989-09-12
    • JP5375388
    • 1988-03-09
    • TOSHIBA CORP
    • YAGUCHI TOSHIYUKI
    • G01R31/317G01R31/28G06F11/22
    • PURPOSE:To make a testing time shorter by comparing optional output data of plural functional circuits to which input test signals are given with the values of the circuits at the time of normal operation and, at the same time, collating whether or not the optional output data are coincident with the data of other functional circuits. CONSTITUTION:Input test data TD selected at the time of testing operation are given to (m) pieces of functional circuits T1, Tm and the circuits T1,-,Tm respectively output N-bit output data. In such state, the output data of an optional functional circuit T1 are compared with the values of the circuit T1 at the time of normal operation and, when they coincide with each other, it is confirmed that the circuit T1 normally operates. Then the exclusive OR gate of a discriminating section takes the exclusive OR of the output data of each functional circuit and, when it is discriminated that all of the output data are the same from the calculated results, normal operations of all functional circuits are confirmed. Therefore, the testing time can be shortened.
    • 10. 发明专利
    • Floating point multiplier
    • 浮动点乘法器
    • JPS59117637A
    • 1984-07-07
    • JP22800282
    • 1982-12-24
    • Toshiba Corp
    • YAGUCHI TOSHIYUKIKANUMA AKIYOSHITAMARU KIICHIROU
    • G06F7/487G06F7/00G06F7/508G06F7/52G06F7/76
    • G06F7/4876G06F7/4991
    • PURPOSE: To execute the floating point multiplication of IEEE standard with one adder, by correcting the input or the output of an exponential part adder.
      CONSTITUTION: The multiplication is executed by adding an exponential part in an adder ALU. The floating point multiplication of IEEE standard is expressed with a form of the subtraction of a base B from addition of inputs X and Y. The subtraction of the base B from the operand X is attained by the addition of the operand X and the complement of the base B, and in this case, necessity of carry occurs in the addition result in accordance with the state of the most significant bit MSB of the operand X. The operation between the operand X and the base B is terminated by considering carry with respect to the inverted result of the MSB of the operand X in an inverter 103. Consequently, the operand X is corrected by the inverter 103 and is inputted to an ALU101, and the operand Y is inputted as it is, thus terminating the multiplication.
      COPYRIGHT: (C)1984,JPO&Japio
    • 目的:通过一个加法器执行IEEE标准的浮点乘法,通过校正指数部分加法器的输入或输出。 构成:通过在加法器ALU中添加指数部分来执行乘法。 IEEE标准的浮点乘法以从输入X和Y的加法中减去基数B的形式表示。通过添加操作数X和操作数X的补码,可以从操作数X中减去基数B 基本B,并且在这种情况下,根据操作数X的最高有效位MSB的状态在相加结果中发生进位的必要性。操作数X与基准B之间的操作通过考虑到 反转器103中的操作数X的MSB的反相结果。因此,操作数X被逆变器103校正并被输入到ALU101,并且操作数Y被原样输入,从而终止乘法。