Microsoft Technology Licensing, LLC

Other

Marius Dumitru

Amir Netz

Cristian Petculescu

Mosha Pasumansky

Paul Jonathon Sanders

Akshai Mirchandani

Alexander Berger

Howard J Dickerman

Richard R Tkachuk

Vasile Paraschiv

Yutong (Jeffrey) Wang

Irina Gorbach

C James MacLennan

Ioan Bogdan Crivat

Raman S Iyer

Thomas P Conlon

Clemens Alden Szyperski

Michael James Coulson

Carlo Aldo Curino

Rathijit Sen

Gregory Lawrence Hughes

Thulusalamatom Krishnamurthi Anand

Matteo Interlandi

Andriy Garbuzov

Anand Bheemarajaiah

Alexandre Tristan St-Cyr

Faisal Mohamood

Theresa Palmer-Boroski

Vjacheslav Min

Yutong Wang

Hans C Lehnert Merino

Xiaoqing Tang

Srinivasan S Turuvekere

Radu C Coman

Surajit J Chaudhuri

Vivek Ravindranath Narasayya

Alexander Gourkov Balikov

Tarique Ashraf Siddiqui

Thierry D'Hers

Adrian Dumitrascu

Rong Jian Guan

Robert B Zare

Edward Melomed

Adrian Ilcu Predescu

Jeffrey Wang

Grzegorz Guzik

Bala Atur

Dmitry Berger

Chu Xu

Valeri Kim

Sergei Gringauze

Krystian Sakowski

Zezhou Huang

Eric DeVerne Jacobsen

Christian Petculescu

A data processing system implements a cache-conscious aggregation framework for cache-efficient top-k aggregation over high cardinality large datasets. The framework leverages skew in the distribution of data in the datasets to minimize data movements within the local caches of the cores of the multicore processors of the data processing system. The framework performs representative sampling on the dataset and utilizes these samples to identify candidate groups in the dataset for the top-k results. The system performs exact aggregations for the candidate groups and performs hashing and pruning on the non-candidate groups in the dataset to identify top-k results included in the non-candidate groups without having to calculate the exact aggregations for the non-candidate groups.

Cache-efficient top-k aggregation over high cardinality large datasets

A method, computer program product, and computing system for optimizing query operations on run length encoding (RLE) data in a parallel processing computing system. Data is received in a plurality of columns of an input table of a parallel processing computing system for query execution; the system determines that at least a portion of the received data in a first number of columns is compressed according to run length encoding (RLE), thereby comprising RLE data columns including RLE data and that the received data in a second number of columns is not compressed according to run length encoding (RLE), thereby comprising non-RLE data columns including non-RLE data. A query operation is executed on the RLE data and the non-RLE data by prioritizing processing of the RLE data columns over processing of the non-RLE data columns.

System and method for accelerating query execution

A method, computer program product, and computing system for processing query operations on run length encoding (RLE), data in a parallel processing computing system. Data for query execution is received at a parallel processing computing system, at least a portion of the data being compressed according to RLE, thereby forming RLE data; and a query operation is executed on the RLE data without performing a decompression operation on the RLE data.

System and method for performing query operations on run length encoded data

Example solutions read compressed data from a file in persistent storage, directly into an in-memory store without decompression. Some examples transcode the compression scheme used by the file into the compression scheme used by the in-memory store whereas, in other examples, the in-memory store is compatible with the compression scheme used by the file. In some examples that use transcoding, radix clustering is used to speed up compression dictionary transcoding. The radix clustering minimizes cache misses, thereby increasing the efficiency of memory access. These approaches significantly improve cold start times when responding to queries.

Reading compressed data directly into an in-memory store

Methods and systems are disclosed for receiving and processing data analysis expressions. A particular method includes receiving a data analysis expression at a pivot table of a spreadsheet. The data analysis expression is executed for a particular cell of the pivot table by determining a context associated with the particular cell, calculating a value of the data analysis expression based on the context, and outputting the calculated value at the particular cell.

Data analysis expressions

A computer-navigable trie structure used in order to represent predicates for matching foreign keys to primary rows in a primary table. The predicates may be wide ranging, and each may be represented by a corresponding descendant path of the trie structure, and defines which foreign keys are to be mapped to the particular row. The trie structure is built by incrementally augmenting the trie structure as each predicate is analyzed. During later use of the trie structure, each foreign key that is a candidate for mapping to one or more parent rows are evaluated. The foreign key is used to navigate through a set of one or more descendant paths of the computer-navigable trie structure. Matching parent rows may then be identified based on the identity of the navigated descendant paths. The foreign key may then be mapped to each of the one or more matching parent rows.

Trie-structure formulation and navigation for joining

In various embodiments, methods and systems for cross-filtering based on configurable direct relationships are provided. A selection of a first endpoint of a first table and a second endpoint of a second table is received. A direct relationship object is configured between the first table and the second table based on the first endpoint and the second endpoint. A cross-filtering direction and endpoint cardinality settings can also be configured for the direct relationship object. The direct relationship object may be configured as a many-to-one, one-to-many, or one-to-one. Automatic cross-filtering is configurable and can be set to cross-filter in one direction, the reverse direction, or both directions, with bidirectional cross filtering being a default configuration. The direct relationship object between the first endpoint and the second is configurable, such that, cross-filtering the first table and the second table to select rows for cross-filtering results is based on the cross-filtering direction.

Bidirectional cross-filtering in analysis service systems

Methods for efficient display of data points in a user interface are performed by systems and apparatuses. Efficient display of data point in a user interface includes maximizing coverage of data points prior to rendering. Coverage is determined using a radius value for represented data points in a data set. The radius may be increased to correspondingly generate additional coverage. Covered data points may be removed from the rendering subset as the radius is set and increased. The radius is increased until the number of represented data points to render is less than a threshold value. Multiple data sets may be efficiently rendered together.

Efficient display of data points in a user interface

Linking of a child table to a parent table in a database system. For a given parent table row, an expression associated with the particular row is identified. The expression may be a semantic expression that comprises something different than or more than an equals expression or a contains expression. The expression might also take as input a field of the parent table other than the primary key of the parent table. For each of multiple (and potentially all) rows of a child table, the expression is evaluated against a foreign key of the corresponding row of the child table. If the foreign key matches the expression, an association is created, and perhaps saved, between the foreign key and the particular row of the parent table. The expressions may differ even down to the granularity of a single row in the parent table, thereby enabling perhaps custom per-row expressions.

Rule-based joining of foreign to primary key

Various technologies pertaining to construction of a query for execution over a cube are described. Tabular data is presented on a displayed on a display screen, where the tabular data represents at least a portion of a data cube. Input is received with respect to the tabular data, and responsive to the input being received, a query is constructed based upon the input. The query is executed over the data cube, resulting in provisioning of a new table.

Constructing queries for execution over multi-dimensional data structures

A relationship amongst multiple relationships between database tables can be specified independent of a query. More specifically, a function (USERELATIONSHIP) can be introduced to the DAX language (Data Analysis Expressions), which provides a way to author formulas that are not evaluated immediately, but that can be evaluated dynamically and concurrently in many different contexts. The function enables a single relationship to be specified in the calculation formula away from the query. This provides a mechanism within the formula that specifies specific relationship(s) that are to be followed when the dynamic expression is evaluated.

Specification of database table relationships for calculation

Growing community of inventors

Sammamish, WA, United States of America

Marius Dumitru