International Business Machines Corporation

Yefim Shuf

Hong Min

Hubertus Franke

Manish Satyapal Gupta

Terence Patrick Purcell

Rajesh Ramkrishna Bordawekar

Xiaowei Shen

You-Chin Gene Fuh

Peter Francis Sweeney

Allan Benjamin Lebovitz

Ou Jin

Dimitri Kanevsky

Rajiv V Joshi

Xiaobo Wang

Genady Grabarnik

Donna N Dillenberger

Ulrich Alfons Finkler

Fen-Ling Lin

Ruiping Li

Patrick Dooling Bossman

Brian Thinh-Vinh Tran

Christopher John Crone

Niall Fraser McCarroll

Dongsheng Chen

Chunfeng Pei

Jonathan Sloan

Akiko Hoshikawa

Marc Snir

James D Johnston, Jr

Zhongliang Zhang

Alex Zlatsin

Matthew C Harvey

Sachin P Sant

In one example, a method for evaluating a system includes obtaining a model of the system that defines a boundary between at least one failure region and a non-failure region for a performance indicator with respect to at least one variable of the system. In one embodiment, obtaining the model involves constructing a new model; however, in other embodiments, obtaining the model involves accepting or retrieving a pre-constructed model is input. The method further includes obtaining importance samples for the at least one variable that are biased to the at least one failure region, and calculating indicator values for the performance indicator by applying the importance samples to the model.

Multi-dimension variable predictive modeling for analysis acceleration

A method of generating synthetic data from a model of a dataset comprises the steps of receiving a model of a dataset, extracting information from the received model, constructing a database view from the extracted information, receiving a query to the constructed database view, and generating synthetic data from the constructed database view according to the received query.

Generating synthetic data

A sequence of one or more input objects are sorted by identifying a property that is exhibited by a sequence of one or more input objects, determining whether each input object from the sequence of one or more input objects exhibits the property, storing each of the one or more input objects into a buffer, wherein an input object is stored in a first buffer if it exhibits the property and an input object is stored in a second buffer if it does not exhibit the property, sorting each of the one or more input objects in each buffer, and merging the one or more input objects in each buffer into a sequence of one or more input objects.

Method for sorting data

Embodiments disclosed herein generally relate to techniques for managing processing of data in computing systems. One embodiment provides a method which includes receiving a set of inputs to apply to at least a first big data definition. Each big data definition encapsulates information specified in the set of inputs into a set of reusable software components. The method also includes generating, based on the reusable software components, a first executable code component for the at least first big data definition. The method further includes deploying the first executable code component to an executing application without interrupting services provided by the executing application to which the first executable code component is deployed.

Big data assistant

The present disclosure relates generally to the field of determining data access patterns associated with different workloads. In various examples, determining data access patterns associated with different workloads may be implemented in the form of systems, methods and/or algorithms. The present disclosure also relates generally to the field of scheduling workloads (and/or recommending scheduling for workloads) based upon the determined data access patterns associated with the different workloads. In various examples, scheduling workloads (and/or recommending scheduling for workloads) may be implemented in the form of systems, methods and/or algorithms.

Optimization of mixed database workload scheduling and concurrency control by mining data dependency relationships via lock tracking

An apparatus and method for efficiently performing a query sort on a data set with duplicate key values is disclosed. The method includes identifying unique key values for a key in a data set after determining that a number of duplicate key values for the key exceed a predefined threshold. The method also includes recording an association of each unique key value with a record in the data set and sorting unique key values. The method further includes storing the unique key values in a sorted order, wherein each unique key value is associated with an appropriate record in the data set.

System and method for an efficient query sort of a data stream with duplicate key values

Techniques for generating a set of one or more materialized query table (MQT) candidates for a workload are provided. The techniques include receiving a workload, wherein the workload comprises a set of one or more queries, generating one or more best matching MQTs (BMQTs) based on one or more query blocks of the one or more queries by removing syntax that is not qualified for a MQT re-write, determining one or more frequently used multi-joins in the workload, using the one or more BMQTs and the one or more frequently used multi-joins to generate a set of one or more workload MQTs (WMQTs), and grouping one or more WMQTs and one or more BMQTs into one or more groups to merge into a set of a smaller number of MQTs and to cover the workload.

Generating materialized query table candidates

Techniques for database table look-up are provided. The techniques include storing one or more column attributes of a database table in a data structure, wherein the data structure also comprises a record identification (RID) column of a table, one or more predicate columns corresponding to the RID column, and a sequence number column that is associated with one or more updated records, generating a key using one or more portions from one or more of the one or more predicate columns, using the key to partition the data structure, wherein partitioning the data structure comprises partitioning the one or more predicate columns for evaluation, and evaluating the one or more predicate columns against the data structure for each matching predicate column-data structure partition.

Database table look-up

Systems and methods for cache replacement monitoring (CRM) are provided. The system includes a monitored cache comprising a monitored cache line set, the monitored cache line set comprising at least one cache line capable of holding data of a monitored address; and a CRM mechanism operatively associated with the monitored cache. The CRM mechanism collects CRM information for the monitored address. The method includes the steps of collecting CRM information for a monitored address in a monitored cache; and recording the CRM information for the monitored address, when at least one of (1) the monitored address is cached in the monitored cache, (2) the monitored address is replaced in the monitored cache, (3) any cache line in a cache line set corresponding to the monitored address is cached in the monitored cache, and (4) any cache line in a cache line set corresponding to the monitored address is replaced in the monitored cache.

Cache line replacement monitoring and profiling

A database query is partitioned into an initial partition including a plurality of parallel groups, and is executed, via an execution plan, based on the initial partition. A sampling subset of data is identified from the plurality of parallel groups. Substantially in parallel with the executing of the query, the execution plan is executed on the sampling subset of data as a sampling thread. The execution plan is modified based on feedback from the execution of the execution plan on the sampling subset of data.

Method, apparatus, and computer program product for adaptive query parallelism partitioning with look-ahead probing and feedback

A system and method for managing computer operations according to stored user preferences is disclosed. The system includes a calendar module for scheduling an event and centrally storing the user preferences regarding the computer operations during the event, and a controller module for retrieving the user preferences centrally stored in the calendar module and centrally controlling the computer operations according to the user preferences during the event.

System and method for managing computer operations according to stored user preferences

Techniques for storage allocation of a data record are provided. The techniques include attempting to identify a first location for storing a data record, wherein the data record comprises one or more data record attributes, if the first location is identified, selecting the first location for storing the data record, and if the first location is not identified, identifying a second location for storing the data record using a cost penalty function and selecting the second location for storing the data record based on the cost penalty function.

Storage allocation

Techniques for partitioning a query are provided. The techniques include establishing one or more criterion for partitioning a query, wherein the query comprises one or more tables, materializing a first of the one or more tables, partitioning the first of the one or more tables until the one or more criterion have been satisfied, and partitioning and joining a remainder of the one or more tables of the query.

Method for partitioning a query

A computer system and method for compiling a program, where the program executes pointer assignments from a source object to a destination object, each source object being addressable through a first pointer and each destination object being addressable through a second pointer. The system and method eliminate write barrier code from association with compiled program code when the first pointer points to a source object whose type is prolific, eliminate write barrier code from association with compiled program code when the second pointer points to a destination object whose type is non-prolific, and associate write barrier code with compiled program code when the source object is non-prolific and the destination object is prolific. Additionally, the system and method can determine not to associate write barrier code with a compiled program code if the second pointer points to a destination object whose type is non-prolific and if the first pointer points to a source object whose type is prolific.

Growing community of inventors

Yorktown Heights, NY, United States of America

Yefim Shuf