专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明申请

US20160078090A1 OPTIMIZING PARALLEL QUERIES USING INTERESTING DISTRIBUTIONS 有权
标题翻译：使用有趣的分布优化并行查询
公开(公告)号：US20160078090A1
公开(公告)日：2016-03-17
申请号：US14953297
申请日：2015-11-27
申请人： Microsoft Technology Licensing, LLC
发明人： Srinath Shankar , Rimma V. Nehme
IPC分类号： G06F17/30
CPC分类号： G06F17/30466 , G06F17/30445 , G06F17/30486 , G06F17/30525
摘要： The present invention extends to methods, systems, and computer program products for optimizing parallel queries using interesting distributions. For each logical operator in an SQL server MEMO, in a top down manner from a root operator to the leaf operators, interesting distributions for the operators can be identified based on the properties of the operators. Identified interesting distributions can be propagated down to lower operators by annotating the lower operators with the interesting distributions. Thus, a SQL server MEMO can be annotated with interesting distributions propagated top down from root to leaf logical operators to generate an annotated SQL server MEMO. Parallel query plans can then be generated from the annotated SQL server MEMO in a bottom up manner from leaf operators to a root operator. Annotated interesting properties can be used to prune operators, thereby facilitating a more tractable search space for a parallel query plan.
摘要翻译：本发明扩展到用于使用有趣分布来优化并行查询的方法，系统和计算机程序产品。对于SQL服务器MEMO中的每个逻辑运算符，以从根运算符到叶运算符的自顶向下的方式，可以基于运算符的属性来识别运算符的有趣分布。通过用有趣的分布注释较低的运算符，识别出有趣的分布可以传播到较低的运算符。因此，SQL服务器MEMO可以用从上到下从根到叶逻辑运算符传播的有趣的分布进行注释，以生成注释的SQL服务器MEMO。然后可以从底部向上的方式从叶操作符到根操作符从注释的SQL服务器MEMO生成并行查询计划。注释有趣的属性可用于修剪运算符，从而为并行查询计划提供了更易于管理的搜索空间。

32. 发明授权

US09256642B2 Techniques for recommending parallel execution of SQL statements 有权
标题翻译：推荐并行执行SQL语句的技术
公开(公告)号：US09256642B2
公开(公告)日：2016-02-09
申请号：US12827926
申请日：2010-06-30
申请人： Hailing Yu , Peter Belknap , Thierry Cruanes , Benoit Dageville , Karl Dias , Khaled Yagoub
发明人： Hailing Yu , Peter Belknap , Thierry Cruanes , Benoit Dageville , Karl Dias , Khaled Yagoub
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30445
摘要： Techniques for automatically recommending parallel execution of a SQL statement. In one set of embodiments, a first determination can be made regarding whether a SQL statement can be executed in parallel. Further, a second determination can be made regarding whether executing the SQL statement in parallel is faster than executing the statement in serial by a predetermined factor. If the first determination and second determination are positive (i.e., the statement can be executed in parallel and parallel execution is faster by the predetermined factor), a recommendation can be provided indicating that the SQL statement should be executed in parallel. In some embodiments, the recommendation can include a report specifying the degree of performance improvement gained from parallel execution, additional system resources consumed by parallel execution, and other statistics pertaining to the recommended parallel execution plan.
摘要翻译：自动推荐并行执行SQL语句的技术。在一组实施例中，可以首先确定是否可以并行执行SQL语句。此外，可以进行关于并行执行SQL语句是否比以预定因子串行执行语句更快的第二确定。如果第一确定和第二确定是正的（即，可以并行执行语句并且并行执行以预定因子更快），则可以提供指示应该并行执行SQL语句的建议。在一些实施例中，该建议可以包括指定从并行执行获得的性能改进程度的报告，并行执行消耗的附加系统资源以及与推荐的并行执行计划有关的其他统计信息。

33. 发明授权

US09256458B2 Conditionally updating shared variable directory (SVD) information in a parallel computer 有权
公开(公告)号：US09256458B2
公开(公告)日：2016-02-09
申请号：US13718435
申请日：2012-12-18
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Charles J. Archer , James E. Carey , Philip J. Sanders , Brian E. Smith
IPC分类号： G06F9/46 , G06F17/30 , G06F12/08 , H04L29/08
CPC分类号： G06F9/46 , G06F12/0817 , G06F12/0833 , G06F12/084 , G06F17/30345 , G06F17/30445 , H04L67/10
摘要： Methods, parallel computers, and computer program products for conditionally updating shared variable directory (SVD) information in a parallel computer are provided. Embodiments include a runtime optimizer receiving a broadcast reduction operation header. The broadcast reduction operation header includes an SVD key and a first SVD address. The first SVD address is associated with the SVD key in a first SVD associated with a first task. Embodiments also include the runtime optimizer retrieving from a remote address cache associated with the second task, a second SVD address indicating a location within a memory partition associated with the first SVD, in response to receiving the broadcast reduction operation header. Embodiments also include the runtime optimizer determining that the first SVD address does not match the second SVD address and updating the remote address cache with the first SVD address.

34. 发明授权

US09223829B2 Interdistinct operator 有权
标题翻译：区分运算符
公开(公告)号：US09223829B2
公开(公告)日：2015-12-29
申请号：US12982767
申请日：2010-12-30
申请人： Franz Faerber , Christian Bensberg , Lars Fricke
发明人： Franz Faerber , Christian Bensberg , Lars Fricke
IPC分类号： G06F17/30
CPC分类号： G06F17/30466 , G06F17/3033 , G06F17/30445
摘要： A computer-implemented system and method for performing distinct operations on multiple tables of shared memory of parallel computing environments are disclosed. A distinct operation is executed on each table of a plurality of tables, each distinct operation eliminating duplicate data from each table, the executing creating a hierarchy of table pairs and distinct results, the distinct results comprising a reduced row set for each table. Duplicates on each reduced row set are detected to complete the distinct operation on the plurality of tables.
摘要翻译：公开了一种用于在并行计算环境的共享存储器的多个表上执行不同操作的计算机实现的系统和方法。在多个表的每个表上执行不同的操作，每个不同的操作消除来自每个表的重复数据，执行创建表对和不同结果的层次，不同的结果包括每个表的减少的行集合。检测每个缩小的行集上的复制以完成多个表上的不同操作。

35. 发明申请

US20150363465A1 METHOD AND SYSTEM FOR PROCESSING QUERIES OVER DATASETS STORED USING HIERARCHICAL DATA STRUCTURES 审中-公开
标题翻译：使用分层数据结构存储的数据库处理查询的方法和系统
公开(公告)号：US20150363465A1
公开(公告)日：2015-12-17
申请号：US14303077
申请日：2014-06-12
申请人： International Business Machines Corporation
发明人： Rajesh R. Bordawekar , Matthew L. Boyle , Jonathan W. Dale , Vladimir Mordvinov
IPC分类号： G06F17/30
CPC分类号： G06F17/30463 , G06F17/30433 , G06F17/30445 , G06F17/30961
摘要： Systems and methods for processing a query are provided. A method for processing a query of a tree-based dataset, comprises receiving the query, and analyzing the query and the dataset to create an execution plan for the query, wherein creating the execution plan comprises partitioning traversals over the dataset into sequential and parallel components, and distributing the components across a plurality of processing threads that independently traverse their portion of the dataset and compute local results. The method further comprises merging the local results to compute a final result.
摘要翻译：提供了用于处理查询的系统和方法。一种用于处理基于树的数据集的查询的方法，包括接收所述查询，以及分析所述查询和所述数据集以创建所述查询的执行计划，其中创建所述执行计划包括将所述数据集上的遍历分为顺序和并行组件并且将组件分布在多个处理线程中，这些线程独立地遍历其数据集的部分并计算局部结果。该方法还包括合并本地结果以计算最终结果。

36. 发明申请

US20150331907A1 PREFIX BURROWS-WHEELER TRANSFORMATION WITH FAST OPERATIONS ON COMPRESSED DATA 有权
标题翻译：在压缩数据上进行快速操作的前提条件
公开(公告)号：US20150331907A1
公开(公告)日：2015-11-19
申请号：US14277038
申请日：2014-05-13
申请人： Spiral Genetics, Inc.
发明人： Jeremy Bruestle
IPC分类号： G06F17/30
CPC分类号： G06F17/2282 , G06F17/277 , G06F17/30144 , G06F17/30339 , G06F17/30445 , G06F17/30864 , G06F17/30961 , G06F19/22 , H03M7/30 , H03M7/3068
摘要： The Prefix Burrows-Wheeler Transform (“PWBT”) is described to provide data operations on data sets even if the data set has been compressed. Techniques to set up a PWBT, including an offset table and a prefix table, and techniques to apply data operations on data sets transformed by PWBT are also described. Data operations include k-Mer substring search. General applications of techniques using PWBT, such as plagiarism searches and open source clearance, are described. Bioinformatics applications of the PWBT, such as genomic analysis and genomic tagging, are also described.
摘要翻译：描述了Prefix Burrows-Wheeler变换（“PWBT”），即使数据集已被压缩，也可以对数据集进行数据操作。还描述了设置PWBT的技术，包括偏移表和前缀表，以及对由PWBT变换的数据集应用数据操作的技术。数据操作包括k-Mer子字符串搜索。描述了使用PWBT的技术的一般应用，例如剽窃搜索和开源清除。还描述了PWBT的生物信息学应用，如基因组分析和基因组标记。

37. 发明授权

US09189515B1 Data retrieval from heterogeneous storage systems 有权
标题翻译：异构存储系统的数据检索
公开(公告)号：US09189515B1
公开(公告)日：2015-11-17
申请号：US13791453
申请日：2013-03-08
申请人： AMAZON TECHNOLOGIES, INC.
发明人： Karthik Tamilmani , Santosh Kalki
IPC分类号： G06F17/30
CPC分类号： G06F17/30445 , G06F17/30424 , G06F17/30943
摘要： Techniques are described for retrieving data stored in disparate datastores that support different or heterogeneous storage systems. A report description may be received from a user, the report description including multiple query templates for generating queries to retrieve data from the disparate datastores. The report description may be analyzed to determine input parameters for generating the queries. A user interface may be dynamically generated to solicit input values corresponding to the input parameters. On receiving the input values, the system may generate and execute the queries of the query plan, and combine the results based on result combination information included in the report description.
摘要翻译：描述了用于检索存储在支持不同或异构存储系统的不同数据存储中的数据的技术。可以从用户接收报告描述，报告描述包括用于生成查询以从不同数据存储中检索数据的多个查询模板。可以分析报告描述以确定用于生成查询的输入参数。可以动态地生成用户界面以征求对应于输入参数的输入值。在接收输入值时，系统可以生成并执行查询计划的查询，并根据报告描述中包含的结果组合信息组合结果。

38. 发明授权

US09177025B2 Hash-join in parallel computation environments 有权
标题翻译：哈希加入并行计算环境
公开(公告)号：US09177025B2
公开(公告)日：2015-11-03
申请号：US13742034
申请日：2013-01-15
申请人： SAP SE
发明人： Christian Bensberg , Christian Mathis , Frederik Transier , Nico Bohnsack , Kai Stammerjohann
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30466 , G06F17/3033 , G06F17/30445
摘要： According to some embodiments, a system and method for a parallel join of relational data tables may be provided by calculating, by a plurality of concurrently executing execution threads, hash values for join columns of a first input table and a second input table; storing the calculated hash values in a set of disjoint thread-local hash maps for each of the first input table and the second input table; merging the set of thread-local hash maps of the first input table, by a second plurality of execution threads operating concurrently, to produce a set of merged hash maps; comparing each entry of the merged hash maps to each entry of the set of thread-local hash maps for the second input table to determine whether there is a match, according to a join type; and generating an output table including matches as determined by the comparing.
摘要翻译：根据一些实施例，可以通过由多个并发执行执行线程计算第一输入表和第二输入表的连接列的散列值来提供用于关系数据表的并行连接的系统和方法; 将所计算的散列值存储在所述第一输入表和所述第二输入表中的每一个的一组不相交的线程局部散列图中; 通过并行操作的第二多个执行线程来合并第一输入表的一组线程局部散列图，以产生一组合并的散列图; 将合并的散列映射的每个条目与第二输入表的线程局部散列映射集合的每个条目进行比较，以根据连接类型确定是否存在匹配; 以及生成包括通过比较确定的匹配的输出表。

39. 发明申请

US20150302038A1 PARALLELIZED IN-PLACE RADIX SORTING 有权
标题翻译：并行放置RADIX分配
公开(公告)号：US20150302038A1
公开(公告)日：2015-10-22
申请号：US14750363
申请日：2015-06-25
申请人： International Business Machines Corporation
发明人： Rajesh BORDAWEKAR , Daniel BRAND , Minsik CHO , Ulrich FINKLER , Ruchir PURI
IPC分类号： G06F17/30
CPC分类号： G06F17/30345 , G06F17/30324 , G06F17/30445 , G06F17/30598
摘要： Methods for sorting a data set. A data storage is divided into a plurality of buckets that is each associated with a respective key value. A plurality of stripes is identified in each bucket. At least one data stripe set is defined that has one stripe within each respective bucket. An in-place partial bucket radix sort is performed on data items contained within one data stripe set with a first processor using an initial radix. Incorrectly sorted data items are then grouped in each bucket into a respective incorrect data item group within each bucket. A radix sort is then performed using the initial radix on the items within the respective incorrect data item group. A first level sorted output is produced.
摘要翻译：数据集排序方法。数据存储器被分成多个桶，每个桶与相应的键值相关联。在每个桶中识别出多个条纹。定义了至少一个数据条带集，每个数据条带集在每个相应的数据桶中都有一个条对包含在使用初始基数的第一处理器的一个数据条带集内的数据项执行就地部分桶基数排序。然后将不正确排序的数据项目分组到每个存储桶中的每个桶中的相应不正确的数据项组。然后使用相应错误数据项组中的项目上的初始基数执行基数排序。产生一级排序输出。

40. 发明授权

US09165032B2 Allocation of resources for concurrent query execution via adaptive segmentation 有权
公开(公告)号：US09165032B2
公开(公告)日：2015-10-20
申请号：US11986599
申请日：2007-11-21
申请人： Robert M Wehrmeister , Awny K Al-Omari , Subbarao Kakarlamudi , Zbigniew Omanski , Kashif A Siddiqui , Hansjorg Zeller , Peter Friedenbach
发明人： Robert M Wehrmeister , Awny K Al-Omari , Subbarao Kakarlamudi , Zbigniew Omanski , Kashif A Siddiqui , Hansjorg Zeller , Peter Friedenbach
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30445 , G06F17/30545
摘要： An enterprise data warehouse or business intelligence system having a plurality of processors and memory resources. The system includes at least a database server, a workload management system, a query compiler, and a query executor. The database server configured to receive a database query from an application at a database client system. The query compiler configured to prepare the execution plan for the query and compute the number of executive server processes (ESPs) in each ESP layer of the query. The workload management system is configured to generate an affinity value, and the query executor is configured to execute the query. As disclosed herein, placement of the executive server process layers of the query onto processors of the computing system is determined using the affinity value. Other embodiments, aspects and features are also disclosed.

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