利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

58 条记录 (耗时 0.031 秒)

    State relaxation based subsequence removal method for fast static compaction in sequential circuits
    1.
    发明授权
    State relaxation based subsequence removal method for fast static compaction in sequential circuits 失效
    基于状态弛豫的子序列去除方法，用于顺序电路中的快速静态压缩

    公开(公告)号：US6145106A

    公开(公告)日：2000-11-07

    申请号：US1543

    申请日：1997-12-31

    申请人： Srimat Chakradhar ,  Michael S. Hsiao

    发明人： Srimat Chakradhar ,  Michael S. Hsiao

    IPC分类号： G01R31/317 ,  G01R31/28 ,  G01R31/3183 ,  G06F11/22

    CPC分类号： G01R31/318335 ,  G01R31/318371

    摘要： A method for fast static compaction in sequential circuits with finite output states by removing subsequences of test vectors from a vector test set. The method has the following steps: (1) relaxing the output states of the sequential circuits; (2) identifying a candidate subsequence of test vectors from the vector test set for removal; (3) temporarily removing the candidate subsequence of test vectors from the vector test set; (4) performing fault simulation on remaining test vectors from the vector test set; (5) examining fault simulation results against a set of removal criteria; (6) permanently removing the temporarily removed candidate subsequence if said set of removal criteria are met; (7) replacing the temporarily removed candidate subsequence if said set of removal criteria are not met; and (8) repeating steps (1) through (7) until all candidate subsequences of test vectors have been identified.

    摘要翻译： 一种用于通过从矢量测试集中去除测试矢量的子序列，在具有有限输出状态的连续电路中快速静态压缩的方法。 该方法具有以下步骤：（1）放宽顺序电路的输出状态; （2）从用于去除的载体测试集中鉴定测试向量的候选子序列; （3）从矢量测试集中临时移除测试向量的候选子序列; （4）对来自向量测试集的剩余测试向量执行故障模拟; （5）根据一组移除标准检查故障模拟结果; （6）如果满足所述一组移除标准，则永久地移除临时移除的候选子序列; （7）如果不满足所述删除标准的集合，则替换暂时移除的候选子序列; （8）重复步骤（1）至（7），直到所有候选子序列已被鉴定。

    COMPILER FOR X86-BASED MANY-CORE COPROCESSORS
    3.
    发明申请
    COMPILER FOR X86-BASED MANY-CORE COPROCESSORS 有权
    用于基于X86的多个核心协处理器的编译器

    公开(公告)号：US20130055225A1

    公开(公告)日：2013-02-28

    申请号：US13594464

    申请日：2012-08-24

    申请人： Nishkam Ravi ,  Tao Bao ,  Ozcan Ozturk ,  Srimat Chakradhar

    发明人： Nishkam Ravi ,  Tao Bao ,  Ozcan Ozturk ,  Srimat Chakradhar

    IPC分类号： G06F9/45

    CPC分类号： G06F8/4441 ,  G06F8/443 ,  G06F8/451 ,  G06F8/456 ,  G06F9/52

    摘要： A system and method for compiling includes, for a parallelizable code portion of an application stored on a computer readable storage medium, determining one or more variables that are to be transferred to and/or from a coprocessor if the parallelizable code portion were to be offloaded. A start location and an end location are determined for at least one of the one or more variables as a size in memory. The parallelizable code portion is transformed by inserting an offload construct around the parallelizable code portion and passing the one or more variables and the size as arguments of the offload construct such that the parallelizable code portion is offloaded to a coprocessor at runtime.

    摘要翻译： 一种用于编译的系统和方法包括：存储在计算机可读存储介质上的应用的可并行化代码部分，如果可并行化代码部分被卸载，确定要传送到协处理器和/或从协处理器传送的一个或多个变量 。 为一个或多个变量中的至少一个确定开始位置和结束位置作为存储器中的大小。 可并行化代码部分通过在可并行化代码部分周围插入卸载结构并将一个或多个变量和大小作为卸载结构的参数传递来转换，使得可并行化代码部分在运行时被卸载到协处理器。

    Systems and methods for implementing best-effort parallel computing frameworks
    5.
    发明授权
    Systems and methods for implementing best-effort parallel computing frameworks 有权
    实现尽力而为并行计算框架的系统和方法

    公开(公告)号：US08286172B2

    公开(公告)日：2012-10-09

    申请号：US12399195

    申请日：2009-03-06

    申请人： Srimat Chakradhar ,  Anand Raghunathan ,  Jiayuan Meng

    发明人： Srimat Chakradhar ,  Anand Raghunathan ,  Jiayuan Meng

    IPC分类号： G06F9/46

    CPC分类号： G06F9/545 ,  G06F8/00 ,  G06F9/4887 ,  G06F2209/485 ,  G06F2209/542

    摘要： Implementations of the present principles include Best-effort computing systems and methods. In accordance with various exemplary aspects of the present principles, a application computation requests directed to a processing platform may be intercepted and classified as either guaranteed computations or best-effort computations. Best-effort computations may be dropped to improve processing performance while minimally affecting the end result of application computations. In addition, interdependencies between best-effort computations may be relaxed to improve parallelism and processing speed while maintaining accuracy of computation results.

    摘要翻译： 本原则的实施包括尽力而为的计算系统和方法。 根据本原理的各种示例性方面，针对处理平台的应用计算请求可被截取并分类为保证计算或尽力而为计算。 可以降低最大的努力以提高处理性能，同时最小程度上影响应用程序计算的最终结果。 此外，可以放宽努力计算之间的相互依赖性，以提高并行性和处理速度，同时保持计算结果的准确性。

    PARTITIONED ITERATIVE CONVERGANCE PROGRAMMING MODEL
    6.
    发明申请
    PARTITIONED ITERATIVE CONVERGANCE PROGRAMMING MODEL 审中-公开
    分类迭代汇编编程模型

    公开(公告)号：US20120084747A1

    公开(公告)日：2012-04-05

    申请号：US13235988

    申请日：2011-09-19

    申请人： Srimat Chakradhar ,  Reza Farivar ,  Anand Raghunathan

    发明人： Srimat Chakradhar ,  Reza Farivar ,  Anand Raghunathan

    IPC分类号： G06F9/44

    CPC分类号： G06F17/10 ,  G06F9/5066 ,  G06K9/6223

    摘要： Methods and systems for iterative convergence include performing at least one global iteration. Each global iteration includes partitioning input data into multiple input data partitions according to an input data partitioning function, partitioning a model into multiple model partitions according to a model partitioning function, performing at least one local iteration using a processor to compute sub-problems formed from a model partition and an input data partition to produce multiple locally updated models, and combining the locally updated models from the at least one local iteration according to a model merging function to produce a merged model.

    摘要翻译： 用于迭代收敛的方法和系统包括执行至少一个全局迭代。 每个全局迭代包括根据输入数据分区功能将输入数据分割成多个输入数据分区，根据模型划分功能将模型划分为多个模型分区，使用处理器执行至少一个局部迭代，以计算从 模型分区和输入数据分区，以产生多个本地更新的模型，以及根据模型合并功能组合来自至少一个局部迭代的本地更新的模型以产生合并的模型。

    Load balancing on hetrogenous processing cluster based on exceeded load imbalance factor threshold determined by total completion time of multiple processing phases
    10.
    发明授权
    Load balancing on hetrogenous processing cluster based on exceeded load imbalance factor threshold determined by total completion time of multiple processing phases 有权
    基于由多个处理阶段的总完成时间确定的超负荷不平衡因子阈值，对Hetrogenous处理集群进行负载平衡

    公开(公告)号：US09038088B2

    公开(公告)日：2015-05-19

    申请号：US13409872

    申请日：2012-03-01

    申请人： Rajat Phull ,  Srihari Cadambi ,  Nishkam Ravi ,  Srimat Chakradhar

    发明人： Rajat Phull ,  Srihari Cadambi ,  Nishkam Ravi ,  Srimat Chakradhar

    IPC分类号： G06F1/12 ,  G06F9/46 ,  G06F9/50 ,  G06F9/52

    CPC分类号： G06F9/5083 ,  G06F9/5088 ,  G06F9/522

    摘要： Methods and systems for managing data loads on a cluster of processors that implement an iterative procedure through parallel processing of data for the procedure are disclosed. One method includes monitoring, for at least one iteration of the procedure, completion times of a plurality of different processing phases that are undergone by each of the processors in a given iteration. The method further includes determining whether a load imbalance factor threshold is exceeded in the given iteration based on the completion times for the given iteration. In addition, the data is repartitioned by reassigning the data to the processors based on predicted dependencies between assigned data units of the data and completion times of a plurality of the processers for at least two of the phases. Further, the parallel processing is implemented on the cluster of processors in accordance with the reassignment.

    摘要翻译： 公开了用于通过对该过程的数据的并行处理实现迭代过程的用于管理处理器集群上的数据负载的方法和系统。 一种方法包括对于给定迭代中的每个处理器经历的多个不同处理阶段的完成时间进行至少一次迭代过程的监视。 该方法还包括基于给定迭代的完成时间来确定在给定迭代中是否超过负载不平衡因子阈值。 另外，通过基于对于至少两个相位的数据的分配的数据单元和多个处理器的完成时间之间的预测依赖性重新分配数据到处理器来重新分配数据。 此外，根据重新分配，在处理器集群上实现并行处理。