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
    • 4. 发明申请
    • Floating-Point Addition Acceleration
    • 浮点加法
    • US20120239719A1
    • 2012-09-20
    • US13487307
    • 2012-06-04
    • Lawrence A. Rigge
    • Lawrence A. Rigge
    • G06F7/42
    • G06F7/485G06F7/49936
    • Embodiments of the present invention generate a normalized floating-point sum from at least two floating-point addends. The mantissa of an un-normalized floating-point sum is generated. A pointer is generated which indicates the location of the left-most significant digit (LSD) in the mantissa of the un-normalized floating-point sum. A plurality of possible values for the exponent of the normalized floating-point sum are generated, in parallel with each other and in parallel with the mantissa addition, based on a common exponent value (e.g., the largest of the two addends' exponent values). Based on the LSD pointer, one of the possible values is selected as the exponent of the normalized floating-point sum. The mantissa of the un-normalized floating-point sum is normalized to yield the mantissa of the normalized floating-point sum. By generating the possible exponent values in parallel, embodiments of the present invention can result in significant time savings over prior-art methods.
    • 本发明的实施例从至少两个浮点加数生成归一化浮点和。 生成非归一化浮点和的尾数。 产生指示非标准化浮点和的尾数中最高有效位(LSD)的位置的指针。 基于公共指数值(例如,两个加数指数值中的最大值),生成与归一化浮点和指数相关并且与尾数相加并行的多个可能值, 。 基于LSD指针,选择其中一个可能的值作为归一化浮点和的指数。 非归一化浮点和的尾数被归一化以产生标准化浮点和的尾数。 通过平行地产生可能的指数值,与现有技术方法相比,本发明的实施例可以导致显着的时间节省。
    • 6. 发明申请
    • FLOATING-POINT ADDITION ACCELERATION
    • 浮点加速
    • US20100023574A1
    • 2010-01-28
    • US12180759
    • 2008-07-28
    • Lawrence A. Rigge
    • Lawrence A. Rigge
    • G06F7/42
    • G06F7/485G06F7/49936
    • Embodiments of the present invention generate a normalized floating-point sum from at least two floating-point addends. The mantissa of an un-normalized floating-point sum is generated. A pointer is generated which indicates the location of the left-most significant digit (LSD) in the mantissa of the un-normalized floating-point sum. A plurality of possible values for the exponent of the normalized floating-point sum are generated, in parallel with each other and in parallel with the mantissa addition, based on a common exponent value (e.g., the largest of the two addends' exponent values). Based on the LSD pointer, one of the possible values is selected as the exponent of the normalized floating-point sum. The mantissa of the un-normalized floating-point sum is normalized to yield the mantissa of the normalized floating-point sum. By generating the possible exponent values in parallel, embodiments of the present invention can result in significant time savings over prior-art methods.
    • 本发明的实施例从至少两个浮点加数生成归一化浮点和。 生成非归一化浮点和的尾数。 产生指示非标准化浮点和的尾数中最高有效位(LSD)的位置的指针。 基于公共指数值(例如,两个加数指数值中的最大值),生成与归一化浮点和指数相关并且与尾数相加并行的多个可能值, 。 基于LSD指针,选择其中一个可能的值作为归一化浮点和的指数。 非归一化浮点和的尾数被归一化以产生标准化浮点和的尾数。 通过平行地产生可能的指数值,与现有技术方法相比,本发明的实施例可以导致显着的时间节省。
    • 8. 发明授权
    • Floating-point addition acceleration
    • 浮点加法
    • US08214416B2
    • 2012-07-03
    • US12180759
    • 2008-07-28
    • Lawrence A. Rigge
    • Lawrence A. Rigge
    • G06F7/42
    • G06F7/485G06F7/49936
    • Embodiments of the present invention generate a normalized floating-point sum from at least two floating-point addends. The mantissa of an un-normalized floating-point sum is generated. A pointer is generated which indicates the location of the left-most significant digit (LSD) in the mantissa of the un-normalized floating-point sum. A plurality of possible values for the exponent of the normalized floating-point sum are generated, in parallel with each other and in parallel with the mantissa addition, based on a common exponent value (e.g., the largest of the two addends' exponent values). Based on the LSD pointer, one of the possible values is selected as the exponent of the normalized floating-point sum. The mantissa of the un-normalized floating-point sum is normalized to yield the mantissa of the normalized floating-point sum. By generating the possible exponent values in parallel, embodiments of the present invention can result in significant time savings over prior-art methods.
    • 本发明的实施例从至少两个浮点加数生成归一化浮点和。 生成非归一化浮点和的尾数。 产生指示非标准化浮点和的尾数中最高有效位(LSD)的位置的指针。 基于公共指数值(例如,两个加数指数值中的最大值),生成与归一化浮点和指数相关并且与尾数相加并行的多个可能值, 。 基于LSD指针,选择其中一个可能的值作为归一化浮点和的指数。 非归一化浮点和的尾数被归一化以产生标准化浮点和的尾数。 通过平行地产生可能的指数值,与现有技术方法相比,本发明的实施例可以导致显着的时间节省。
    • 9. 发明授权
    • Multi-gain amplifier with input impedance control
    • 具有输入阻抗控制的多增益放大器
    • US07382189B2
    • 2008-06-03
    • US11526855
    • 2006-09-25
    • Jinghong ChenShaorui LiLawrence A. Rigge
    • Jinghong ChenShaorui LiLawrence A. Rigge
    • H03F3/45
    • H03F3/45188H03F1/56H03F3/19H03F2200/222H03F2200/294H03F2200/451H03F2203/45316H03F2203/45332H03F2203/45506H03F2203/45616H03F2203/45704H03F2203/45726H03H7/38
    • In one embodiment, an amplifier circuit has at least one branch and current-source circuitry providing a tail current to the branch, which has at least one load tank, at least one input transistor coupled to the load tank, and variable-impedance circuitry coupled between an input node of the amplifier circuit and the gate of the input transistor. The transconductance of the input transistor can be altered to achieve two or more different gain settings for the amplifier circuit. The variable-impedance circuitry can be controlled to contribute any one of at least two different levels of impedance to the overall input impedance of the amplifier circuit. If the transconductance of the input transistor is reduced, then the variable-impedance circuitry can increase the level of impedance contributed to the overall input impedance of the amplifier circuit such that the overall input impedance of the amplifier circuit remains substantially unchanged.
    • 在一个实施例中,放大器电路具有至少一个分支和电流源电路,其向分支提供尾电流,该分支具有至少一个负载箱,耦合到负载箱的至少一个输入晶体管和耦合到可变阻抗电路 在放大器电路的输入节点和输入晶体管的栅极之间。 可以改变输入晶体管的跨导以实现放大器电路的两个或多个不同的增益设置。 可控制可变阻抗电路可以对放大器电路的整个输入阻抗提供至少两个不同等级的阻抗中的任何一个。 如果输入晶体管的跨导减小,则可变阻抗电路可以增加对放大器电路的总体输入阻抗贡献的阻抗水平,使得放大器电路的总体输入阻抗基本上保持不变。