利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

37 条记录 (耗时 0.031 秒)

    Variable reordering (Mux) instructions for parallel table lookups from registers
    1.
    发明授权
    Variable reordering (Mux) instructions for parallel table lookups from registers 失效
    来自寄存器的并行表查找的可变重排序（Mux）指令

    公开(公告)号：US07424597B2

    公开(公告)日：2008-09-09

    申请号：US10403785

    申请日：2003-03-31

    申请人： Ruby B. Lee ,  Dale Morris

    发明人： Ruby B. Lee ,  Dale Morris

    IPC分类号： G06F9/312 ,  G06F9/315

    CPC分类号： G06F9/30032 ,  G06F9/3004

    摘要： Parallel table lookups are implemented using variable Mux instructions to reorder data. Table data can be represented in a “table” register, while the desired ordering can be represented in an “Index” register. A direct variable Mux instruction can specify the table register and the index register as arguments, along with a result register. The instruction writes at least some of the data from the table register into the result register as specified in the index register. If the entire table cannot fit within a single register, entries can be divided between two or more table registers. An indirect variable Mux instruction can specify both a table-register-select register and a subword-location-select register. Both the direct and indirect Mux instructions can be used with entry data that is divided in accordance with significance between registers. In that case, plural Mux instructions are used with UnPack instructions that concatenate portions of the table entries.

    摘要翻译： 使用变量Mux指令实现并行表查找，以重新排序数据。 表数据可以在“表”寄存器中表示，而所需的顺序可以在“索引”寄存器中表示。 直接变量Mux指令可以指定表寄存器和索引寄存器作为参数，以及结果寄存器。 该指令将表寄存器中的至少一些数据写入索引寄存器中指定的结果寄存器。 如果整个表不能放在单个寄存器中，则可以在两个或多个表寄存器之间划分条目。 间接变量Mux指令可以指定表寄存器选择寄存器和子字选择寄存器。 直接和间接MUX指令都可以与根据寄存器之间的重要性划分的条目数据一起使用。 在这种情况下，多个Mux指令用于连接表项部分的UnPack指令。

    Image matching using pixel-depth reduction before image comparison
    2.
    发明授权
    Image matching using pixel-depth reduction before image comparison 有权
    图像比较前使用像素深度缩小的图像匹配

    公开(公告)号：US07274825B1

    公开(公告)日：2007-09-25

    申请号：US10403754

    申请日：2003-03-31

    申请人： Ruby B. Lee ,  Dale Morris

    发明人： Ruby B. Lee ,  Dale Morris

    IPC分类号： G06K9/36

    CPC分类号： H04N19/59 ,  H04N19/51 ,  H04N19/56

    摘要： A block-matching method reduces pixel depth prior to match evaluation to drastically reduce the computations required intensive block-matching applications such motion estimation for video compression. Pixel-depth reduction is achieved by analyzing incorporating images to determine how to reduce pixel depth so as to retain information useful for block matching. Original pixel values (e.g., 8-bit), are compressed to lower-depth (e.g., e.g., 1-bit or 1.6-bit) pixel values. The resulting converted blocks are XORed to yield a comparison image. The 1s in the comparison image are tallied to provide a match measure. In the image analysis, the original images can be subsampled and averages can be computed based on the subsample pixels to reduce computational overhead.

    摘要翻译： 块匹配方法在匹配评估之前减少像素深度，以显着减少计算所需的密集块匹配应用程序，用于视频压缩的运动估计。 通过分析并入图像来确定如何减少像素深度以便保留有用于块匹配的信息来实现像素深度减小。 原始像素值（例如，8位）被压缩到较低深度（例如，1比特或1.6比特）的像素值。 将所得到的经转换的块进行异或以产生比较图像。 比较图像中的1s被计数以提供匹配度量。 在图像分析中，原始图像可以被二次采样，并且可以基于子样本像素来计算平均值，以减少计算开销。

    Biomarkers and assays for carcinogenesis
    4.
    发明申请
    Biomarkers and assays for carcinogenesis 审中-公开
    生物标志物和致癌作用的测定

    公开(公告)号：US20060063177A1

    公开(公告)日：2006-03-23

    申请号：US11189064

    申请日：2005-07-25

    申请人： Roderick Bunch ,  Dale Morris ,  Sandra Curtiss ,  Charles Rodi

    发明人： Roderick Bunch ,  Dale Morris ,  Sandra Curtiss ,  Charles Rodi

    IPC分类号： C12Q1/68

    摘要： The present invention relates to carcinogenesis biomarkers produced by phenobarbitol-treated rat hepatocytes, nucleic acid molecules that encode carcinogenesis biomarkers or a fragment thereof and nucleic acid molecules that are useful as probes or primers for detecting or inducing carcinogenesis, respectively. The invention also relates to applications of the factor or fragment such as forming antibodies capable of binding the carcinogenesis biomarkers or fragments thereof.

    摘要翻译： 本发明涉及由苯巴比妥治疗的大鼠肝细胞产生的致癌生物​​标志物，编码致癌生物标志物的核酸分子或其片段，以及可用作探测或诱导癌发生的探针或引物的核酸分子。 本发明还涉及因子或片段的应用，例如形成能够结合致癌生物标志物或其片段的抗体。

    Multiprocessor system having plural memory locations for respectively storing TLB-shootdown data for plural processor nodes
    6.
    发明授权
    Multiprocessor system having plural memory locations for respectively storing TLB-shootdown data for plural processor nodes 失效
    具有用于分别存储用于多个处理器节点的TLB击落数据的多个存储器位置的多处理器系统

    公开(公告)号：US07281116B2

    公开(公告)日：2007-10-09

    申请号：US10903200

    申请日：2004-07-30

    申请人： Jonathan K. Ross ,  Dale Morris

    发明人： Jonathan K. Ross ,  Dale Morris

    IPC分类号： G06F12/00

    CPC分类号： G06F12/1027 ,  G06F2212/682

    摘要： The present invention provides a multiprocessor system and method in which plural memory locations are used for storing TLB-shootdown data respectively for plural processors. In contrast to systems in which a single area of memory serves for all processors' TLB-shootdown data, different processors can describe the memory they want to free concurrently. Thus, concurrent TLB-shootdown request are less likely to result in performance-limiting TLB-shootdown contentions that have previously constrained the scaleability of multiprocessor systems.

    摘要翻译： 本发明提供一种多处理器系统和方法，其中使用多个存储器位置来分别存储用于多个处理器的TLB击倒数据。 与其中单个存储器区域用于所有处理器的TLB击倒数据的系统相反，不同的处理器可以描述他们想要同时释放的存储器。 因此，并发的TLB-downdown请求不太可能导致先前限制多处理器系统可扩展性的性能限制TLB击倒争用。

    Privileged resource access
    7.
    发明申请
    Privileged resource access 审中-公开
    特权资源访问

    公开(公告)号：US20060064528A1

    公开(公告)日：2006-03-23

    申请号：US10944266

    申请日：2004-09-17

    申请人： Donald Soltis, ,  Dale Morris

    发明人： Donald Soltis, ,  Dale Morris

    IPC分类号： G06F13/24

    CPC分类号： G06F13/24

    摘要： At least one entry in an original interrupt vector table is replaced with an instruction set to handle access to a privileged resource. An operating system privilege level is modified to one or more resources. Subsequent access to the privileged resource causes an interrupt. Processing of the interrupt is directed to the instruction set to handle access to the privileged resource.

    摘要翻译： 原始中断向量表中的至少一个条目被替换为处理对特权资源的访问的指令集。 操作系统权限级别被修改为一个或多个资源。 对特权资源的后续访问会导致中断。 中断的处理针对指令集来处理对特权资源的访问。

    Multiprocessor system having plural memory locations for respectively storing TLB-shootdown data for plural processor nodes
    8.
    发明申请
    Multiprocessor system having plural memory locations for respectively storing TLB-shootdown data for plural processor nodes 失效
    具有用于分别存储用于多个处理器节点的TLB击落数据的多个存储器位置的多处理器系统

    公开(公告)号：US20060026359A1

    公开(公告)日：2006-02-02

    申请号：US10903200

    申请日：2004-07-30

    申请人： Jonathan Ross ,  Dale Morris

    发明人： Jonathan Ross ,  Dale Morris

    IPC分类号： G06F12/00 ,  G06F12/10

    CPC分类号： G06F12/1027 ,  G06F2212/682

    摘要： The present invention provides a multiprocessor system and method in which plural memory locations are used for storing TLB-shootdown data respectively for plural processors. In contrast to systems in which a single area of memory serves for all processors' TLB-shootdown data, different processors can describe the memory they want to free concurrently. Thus, concurrent TLB-shootdown request are less likely to result in performance-limiting TLB-shootdown contentions that have previously constrained the scaleability of multiprocessor systems.

    摘要翻译： 本发明提供一种多处理器系统和方法，其中使用多个存储器位置来分别存储用于多个处理器的TLB击倒数据。 与其中单个存储器区域用于所有处理器的TLB击倒数据的系统相反，不同的处理器可以描述他们想要同时释放的存储器。 因此，并发的TLB-downdown请求不太可能导致先前限制多处理器系统可扩展性的性能限制TLB击倒争用。

    Multiprocessor system with interactive synchronization of local clocks
    9.
    发明申请
    Multiprocessor system with interactive synchronization of local clocks 有权
    具有本地时钟交互式同步的多处理器系统

    公开(公告)号：US20050033947A1

    公开(公告)日：2005-02-10

    申请号：US10638696

    申请日：2003-08-08

    申请人： Dale Morris ,  Jonathan Ross

    发明人： Dale Morris ,  Jonathan Ross

    IPC分类号： G06F1/12 ,  G06F1/14 ,  G06F9/00 ,  H04J3/06

    CPC分类号： G06F1/14 ,  H04J3/0638

    摘要： A multiprocessor computer system comprises multiple data processors, each with an internal clock for providing time stamps to application software. The processors take turns as synchronization masters. The present master transmits a “request” time stamp (indicating the time of transmission according to the local clock) to the other (“slave”) processors. Each slave processor responds by returning a “response” time stamp (indicating the time of transmission of the response according to the local slave clock) of its own along with the received request time stamp. The master calculates clock adjustment values from the time of receipt of the responses and the included time stamps. This allows asynchronous clocks to be synchronized so that application time stamps can be validly compared across processors.

    摘要翻译： 多处理器计算机系统包括多个数据处理器，每个数据处理器具有用于向应用软件提供时间戳的内部时钟。 处理器轮流作为同步主机。 本主机向另一个（“从”）处理器发送“请求”时间戳（指示根据本地时钟发送的时间）。 每个从属处理器通过根据接收到的请求时间戳返回一个“响应”时间戳（指示根据本地从属时钟发送响应的时间）。 主人从接收到响应时间和包含的时间戳计算时钟调整值。 这允许异步时钟被同步，以便可以在处理器之间有效地比较应用程序时间戳。