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
    • ARCHITECTURE RE-UTILIZING COMPUTATIONAL BLOCKS FOR PROCESSING OF HETEROGENEOUS DATA STREAMS
    • 架构重新利用异构数据流处理的计算块
    • US20090077359A1
    • 2009-03-19
    • US11945743
    • 2007-11-27
    • Hari ChakravarthulaChristopher J. LooJose Mendez
    • Hari ChakravarthulaChristopher J. LooJose Mendez
    • G06F9/30
    • G06F17/153G06T1/20G06T5/20
    • An architecture for heterogeneous data processing which reuses the same hardware to process different data in different manners is disclosed. The different processing has a substantial similarity; such as performing different variations of a computation. For example, the computation may involve the same mathematical operations but use different constants or coefficients, or performing similar arithmetic operations that can be switched such as addition and subtraction, or performing arithmetic operations in different orders, etc. The different processing might be applying different convolution kernels depending on the pixel color. The differences between the kernels could include different kernel sizes, different coefficient locations, and different coefficient values. The same hardware is re-used for all of the similar computations, under the control of external control logic that allows hardware re-use.
    • 公开了一种用于异构数据处理的架构,其重复使用相同的硬件以不同的方式处理不同的数据。 不同的处理方式有很大的相似性; 例如执行计算的不同变化。 例如,计算可以包括相同的数学运算,但使用不同的常数或系数,或执行可以切换的类似算术运算,例如加法和减法,或以不同的顺序执行算术运算等。不同的处理可能是应用不同的 取决于像素颜色的卷积内核。 内核之间的差异可能包括不同的内核大小,不同的系数位置和不同的系数值。 在所有类似的计算中,相同的硬件被重新用于允许硬件重用的外部控制逻辑的控制。
    • 5. 发明授权
    • Efficient implementations of kernel computations
    • 内核计算的高效实现
    • US08417759B2
    • 2013-04-09
    • US11939456
    • 2007-11-13
    • Hari ChakravarthulaChristopher LooJose Mendez
    • Hari ChakravarthulaChristopher LooJose Mendez
    • G06F17/16
    • G06F17/153G06T5/20G06T2207/10024
    • A method and apparatus for efficiently performing digital signal processing is provided. In one embodiment, kernel matrix computations are simplified by grouping similar kernel coefficients together. Each coefficient group contains only coefficients having the same value. At least one of the coefficient groups has at least two coefficients. Techniques are disclosed herein to efficiently apply successive first order difference operations to a data signal. The techniques allow for a low gate count. In particular, the techniques allow for a reduction of the number of multipliers without increasing clock frequency, in an embodiment. The techniques update pixels of a data signal at a rate of two clock cycles per each pixel, in an embodiment. The techniques allow hardware that is used to process a first pixel to be re-used to start the processing of a second pixel while the first pixel is still being processed.
    • 提供了一种有效执行数字信号处理的方法和装置。 在一个实施例中,通过将相似的内核系数分组在一起来简化核矩阵计算。 每个系数组仅包含具有相同值的系数。 至少一个系数组具有至少两个系数。 本文公开的技术有效地将连续的一阶差分运算应用于数据信号。 这些技术允许低门数。 具体地,在一个实施例中,这些技术允许减少乘法器的数量而不增加时钟频率。 在一个实施例中,这些技术以每个像素的两个时钟周期的速率更新数据信号的像素。 这些技术允许用于处理要重新使用的第一像素的硬件,以在第一像素仍在处理时开始第二像素的处理。
    • 7. 发明申请
    • EFFICIENT IMPLEMENTATIONS OF KERNEL COMPUTATIONS
    • KERNEL计算的有效实施
    • US20080250094A1
    • 2008-10-09
    • US11939456
    • 2007-11-13
    • Hari ChakravarthulaChristopher LooJose Mendez
    • Hari ChakravarthulaChristopher LooJose Mendez
    • G06F17/16
    • G06F17/153G06T5/20G06T2207/10024
    • A method and apparatus for efficiently performing digital signal processing is provided. In one embodiment, kernel matrix computations are simplified by grouping similar kernel coefficients together. Each coefficient group contains only coefficients having the same value. At least one of the coefficient groups has at least two coefficients. Techniques are disclosed herein to efficiently apply successive first order difference operations to a data signal. The techniques allow for a low gate count. In particular, the techniques allow for a reduction of the number of multipliers without increasing clock frequency, in an embodiment. The techniques update pixels of a data signal at a rate of two clock cycles per each pixel, in an embodiment. The techniques allow hardware that is used to process a first pixel to be re-used to start the processing of a second pixel while the first pixel is still being processed.
    • 提供了一种有效执行数字信号处理的方法和装置。 在一个实施例中,通过将相似的内核系数分组在一起来简化核矩阵计算。 每个系数组仅包含具有相同值的系数。 至少一个系数组具有至少两个系数。 本文公开的技术有效地将连续的一阶差分运算应用于数据信号。 这些技术允许低门数。 具体地,在一个实施例中,这些技术允许减少乘法器的数量而不增加时钟频率。 在一个实施例中,这些技术以每个像素的两个时钟周期的速率更新数据信号的像素。 这些技术允许用于处理要重新使用的第一像素的硬件,以在第一像素仍在处理时开始第二像素的处理。
    • 8. 发明申请
    • Overlaminated pressure-sensitive adhesive construction
    • 叠层压敏胶结构
    • US20050191486A1
    • 2005-09-01
    • US11119481
    • 2005-04-28
    • William ScholzEric SuNorman ContiJohannes SchutDavid ScanlanSteven VargasRonald UgolickJose MendezEdward Sun
    • William ScholzEric SuNorman ContiJohannes SchutDavid ScanlanSteven VargasRonald UgolickJose MendezEdward Sun
    • C09J7/02G09F3/10B32B7/12
    • G09F3/10C09J7/35Y10T156/11Y10T428/14Y10T428/1405Y10T428/1452Y10T428/1462Y10T428/1471Y10T428/1476Y10T428/1486Y10T428/24851Y10T428/24868Y10T428/24876Y10T428/28Y10T428/2848
    • Overlaminated faceless PSA label constructions of this invention comprise a low material cost, thin prelaminate PSA construction having a layer of pressure-sensitive material disposed on a release surface of a removable substrate, and a nonblocking continuous film disposed over a surface of the layer of pressure-sensitive adhesive to render the pressure-sensitive adhesive tack free. An optically transparent overlaminate film layer is disposed over the nonblocking continuous film, and a printed indicia is interposed between the overlaminate film layer and nonblocking continuous film. The prelaminate PSA construction does not include a conventional facestock formed from paper, cardboard or plastic, and is highly conformable. The overlaminated film layer can be applied to the prelaminate faceless PSA construction by pressure lamination, via a further PSA layer interposed between continuous film and the overlaminate film layer, or by heat and pressure by forming one of the continuous film or overlaminate film layers from a heat-activatable material that itself forms a laminating adhesive surface. Alternatively, the overlaminate film layer can be applied to the prelaminate PSA construction as a film-forming material. The overlaminated PSA construction has a sufficient Gurley stiffness to permit high-speed converting and dispensing by peel plate equipment without sacrificing the high degree of conformity provided by the underlying prelaminate PSA construction.
    • 本发明的无覆盖的无标签PSA标签结构包括低材料成本,薄的预层压PSA结构,其具有设置在可移除基底的释放表面上的压敏材料层,以及设置在压力层表面上的非阻塞连续膜 敏感粘合剂,以使压敏粘合剂无粘性。 将光学透明的层叠膜设置在非阻挡连续膜上,印刷标记介于层叠膜层和非阻挡连续膜之间。 预层压PSA结构不包括由纸,纸板或塑料形成的常规面料,并且是高度一致的。 叠层膜可以通过压力层压,通过介于连续膜和层叠膜层之间的另一粘合剂层,或通过加热和压力,通过从一层连续膜或覆盖膜层中形成一层 本身形成层压粘合剂表面的可热激活的材料。 或者,叠层膜层可以作为成膜材料应用于预层压PSA结构。 叠层PSA结构具有足够的Gurley刚度,以允许剥离板设备进行高速转换和分配,而不会牺牲基础的预层压PSA结构提供的高度一致性。