专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明申请

US20130262540A1 Transcendental and Non-Linear Components Using Series Expansion 有权
标题翻译：超越和非线性组件使用系列扩展
公开(公告)号：US20130262540A1
公开(公告)日：2013-10-03
申请号：US13435900
申请日：2012-03-30
申请人： Vaughn T. Arnold , Brijesh Tripathi , Albert Kuo
发明人： Vaughn T. Arnold , Brijesh Tripathi , Albert Kuo
IPC分类号： G06F17/17 , G06F7/523 , G06F7/50 , G06F1/03
CPC分类号： G06F7/544 , G06F1/03 , G06F1/0307 , G06F1/0356 , G06F2101/08 , G06F2101/12
摘要： In an embodiment, hardware implementing a transcendental or other non-linear function is based on a series expansion of the function. For example, a Taylor series expansion may be used as the basis. One or more of the initial terms of the Taylor series may be used, and may be implemented in hardware. In some embodiments, modifications to the Taylor series expansion may be used to increase the accuracy of the result. In one embodiment, a variety of bit widths for the function operands may be acceptable for use in a given implementation. A methodology for building a library of series-approximated components for use in integrated circuit design is provided which synthesizes the acceptable implementations and tests the results for accuracy. A smallest (area-wise) implementation which produces a desired level of accuracy may be selected as the library element.
摘要翻译：在一个实施例中，实现先验或其他非线性函数的硬件基于功能的一系列扩展。例如，可以使用泰勒级数展开作为基础。可以使用泰勒级数的一个或多个初始项，并且可以以硬件实现。在一些实施例中，可以使用对泰勒级数展开的修改来提高结果的准确性。在一个实施例中，功能操作数的各种位宽可以被接受以用于给定的实现。提供了一种用于构建用于集成电路设计的串联近似组件库的方法，其综合了可接受的实现并且测试结果的准确性。可以选择产生所需精度水平的最小（区域）实现作为库元件。

52. 发明授权

US07649944B2 Motion vector derivation method, moving picture coding method and moving picture decoding method 有权
标题翻译：运动矢量导出方法，运动图像编码方法和运动图像解码方法
公开(公告)号：US07649944B2
公开(公告)日：2010-01-19
申请号：US11980535
申请日：2007-10-31
申请人： Shinya Kadono , Satoshi Kondo , Makoto Hagai , Kiyofumi Abe
发明人： Shinya Kadono , Satoshi Kondo , Makoto Hagai , Kiyofumi Abe
IPC分类号： H04B1/66 , H04N7/12
CPC分类号： H04N19/52 , G06F1/03 , G06F2101/12 , H04N19/105 , H04N19/124 , H04N19/172 , H04N19/176 , H04N19/30 , H04N19/43 , H04N19/503 , H04N19/51 , H04N19/513 , H04N19/577 , H04N19/587 , H04N19/61 , H04N19/625 , H04N21/2743
摘要： A motion vector derivation unit includes a comparison unit for comparing a parameter TR1 for a reference vector with a predetermined value to determine whether it exceeds the predetermined value or not; a switching unit for switching selection between the maximum value of a pre-stored parameter TR and the parameter TR1 according to the comparison result by the comparison unit; a multiplier parameter table (for multipliers); and a multiplier parameter table (for divisors) for associating the parameter TR1 with a value approximate to the inverse value (1/TR1) of this parameter TR1.
摘要翻译：运动矢量导出单元包括比较单元，用于将参考矢量的参数TR1与预定值进行比较，以确定其是否超过预定值; 切换单元，用于根据比较单元的比较结果切换预存储参数TR的最大值与参数TR1之间的选择; 乘数参数表（用于乘数）; 以及用于将参数TR1与接近该参数TR1的反相值（1 / TR1）的值相关联的乘数参数表（用于除数）。

53. 发明授权

US07467174B2 Processing unit having decimal floating-point divider using Newton-Raphson iteration 有权
标题翻译：具有使用牛顿 - 拉夫逊迭代的十进制浮点除法器的处理单元
公开(公告)号：US07467174B2
公开(公告)日：2008-12-16
申请号：US10983105
申请日：2004-11-05
申请人： Liang-Kai Wang , Michael J. Schulte
发明人： Liang-Kai Wang , Michael J. Schulte
IPC分类号： G06F7/487
CPC分类号： G06F7/496 , G06F1/035 , G06F7/4873 , G06F7/49963 , G06F7/49968 , G06F7/49973 , G06F7/49978 , G06F7/49984 , G06F2101/12 , G06F2207/4911 , G06F2207/5355
摘要： A decimal floating-point divider is described that implements efficient hardware-based techniques for performing decimal floating-point division. The divider uses an accurate piecewise linear approximation to obtain an initial estimate of a divisor's reciprocal. The divider improves the initial estimate of the divisor's reciprocal using a modified form of Newton-Raphson iteration. The divider multiplies the estimated divisor's reciprocal by the dividend to produce a preliminary quotient. The preliminary quotient is rounded to produce the final decimal floating-point quotient.
摘要翻译：描述了十进制浮点除法器，它实现了用于执行十进制浮点除法的高效的基于硬件的技术。分频器使用精确的分段线性近似来获得除数的倒数的初始估计。分割器使用牛顿 - 拉夫逊迭代的修改形式改进了除数的倒数的初始估计。除数将估计除数的倒数与股息相乘以产生初步商。初始商四舍五入以产生最终的十进制浮点商。

54. 发明申请

US20060053192A1 Apparatus and method for implementing efficient arithmetic circuits in programmable logic devices 失效
公开(公告)号：US20060053192A1
公开(公告)日：2006-03-09
申请号：US11264778
申请日：2005-10-31
申请人： Chang Choo , Asher Hazanchuk
发明人： Chang Choo , Asher Hazanchuk
IPC分类号： G06F7/38
CPC分类号： G06F1/03 , G06F2101/12 , G06F2101/16 , H03K19/1733
摘要： Efficient implementation of arithmetic circuits in programmable logic devices by using Look-Up Tables (LUTs) to store pre-calculated values. A table look-up operation is performed in place of complex arithmetic operations. In this way, at the expense of a few LUTs, many logic elements can be saved. This approach is particularly applicable to circuits for calculating reciprocal values and circuits for performing normalized LMS algorithm.

55. 发明授权

US07007058B1 Methods and apparatus for binary division using look-up table 有权
标题翻译：使用查找表进行二分法的方法和装置
公开(公告)号：US07007058B1
公开(公告)日：2006-02-28
申请号：US10190892
申请日：2002-07-08
申请人： Valeri Kotlov
发明人： Valeri Kotlov
IPC分类号： G06F7/50
CPC分类号： G06F7/535 , G06F1/0356 , G06F2101/12 , G06F2207/5355
摘要： Improved methods of operating a digital data processor to perform binary division include estimating reciprocals of at least selected divisors based on value accessed from a look-up table. For divisors in a first numerical range, the estimation can be based on a value stored in a first look-up table at an index defined by the divisor. For divisors in a second numerical range, the estimation can be based on an index that is a bitwise-shifted function of the divisor. The methods can be applied to scalar and vector binary division.
摘要翻译：操作数字数据处理器以执行二进制划分的改进的方法包括基于从查找表访问的值来估计至少选定的除数的倒数。对于第一数值范围的除数，估计可以基于由除数定义的索引处存储在第一查找表中的值。对于第二数值范围的除数，估计可以基于除数的按位移函数的指标。该方法可应用于标量和矢量二进制分割。

56. 发明申请

US20050071401A1 Method and system for approximating sine and cosine functions 有权
标题翻译：近似正弦和余弦函数的方法和系统
公开(公告)号：US20050071401A1
公开(公告)日：2005-03-31
申请号：US10987487
申请日：2004-11-12
申请人： Daniel Clifton
发明人： Daniel Clifton
IPC分类号： G06F1/035 , G06F7/00
CPC分类号： G06F1/0356 , G06F7/483 , G06F2101/08 , G06F2101/10 , G06F2101/12
摘要： A technique for approximating output values of a function based on LaGrange polynomials is provided. Factorization of a LaGrange polynomial results in a simplified representation of the LaGrange polynomial. With this simplified representation, an output value of a function may be determined based on an input value comprising a fixed point input mantissa and an input exponent. Based on a first portion of the fixed point input mantissa, a point value and at least one slope value are provided. At least one slope value is based on a LaGrange polynomial approximation of the function. Thereafter, the point value and the at least one slope value are combined with a second portion of the fixed point input mantissa to provide an output mantissa. Based on this technique, a single set of relatively simple hardware elements may be used to implement a variety of functions with high precision.
摘要翻译：提供了一种用于近似基于LaGrange多项式的函数的输出值的技术。 LaGrange多项式的因式分解导致LaGrange多项式的简化表示。利用这种简化的表示，可以基于包括固定点输入尾数和输入指数的输入值来确定功能的输出值。基于固定点输入尾数的第一部分，提供点值和至少一个斜率值。至少一个斜率值是基于函数的LaGrange多项式近似。此后，将点值和至少一个斜率值与固定点输入尾数的第二部分组合以提供输出尾数。基于这种技术，可以使用一组相对简单的硬件元件来实现高精度的各种功能。

57. 发明申请

US20040233988A1 Motion vector derivation method, dynamic image encoding method, and dynamic image decoding method 有权
标题翻译：运动矢量导出方法，动态图像编码方法和动态图像解码方法
公开(公告)号：US20040233988A1
公开(公告)日：2004-11-25
申请号：US10475655
申请日：2003-10-23
发明人： Shinya Kadono , Satoshi Kondo , Makoto Hagai , Kiyofumi Abe
IPC分类号： H04N007/12
CPC分类号： H04N19/52 , G06F1/03 , G06F2101/12 , H04N19/105 , H04N19/124 , H04N19/172 , H04N19/176 , H04N19/30 , H04N19/43 , H04N19/503 , H04N19/51 , H04N19/513 , H04N19/577 , H04N19/587 , H04N19/61 , H04N19/625 , H04N21/2743
摘要： A motion vector derivation unit (11) includes a comparison unit (20) for comparing a parameter TR1 for a reference vector with a predetermined value to determine whether it exceeds the predetermined value or not; a switching unit (21) for switching selection between the maximum value of a pre-stored parameter TR and the parameter TR1 according to the comparison result by the comparison unit (20); a multiplier parameter table (for multipliers) (22); and a multiplier parameter table (for divisors) (24) for associating the parameter TR1 with a value approximate to the inverse value (1/TR1) of this parameter TR1.
摘要翻译：运动矢量导出单元（11）包括比较单元（20），用于将参考矢量的参数TR1与预定值进行比较，以确定其是否超过预定值; 根据比较单元（20）的比较结果，切换单元（21），用于切换预存储参数TR的最大值与参数TR1之间的选择; 乘数参数表（用于乘数）（22）; 以及用于将参数TR1与接近该参数TR1的逆值（1 / TR1）的值相关联的乘数参数表（用于除数）（24）。

58. 发明申请

US20040167956A1 Method and apparatus for executing division 审中-公开
标题翻译：执行分割的方法和装置
公开(公告)号：US20040167956A1
公开(公告)日：2004-08-26
申请号：US10484163
申请日：2004-01-20
发明人： Jaako Vihriala
IPC分类号： G06F007/52
CPC分类号： G06F7/535 , G06F1/03 , G06F2101/12 , G06F2207/5354 , G06F2207/5356
摘要： A method of executing division and an electronic apparatus implementing the method are provided. In the method, an auxiliary divisor is retrieved from a look-up table stored in the electronic apparatus, the auxiliary divisor being a predetermined number generated by the product of the powers of the integer two and the reciprocal of the divisor. In the method, the division is executed in the electronic apparatus by multiplying the dividend of the division by the auxiliary divisor. The result of the division is scaled in the electronic apparatus in order to represent it in the desired form by shifting the result obtained by multiplying.
摘要翻译：提供一种执行划分的方法和实现该方法的电子设备。在该方法中，从存储在电子设备中的查找表中检索辅助除数，辅助除数是由整数2的幂和乘数的倒数产生的预定数。在该方法中，通过将除法的除数乘以辅助除数来在电子设备中执行除法。在电子设备中对划分的结果进行缩放，以便通过乘以所获得的结果来以期望的形式表示。

59. 发明申请

US20030220953A1 Circuits, systems, and methods implementing approximations for logarithm, inverse logrithm,and reciprocal 有权
标题翻译：电路，系统和方法实现对数，倒数和倒数的近似
公开(公告)号：US20030220953A1
公开(公告)日：2003-11-27
申请号：US10147844
申请日：2002-05-17
申请人： TEXAS INSTRUMENTS INCORPORATED
发明人： Rustin W. Allred
IPC分类号： G06F001/02
CPC分类号： G06F1/0307 , G06F1/035 , G06F2101/12
摘要： A digital signal system (30) for determining an approximate logarithm of a value of x having a base b. The system comprises circuitry (32) for storing x as a digital representation and circuitry for identifying a most significant digit (MSD) of the digital representation. Adjacent the most significant digit is located a set of bits in respective lesser significant bit locations. The system further comprises a table (36) for storing a set of predetermined logarithms having the base b, wherein each of the predetermined logarithms corresponds to a number in a set of numbers. The system further comprises circuitry for addressing the table in response to a first bit group (t) of the set of bits in respective lesser significant bit locations, and in response the table is for outputting a one of the predetermined logarithms corresponding to a first number (Ia) in the set of numbers. Lastly, the system comprises circuitry (38) for outputting the approximate logarithm of the value of x in response to the one of the predetermined logarithms and further in response to a function estimation between logarithms at a first and second endpoint. The first endpoint corresponds to the first number in the set of numbers times a power of b and the second endpoint corresponds to a second number in the set of numbers times the power of b. Further, the function estimation estimates a logarithm at a number located at distance from one of the first and second endpoints, wherein the distance is responsive to a second bit group of the set of bits.
摘要翻译：一种用于确定具有基底b的x的近似对数的数字信号系统（30）。该系统包括用于存储x作为数字表示的电路（32）和用于识别数字表示的最高有效数字（MSD）的电路。邻近最高有效位位于相应较低有效位位置的一组位。该系统还包括一个用于存储一组具有基础b的预定对数的表（36），其中每个预定对数对应于一组数字中的一个数字。系统还包括用于响应于相应较低有效位位置中的位组的第一位组（t）寻址表的电路，并且响应该表用于输出对应于第一数字的预定对数中的一个（Ia）中的数字。最后，该系统包括用于响应于预定对数中的一个输出x的值的近似对数并进一步响应于在第一和第二端点处的对数之间的函数估计的电路（38）。第一个端点对应于一组数字中的第一个数字乘以b的幂，而第二个端点对应于数字集合中的第二个数乘以b的幂。此外，功能估计估计位于距离第一和第二端点之一的距离处的数字上的对数，其中该距离响应该组位的第二位组。

60. 发明授权

US06260054B1 Reciprocal generator using piece-wise-linear segments of varying width with floating-point format 有权
标题翻译：使用具有浮点格式的不同宽度的分段线性段的互易发生器
公开(公告)号：US06260054B1
公开(公告)日：2001-07-10
申请号：US09182349
申请日：1998-10-29
申请人： Andrew Rosman , Tao Lin
发明人： Andrew Rosman , Tao Lin
IPC分类号： G06F752
CPC分类号： G06F1/035 , G06F7/49936 , G06F7/74 , G06F2101/12
摘要： A reciprocal generator is useful for perspective correction for 3D graphics. The input range is divided into many sections. A lookup table contains reciprocal outputs for only two of the sections, the smallest-inputs section and the largest-inputs section. Entries in the table for the smallest section contain a base and a scale factor to indicate the reciprocal value. One entry is provided for each possible input value in the smallest section. This provides high precision where the outputs have the largest values, reducing visible distortions caused by relatively small changes in the large output values. Each section is divided into intervals, with one table entry for each interval. For the largest section, each table entry has an initial reciprocal and a slope of a line approximating the reciprocal curve in that interval. Reciprocals for inputs within the interval are calculated by multiplying an offset into the interval by the slope, and then adding to the initial reciprocal for that interval. Each section is twice as wide as the previous section, but has the same number of intervals. A scale factor is generated by counting a number of leading zeros in the input. Then the input is shifted by the number of leading zeros and input of the table. Thus the inputs are scaled to points within the largest section, so intermediate sections do not have to be stored in the table.
摘要翻译：相互发生器对3D图形的透视校正很有用。输入范围分为多个部分。查找表仅包含两个部分的倒数输出，即最小输入部分和最大输入部分。表中最小部分的条目包含一个基数和一个比例因子，用于指示相互的值。为最小部分中的每个可能的输入值提供一个条目。这提供了高精度，其中输出具有最大值，减少了由大输出值相对小的变化引起的可见失真。每个部分分为间隔，每个间隔有一个表条目。对于最大部分，每个表条目具有初始倒数和接近该间隔中的倒数曲线的线的斜率。通过将间隔中的偏移乘以斜率，然后将该间隔的初始倒数相加来计算间隔内输入的互惠。每个部分的宽度是前一部分的两倍，但间隔时间相同。通过对输入中的前导零的数量进行计数来生成比例因子。然后将输入移动到前导零的数量和表的输入。因此，输入被缩放到最大部分内的点，因此中间部分不必存储在表中。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式