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. 发明公开
    • 곱셈 기능을 수행하기 위한 방법 및 장치
    • 用于执行多项功能的方法和装置
    • KR1020100090751A
    • 2010-08-17
    • KR1020100066205
    • 2010-07-09
    • 인텔 코포레이션
    • 탕,핑택피터캐빈,로버트디.
    • G06F7/57G06F7/44G06F7/52
    • G06F7/535G06F7/483G06F7/5443G06F2207/5354G06F2207/5356
    • PURPOSE: A method and an apparatus for performing multiplicative functions are provided to reduce standby time thereof by removing reciprocal calculation. CONSTITUTION: A computing system(100) comprises one or more processors(110) coupled to a system interconnect(115). The processor has multiple or many processing cores. The computing system also includes a chipset(130) coupled to the system interconnect. The chipset includes one or more integrated circuit packages or chips. Chipset comprises one or more device interfaces(135) to support data transfers to and/or from other components(160) of the computing system such as, for example, keyboards, mice, network interfaces, etc. The device interface is coupled with other components through a bus(165). The chipset is coupled to a PCI(Peripheral Component Interconnect) bus(185). The chipset includes a PCI bridge(145) that provides an interface to the PCI bus. The PCI Bridge provides a data path between the processor as well as other components, and peripheral devices such as, for example, an audio device(180). Other devices are also coupled to the PCI bus.
    • 目的:提供一种用于执行乘法函数的方法和装置,以通过去除相互计算来减少其待机时间。 构成:计算系统(100)包括耦合到系统互连(115)的一个或多个处理器(110)。 处理器具有多个或多个处理核心。 计算系统还包括耦合到系统互连的芯片组(130)。 芯片组包括一个或多个集成电路封装或芯片。 芯片组包括一个或多个设备接口(135),以支持向计算系统的其他组件(160)传送数据和/或从计算系统的其他组件(160)传输数据,例如键盘,鼠标,网络接口等。设备接口与其他 部件通过总线(165)。 芯片组耦合到PCI(外围组件互连)总线(185)。 该芯片组包括提供PCI总线接口的PCI桥(145)。 PCI桥提供处理器以及其他组件之间的数据路径,以及外围设备,例如音频设备(180)。 其他设备也耦合到PCI总线。
    • 3. 发明公开
    • 작은 사이즈의 룩업 테이블을 갖는 파이프라인 나눗셈연산기 및 연산방법
    • 具有小尺寸的查看表及其操作方法的管理部分
    • KR1020040011916A
    • 2004-02-11
    • KR1020020045232
    • 2002-07-31
    • 학교법인연세대학교
    • 정웅정종철박우찬이문기한탁돈
    • G06F7/52
    • G06F7/535G06F2207/5354
    • PURPOSE: A pipelined ALU(Arithmetic and Logical Unit) having a lookup table of a small size and an operation method thereof are provided to decrease the size of the lookup table while increasing a delay time by one cycle. CONSTITUTION: A dividend X and a divisor Y have a regulated fixed point. The lookup table(LUT2) stores internal parameters and calculates the 1/(Yh)¬2 by using the divisor. The first multiplier(MUL3) calculates the divisor A by multiplying the 1/(Yh)¬2 of the lookup table to the (Yh-Y1) obtained from the dividend X and the divisor Y. The second and the third multiplier(MUL4,MUL5) calculate and output the AX and the AY by respectively operating the divisor A to the dividend Y and the divisor Y. The fourth multiplier(MUL6) outputs a quotient Q by operating the AX to the bit-inverted 2-AY.
    • 目的:提供具有小尺寸查找表及其操作方法的流水线ALU(算术和逻辑单元),以减小查找表的大小,同时将延迟时间增加一个周期。 构成:股息X和除数Y具有规定的固定点。 查找表(LUT2)存储内部参数,并使用除数计算1 /(Yh)¬2。 第一乘法器(MUL3)通过将查找表的1 /(Yh)¬2与从被除数X和除数Y获得的(Yh-Y1)相乘来计算除数A.第二和第三乘法器(MUL4, MUL5)通过将除数A分配到除数Y和除数Y来计算和输出AX和AY。第四乘法器(MUL6)通过将AX操作到位反转的2-AY来输出商Q。
    • 5. 发明公开
    • 곱셈 기능을 수행하기 위한 방법 및 장치
    • 用于执行多项功能的方法和装置
    • KR1020080089313A
    • 2008-10-06
    • KR1020080030071
    • 2008-03-31
    • 인텔 코포레이션
    • 탕,핑택피터캐빈,로버트디.
    • G06F7/57G06F7/00
    • G06F7/535G06F7/483G06F7/5443G06F2207/5354G06F2207/5356
    • A method and an apparatus for performing multiplicative functions are provided to reduce the latency of the refinement process by removing reciprocal calculation in a critical process of a refinement process. A method for performing multiplicative functions comprises the following several steps. A floating point number X in a format according to which a reciprocal residual unit is implemented is received(610). The X may be normalized to obtain X', namely a normalized value of the X(620). An approximate reciprocal of X' may be obtained from a lookup table(630). A product of X' and reciprocal(X') may be computed by a multiplier(640). Y=1-X'*reciprocal(X') may be computed by using an adder(650). The Y may be normalized such that the most significant bit of the magnitude of the mantissa is non-zero(660). The normalized Y may be rounded and formatted in the desired floating point format(670).
    • 提供了一种用于执行乘法函数的方法和装置,以通过在精细化过程的关键过程中去除相互计算来减少细化过程的等待时间。 执行乘法函数的方法包括以下几个步骤。 接收实现了相互残留单位的格式的浮点数X(610)。 X可以归一化以获得X',即X(620)的归一化值。 可以从查找表(630)获得X'的近似倒数。 乘法器(640)可以计算X'和倒数(X')的乘积。 可以通过使用加法器(650)来计算Y = 1-X'*倒数(X')。 Y可以归一化,使得尾数幅度的最高有效位不为零(660)。 归一化的Y可以被舍入并以所需的浮点格式格式化(670)。