利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.025 秒)

    Optimizing cache efficiency within application software
    2.
    发明授权
    Optimizing cache efficiency within application software 有权
    优化应用软件中的缓存效率

    公开(公告)号：US07526628B2

    公开(公告)日：2009-04-28

    申请号：US11538312

    申请日：2006-10-03

    申请人： David Michael Pullen ,  Michael Antony Sieweke

    发明人： David Michael Pullen ,  Michael Antony Sieweke

    IPC分类号： G06F12/02

    CPC分类号： G06F12/0802 ,  G06F8/4442 ,  G06F2212/601

    摘要： The present invention finds the optimum organization of compiled code within an application to ensure maximal cache efficiency. A configuration file specifies predefined cache, optimization, and application parameters. The cache parameters include a cache size, cache line size, set associativity, address-to-cache-line mapping algorithm, and set replacement algorithm. The optimization parameters specify the minimum acceptable efficiency level. The application parameters include a list of object modules and functions within those modules. All possible orderings of the modules are stepped through to determine where the specified functions fall within the cache given the location of the function within the module. The function locations in each permutation of the orderings are analyzed to find a solution that matches or beats the optimization parameters.

    摘要翻译： 本发明在应用程序中找到编译代码的最佳组织，以确保最大的缓存效率。 配置文件指定预定义的缓存，优化和应用程序参数。 高速缓存参数包括高速缓存大小，高速缓存行大小，集合关联性，地址到高速缓存行映射算法和集合置换算法。 优化参数指定最小可接受的效率水平。 应用程序参数包括这些模块中对象模块和功能的列表。 模块中的所有可能的排序顺序进行，以确定给定功能在模块内的位置，指定的功能落在缓存中。 分析排序的每个排列中的函数位置，以找到匹配或击败优化参数的解。

    Method and system for efficient rapid loss detection in a bonding system
    3.
    发明申请
    Method and system for efficient rapid loss detection in a bonding system 失效
    一种粘结系统中有效快速损失检测的方法和系统

    公开(公告)号：US20080130649A1

    公开(公告)日：2008-06-05

    申请号：US11606095

    申请日：2006-11-30

    申请人： David Michael Pullen

    发明人： David Michael Pullen

    IPC分类号： H04L12/56

    CPC分类号： H04L47/10 ,  H04L45/245 ,  H04L47/34

    摘要： An apparatus, method, and computer program for efficient rapid loss detection in a channel bonding system. A received packet having a packet sequence number (PSN) not equal to a next expected PSN is queued. A channel counter for a first channel on which the received packet was received is incremented. If all channel counters are non-zero, increment the next expected PSN to equal a lowest queued packet PSN. Forward the queued packet with the lowest queued packet PSN. Decrement a channel counter for a second channel from which the lowest PSN packet is forwarded.

    摘要翻译： 一种用于在通道结合系统中进行快速损失检测的装置，方法和计算机程序。 具有不等于下一个预期PSN的分组序列号（PSN）的接收分组被排队。 接收到接收的分组的第一信道的信道计数器递增。 如果所有通道计数器都为非零，则将下一个预期的PSN递增到等于最低排队分组PSN。 转发具有最低排队分组PSN的排队分组。 递减最小PSN包转发的第二个信道的信道计数器。

    Method and system for efficient rapid loss detection in a bonding system
    4.
    发明授权
    Method and system for efficient rapid loss detection in a bonding system 失效
    一种粘结系统中有效快速损失检测的方法和系统

    公开(公告)号：US07916731B2

    公开(公告)日：2011-03-29

    申请号：US11606095

    申请日：2006-11-30

    申请人： David Michael Pullen

    发明人： David Michael Pullen

    IPC分类号： H04L12/28

    CPC分类号： H04L47/10 ,  H04L45/245 ,  H04L47/34

    摘要： An apparatus, method, and computer program for efficient rapid loss detection in a channel bonding system. A received packet having a packet sequence number (PSN) not equal to a next expected PSN is queued. A channel counter for a first channel on which the received packet was received is incremented. If all channel counters are non-zero, increment the next expected PSN to equal a lowest queued packet PSN. Forward the queued packet with the lowest queued packet PSN. Decrement a channel counter for a second channel from which the lowest PSN packet is forwarded.

    摘要翻译： 一种用于在通道结合系统中进行快速损失检测的装置，方法和计算机程序。 具有不等于下一个预期PSN的分组序列号（PSN）的接收分组被排队。 接收到接收的分组的第一信道的信道计数器递增。 如果所有通道计数器都为非零，则将下一个预期的PSN递增到等于最低排队分组PSN。 转发具有最低排队分组PSN的排队分组。 递减最小PSN包转发的第二个信道的信道计数器。

    Method and system for the fractal compression of data using an integrated circuit for discrete cosine transform compression/decompression
    5.
    发明授权
    Method and system for the fractal compression of data using an integrated circuit for discrete cosine transform compression/decompression 有权
    使用用于离散余弦变换压缩/解压缩的集成电路对数据进行分形压缩的方法和系统

    公开(公告)号：US5923376A

    公开(公告)日：1999-07-13

    申请号：US177235

    申请日：1998-10-22

    申请人： David Michael Pullen ,  Bradley Thomas Howard

    发明人： David Michael Pullen ,  Bradley Thomas Howard

    IPC分类号： G06T9/00 ,  H04N7/26 ,  H04N7/28 ,  H04N7/30 ,  H04N7/50

    CPC分类号： H04N19/94 ,  H04N19/124 ,  H04N19/126 ,  H04N19/147 ,  H04N19/154 ,  H04N19/176 ,  H04N19/19 ,  H04N19/53 ,  H04N19/60 ,  H04N19/61 ,  H04N19/96 ,  H04N19/99

    摘要： A method for compressing related data sets of a sequence is disclosed. The method compares domain blocks from a current frame buffer to range blocks in a previous frame buffer or vector quantization ("VQ") tables to generate codes. The method includes determining an initial codeword that represents a domain block of a current frame buffer in reference to a selected range block in a previous frame buffer. The selected range block is identified by a best measurement determined from an initial type of search performed on a first group of range blocks in the previous frame buffer. A cost factor is generated for coding the initial codeword. A first estimated cost of a codeword representing the domain block in reference to a second range block is determined. The second range block is identified by an estimated best measurement determined for a second type of search performed on a second group of range blocks. The first estimated cost is compared to initial codeword cost and a second type of search is performed in response to the first estimated cost being less than the initial codeword cost. A second codeword is generated that represents the domain block in reference to a second range block that corresponds to an actual best measurement determined by the second type of search and the cost of coding the second codeword is determined. The codeword having the least cost between the initial codeword and the second codeword is selected for representing the domain block.

    摘要翻译： 公开了一种用于压缩序列的相关数据集的方法。 该方法将来自当前帧缓冲器的域块与前一帧缓冲器或矢量量化（“VQ”）表中的范围块进行比较以生成代码。 该方法包括参考前一帧缓冲器中的所选择的范围块来确定表示当前帧缓冲器的域块的初始码字。 所选择的范围块由在先前帧缓冲器中对第一组范围块执行的初始搜索类型确定的最佳测量来标识。 生成用于编码初始码字的成本因子。 确定代表第二范围块的域块的代码字的第一估计成本。 第二范围块由对第二组范围块执行的第二类型的搜索确定的估计最佳测量来识别。 将第一估计成本与初始码字成本进行比较，并且响应于第一估计成本小于初始码字成本来执行第二类型的搜索。 生成第二代码字，其表示对应于由第二类型的搜索确定的实际最佳测量的第二范围块，并确定第二码字的编码成本的域块。 选择在初始码字和第二码字之间具有最小成本的码字来表示域块。

    Upstream channel bonding using legacy maps in a cable communications system
    7.
    发明授权
    Upstream channel bonding using legacy maps in a cable communications system 有权
    在有线通信系统中使用传统地图的上行信道绑定

    公开(公告)号：US08705567B2

    公开(公告)日：2014-04-22

    申请号：US11384409

    申请日：2006-03-21

    申请人： Lisa Voigt Denney ,  Niki Roberta Pantelias ,  A. Scott Hollums ,  Victor T. Hou ,  John Daniel Horton, Jr. ,  David Michael Pullen

    发明人： Lisa Voigt Denney ,  Niki Roberta Pantelias ,  A. Scott Hollums ,  Victor T. Hou ,  John Daniel Horton, Jr. ,  David Michael Pullen

    IPC分类号： H04J3/16 ,  H04W4/00

    CPC分类号： H04J3/1682 ,  H04L12/2801 ,  H04N21/6168

    摘要： A method for increasing upstream bandwidth per cable modem user in a cable communications system that includes a cable modem termination system (CMTS) and a plurality of cable modems is provided. The method permits a cable modem to transmit data to the CMTS on multiple upstream channels simultaneously using a technique called “channel bonding.” Bandwidth allocation is achieved by transmitting from a CMTS to a cable modem a unique bandwidth allocation message for each upstream channel in a bonded group of upstream channels, wherein the combination of unique bandwidth allocation messages collectively allocates requested bandwidth across the bonded group.

    摘要翻译： 提供了一种用于在包括电缆调制解调器终端系统（CMTS）和多个电缆调制解调器的有线通信系统中增加每个电缆调制解调器用户的上行带宽的方法。 该方法允许电缆调制解调器使用称为“信道绑定”的技术同时在多个上行信道上向CMTS发送数据。通过从CMTS向电缆调制解调器发送用于每个上行信道的唯一带宽分配消息来实现带宽分配 绑定的上行信道组，其中，唯一带宽分配消息的组合在绑定组中共同分配请求的带宽。

    Method, system, and computer program product for high performance bonding resequencing
    10.
    发明授权
    Method, system, and computer program product for high performance bonding resequencing 有权
    方法，系统和计算机程序产品，用于高性能键合重新测序

    公开(公告)号：US07751404B2

    公开(公告)日：2010-07-06

    申请号：US11902603

    申请日：2007-09-24

    申请人： David Michael Pullen ,  Niki Pantelias ,  Dannie Gay

    发明人： David Michael Pullen ,  Niki Pantelias ,  Dannie Gay

    IPC分类号： H04L12/28 ,  H04L12/56

    CPC分类号： H04L12/2801 ,  H04L49/9094

    摘要： A method, system, and computer program product for receiving and resequencing a plurality of data segments received on a plurality of channels of a bonding channel set, comprising determining if a sequence number of a received segment matches an expected sequence number. If so, the process includes forwarding the segment for further processing, incrementing the expected sequence number; and forwarding any queued packets corresponding to the expected sequence number and immediately succeeding sequence numbers less than a sequence number of annexed missing segment. If the sequence number of the received segment does not match the expected sequence number, the received segment is queued at a memory location. The address of this location is converted to a segment index. The segment index is stored in a sparse array.

    摘要翻译： 一种用于接收和重新排序在绑定信道集合的多个信道上接收的多个数据段的方法，系统和计算机程序产品，包括确定所接收的段的序列号是否匹配预期序列号。 如果是，则该过程包括转发该段用于进一步处理，递增预期序列号; 并转发与预期序列号相对应的任何排队的分组，并且紧接着小于所附加的丢失分段的序列号的后续序列号。 如果接收到的段的序列号与预期序列号不匹配，则接收到的段在存储位置排队。 该位置的地址将转换为段索引。 段索引存储在稀疏数组中。