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
    • 9. 发明授权
    • Method and apparatus to perform pipelined denormalization of
floating-point results
    • 执行浮点结果的流水线非规范化的方法和装置
    • US5943249A
    • 1999-08-24
    • US843081
    • 1997-04-25
    • Glen Howard Handlogten
    • Glen Howard Handlogten
    • G06F5/01G06F7/52
    • G06F5/012
    • A method of processing a floating-point instruction (including a multiply-add instruction) in a floating-point processor. Prior-art techniques require prenormalization of intermediate results generated by the floating-point processor, but normalization can sometimes result in an underflow condition, which requires denormalizing the intermediate result. The present invention provides a method of determining an amount to shift the mantissa of the intermediate result to obtain a final result while avoiding ever producing an exponent that is out of range. The invention also allows denormalized numbers to be stored in the floating-point registers in a denormalized form. The method of determining the shift amount first requires a determination of whether both, or only one, of the product and adder operands are denormalized. If both are denormalized, then the shift amount is equal to the addend alignment amount. If, however, at least one of these values is normalized, then a leading zero overlay is used to derive the shift amount.
    • 一种在浮点处理器中处理浮点指令(包括加法指令)的方法。 现有技术需要由浮点处理器产生的中间结果进行正规化,但归一化有时会导致下溢条件,这需要对中间结果进行非规范化。 本发明提供了一种确定用于移动中间结果的尾数以获得最终结果的量的方法,同时避免产生超出范围的指数。 本发明还允许非正规化数字以非规格化的形式存储在浮点寄存器中。 首先确定移位量的方法需要确定乘积和加法器操作数是否被非规范化。 如果两者都非正规化,则移位量等于加数对准量。 然而,如果这些值中的至少一个被归一化,则使用前导零覆盖来导出移位量。
    • 10. 发明授权
    • Method and apparatus for hierarchial scheduling of virtual paths with underutilized bandwidth
    • 具有未充分利用带宽的虚拟路径的层次调度的方法和装置
    • US07362706B2
    • 2008-04-22
    • US10317413
    • 2002-12-12
    • Lyle Edwin GrosbachGlen Howard HandlogtenJames Francis MikosDavid Alan Norgaard
    • Lyle Edwin GrosbachGlen Howard HandlogtenJames Francis MikosDavid Alan Norgaard
    • H04L12/26
    • H04L47/50H04L2012/5679
    • A method and apparatus are provided for implementing hierarchical scheduling of oversubscribed virtual paths with underutilized bandwidth that works for both ATM (cell) and IP (frame) scheduling. A scheduler includes a first calendar for pipes and autonomous flows and a second calendar for pipe flows. A winner of a pipe or an autonomous flow is identified from the first calendar. Responsive to an identified winner pipe, a pipe queue is checked for an associated pipe flow for the winner pipe. Responsive to identifying an empty pipe queue for the winner pipe, a pipe win credit is assigned to the pipe without reattaching the winner pipe to the first calendar. Then a next winner is identified from the first calendar. When a winner pipe flow is identified from the second calendar and the pipe win credit is assigned to the pipe for the winner pipe flow, then the winner pipe flow is serviced without delay.
    • 提供了一种方法和装置,用于实现对于ATM(小区)和IP(帧)调度工作的未充分利用的带宽的超额预订的虚拟路径的分级调度。 调度器包括用于管道和自主流的第一日历和用于管道流的第二日历。 从第一个日历识别管道或自主流的获胜者。 对于确定的胜利者管道,检查管道队列以获得胜利管道的相关管道流量。 响应于为胜利者管道识别空管道队列,将管道赢取信用额度分配给管道,而不将胜利者管道重新连接到第一个日历。 然后从第一个日历识别下一个赢家。 当从第二个日历识别获胜者管道流量,并且将管道信贷分配给胜利者管道的管道时,优胜者管道流程将被无延误地维护。