Cadence Design Systems, Inc.

Tabula, Inc.

Amazon Technologies, Inc.

Altera Corporation

Other

Altera Corporaton

Andrew Edward Caldwell

Steven L Teig

Jason Rupert Redgrave

Herman Henry Schmit

Anurag Windlass Gupta

Etienne Jacques

Brad Hutchings

Christopher D Ebeling

Andre Rohe

Jonathan Frankle

Daniel J Pugh

Michail Petropoulos

Marc Howard Beitchman

Martin L Voogel

Scott J Weber

Rahul Sharma Pathak

Shangzhi Sun

Hung Q Nguyen

Timothy J Callahan

Shilpa V Yeole

Akira Fujimura

Mehul A Shah

Jung Ko

Ippokratis Pandis

George Steven McPherson

Naresh Chainani

Trevis Chandler

Prajakta Datta Damle

Xing Wu

Abhishek Rajnikant Sinha

Kent R Townley

Turkay Mert Hocanin

Jason Douglas Denton

Luca Natali

Bhargava Ram Kalathuru

Martin Grund

Jian Fang

Pratik Bhagwat Gawande

Yuanyuan Yue

Sumeetkumar Veniklal Maru

Armen Tangamyan

Yufeng Jiang

Carlos Garcia-Alvarado

Michael Glenn Wrighton

Vijairam Parasuraman

Thomas S Chanack

Bhaven Avalani

John Benjamin Tobler

Stavros Harizopoulos

George Constantin Caragea

Oscar Buset

Sainath Chowdary Mallidi

Venkatraman Govindaraju

Tim Januschowski

Frederick Ryan Johnson

Valentin Flunkert

Steffen Rochel

Fabian Oliver Nagel

Kiran Kumar Chinta

Srividhya Srinivasan

Naveen Muralimanohar

Terence Kelly

Ramakrishna Kotla

Nikolaos Armenatzoglou

Adam S Hartman

Islam Mohamed Hatem A Atta

Arjun Ashok

Burst performance of a database query may be determined according to a size of the database query. A query to a database may be received. A size may be determined for the query. If the size is less than a size threshold assigned to a first query engine, then the query may be performed at the first query engine. If the size is greater than or equal to the size threshold assigned to the first query engine, then the query may be performed at a second query engine.

Burst performance of database queries according to query size

Compiled portions of code generated to perform a query plan at a query engine may be shared with other query engines. A data store, separate from the query engines, may store compiled portions of query code generated for different queries. If a query engine does not have a locally stored compiled portion of query code, then the separate data store may be accessed in order to obtain a compiled portion of query code, allowing reuse of compiled query code across different queries engines for queries directed to different databases.

Sharing compiled code for executing queries across query engines

Placement decisions may be made to place data in a multi-tenant cache. Usage of multi-tenant cache nodes for performing access requests may be obtained. Usage prediction techniques may be applied to the usage to determine placement decisions for data amongst the multi-tenant cache nodes. Placement actions for the data amongst at the multi-tenant cache nodes may be performed according to the placement decisions.

Making decisions for placing data in a multi-tenant cache

Dynamic generation of data catalogs may be implemented for accessing data sets in different storage locations. Data sets may be accessed in order to extract portions of data. Structure recognition techniques may be applied to the extracted data in order to determine structural information for the data sets. The structural information may then be stored as part of a data catalog for the data sets. Requests to access the data catalog from different clients may be received and the requested structural data supplied so that the clients may access different data sets utilizing the supplied structural data. Data catalogs may be updated as changes to data sets are made.

Dynamic generation of data catalogs for accessing data

A tree-based format may be implemented for data stored in a data store. A table may be maintained across one or multiple storage nodes in storage slabs. Storage slabs may be mapped to different nodes of a tree. Each node of the tree may be assigned a different range of distribution scheme values which identify what portions of the table are stored in the storage slab. Storage slabs mapped to child nodes in the tree may be assigned portions of the range of distribution scheme values assigned to a parent. Storage nodes may be added or removed for storing the table. Storage slabs may be moved from one storage node to another in order to accommodate the addition or removal of storage nodes.

Tree-based format for data storage

Tiered storage may be implemented for processing data. Data processors may maintain some of a data set, including user data and metadata describing the user data, locally. The data set is also maintained a data store remote to the data processor. When processing requests are received, a determination is made as to whether the local portions of the data set can execute the processing request or one or more additional portions of the data set are needed from the remote data store. If additional portions of the data set are needed, then a request may be sent to the data store for the additional portions. Once received, the data processor may execute the processing request utilizing the additional portions. Portions of the data set maintained locally at the data processor may be selected and flushed from local storage to the remote data store.

Tiered storage for data processing

A system such as a database management system determines a rule to impose sorted order upon a column without applying a sorting algorithm to the column and stores the rule to be applied to sort the column. In an embodiment, a permutation is the rule. The column, in an embodiment, is a column of a database table. In some cases, the rule is used to efficiently impose a correct sorted order on a subset of unsorted columns without the use of a sorting algorithm. In some cases, the rule is generated based at least in part on another column that is sorted using a sorting algorithm such as quicksort.

Sorting by permutation

The configuration of computing resources for executing queries may be selected. A comparison of the configuration of computing resources that executed previous queries may be made to select the configuration of computing resources for a received query. A historical query execution model maybe applied, in some embodiments, to determine a resource configuration for computing resources to execute a query. The computing resources may be selected from available computing resources according to the determined resource configuration.

Selecting resource configurations for query execution

Late encoding binding can be applied to data added to a data set according to the encoding history for the data set. When a request to add data is received, an evaluation of the encoding history can determine whether a currently specified encoding for the data can be changed. If changeable, a different encoding scheme for the data may be identified and the data added to the data set according to the different encoding scheme.

Evaluating encoding history for late encoding binding of data

Optimized query plans may be generated independent of the query engine that performs the optimized query plan. A request to generate an optimized query plan for a query may be received and a type of engine for performing the query may be identified. An initial plan may be generated in an engine-specific format for the type of engine that is translated into an optimization plan format. An analysis of the initial plan optimization plan format may be performed to generate an optimized query plan. The optimized query plan may be translated into the engine-specific format and sent in response to the request for the optimized query plan.

Engine independent query plan optimization

The capabilities of individual nodes that process a query may be evaluated to perform query planning. An operation of a plan to perform a query can be identified for assignment to a node based on the capabilities of nodes to perform the query operation. A node may be selected based on the difference between the selected node's capability to perform the query operation and other nodes capabilities to perform the operation. Capability-based selection can be performed at runtime, in some embodiments, in order to make query operation assignments based on further information obtained as a result of performing prior operations in the query.

Capability-based query planning for heterogenous processing nodes

Cardinality values can be derived from an approximate quantile summary. An approximate quantile summary can be generated for a column of a database table at data ingestion, data update, upon request, in response to a query, and in various other scenarios. When a query is received that includes a predicate directed to the column of the approximate quantile summary, a cardinality value may be derived from the boundary values of one or more quantiles that include the predicate. The cardinality value may then be used to select a query plan. The query may be performed according to the selected query plan.

Deriving cardinality values from approximate quantile summaries

Growing community of inventors

Santa Clara, CA, United States of America

Andrew Edward Caldwell