公开(公告)号：US20240111668A1

公开(公告)日：2024-04-04

申请号：US18374944

申请日：2023-09-29

Applicant: Oracle International Corporation

Inventor： Hariharan Lakshmanan ,  Teck Hua Lee ,  Vinita Subramanian ,  Gary Smith ,  Lijian Wan ,  Shasank Kisan Chavan ,  Venkat Raman Senapati

IPC: G06F12/02

CPC classification number: G06F12/023

Abstract: Techniques are provided for implementing an in-memory columnar data store that is configured to either grow or shrink in response to performance prediction data generated from database workload information. A system maintains allocations of volatile memory from a given memory area for a plurality of memory-consuming components in a database system. The system receives for each memory-consuming component, performance prediction data that contains performance predictions for a plurality of memory allocation sizes for the memory-consuming components. The system determines a target memory allocation for an in-memory columnar data store based on the performance predictions. The system determines an incrementally adjusted amount of memory for the in-memory columnar data store and causes the incrementally adjusted amount to be allocated to the in-memory columnar data store.

公开(公告)号：US11797539B2

公开(公告)日：2023-10-24

申请号：US17018018

申请日：2020-09-11

Applicant: Oracle International Corporation

Inventor： Shasank Kisan Chavan ,  James Kearney ,  Weiwei Gong

IPC: G06F16/2455 ,  G06F16/22 ,  G06F16/25 ,  G06F9/30 ,  G06F9/38

CPC classification number: G06F16/2456 ,  G06F9/30047 ,  G06F9/3887 ,  G06F16/2255 ,  G06F16/252

Abstract: The present invention relates to hash join acceleration. In an embodiment, a computer receives a request to join build data rows with probe data rows. Each data row is associated with a respective join key value. From multiple buckets of a hash table, a bucket is selected that contains entries of multiple respective join key values in respective locations within the bucket. Whether or not the bucket contains an entry of the join key value of a build data row is detected. While building, multiple locations within the bucket are concurrently inspected to find an empty location in which to store the entry of the join key value of the build data row. The bucket is concurrently probed to detect whether or not the entries in the bucket include an entry of a join key value of a probe data row. For the join request, a response is sent that is based on the concurrent probing of the bucket.

公开(公告)号：US11507590B2

公开(公告)日：2022-11-22

申请号：US16904392

申请日：2020-06-17

Applicant: Oracle International Corporation

Inventor： Siva Ravada ,  Ying Hu ,  Zhen Hua Liu ,  Shasank Kisan Chavan ,  Aurosish Mishra ,  Vikas Arora

IPC: G06F16/25 ,  G06F16/22 ,  G06F9/38 ,  G06F16/242 ,  G06F16/2457

Abstract: Techniques are introduced herein for maintaining geometry-type data on persistent storage and in memory. Specifically, a DBMS that maintains a database table, which includes at least one column storing spatial data objects (SDOs), also maintains metadata for the database table that includes definition data for one or more virtual columns of the table. According to an embodiment, the definition data includes one or more expressions that calculate minimum bounding box values for SDOs stored in the geometry-type column in the table. The one or more expressions in the metadata maintained for the table are used to create one or more in-memory columns that materialize the bounding box data for the represented SDOs. When a query that uses spatial-type operators to perform spatial filtering over data in the geometry-type column is received, the DBMS replaces the spatial-type operators with operators that operate over the scalar bounding box information materialized in memory.

公开(公告)号：US11429604B2

公开(公告)日：2022-08-30

申请号：US17015580

申请日：2020-09-09

Applicant: Oracle International Corporation

Inventor： Shasank Kisan Chavan ,  Garret F. Swart ,  Weiwei Gong

IPC: G06F16/2453 ,  G06N20/00 ,  G06F16/901 ,  G06N5/04

Abstract: The present invention relates to optimized access of a database. Herein are techniques to accelerate execution of any combination of ad hoc query, heterogenous hardware, and fluctuating workload. In an embodiment, a computer receives a data access request for data tuples and compiles the data access request into relational operators. A particular implementation of a particular relational operator is dynamically selected from multiple interchangeable implementations. Each interchangeable implementation contains respective physical operators. A particular hardware operator for a particular physical operator is selected from multiple interchangeable hardware operators that include: a first hardware operator that executes on first processing hardware, and a second hardware operator that executes on second processing hardware that is functionally different from the first processing hardware. A response to the data access request is generated based on: the data tuples, the particular implementation of the particular relational operator, and the particular hardware operator.

公开(公告)号：US20220114178A1

公开(公告)日：2022-04-14

申请号：US17162564

申请日：2021-01-29

Applicant: Oracle International Corporation

Inventor： Vlad Ioan Haprian ,  Mikael Gonzalez Morales ,  Laurent Daynes ,  Zhen Hua Liu ,  Danica Porobic ,  Marco Arnaboldi ,  Jean-Pierre Lozi ,  Hugo Kapp ,  Sungpack Hong ,  Shasank Kisan Chavan ,  Hassan Chafi

IPC: G06F16/2455 ,  G06F16/26 ,  G06F16/2453 ,  G06F16/248 ,  G06F16/22

Abstract: Techniques are provided for processing a graph query by exploiting an in-memory graph index and minimizing the number of storage accesses needed to project properties of generated paths. A predefined number of paths from a graph query runtime is accumulated, using different data structures, before executing storage accesses necessary to retrieve all properties needed. A first data structure stores all paths from the graph query runtime that hit cache(s) entirely. A second data structure stores paths that do not hit caches at any level or only a subset of the levels does. Once any of these data structures are full, result rows are produced based on the two data structures prior to extracting more paths from the graph query runtime.

公开(公告)号：US11093459B2

公开(公告)日：2021-08-17

申请号：US16747827

申请日：2020-01-21

Applicant: Oracle International Corporation

Inventor： Marco Arnaboldi ,  Jean-Pierre Lozi ,  Laurent Phillipe Daynes ,  Vlad Ioan Haprian ,  Shasank Kisan Chavan ,  Hugo Kapp ,  Sungpack Hong

IPC: G06F16/30 ,  G06F7/00 ,  G06F16/21 ,  G06F16/27 ,  G06F16/28 ,  G06F16/901

Abstract: Herein are techniques that concurrently populate entries in a compressed sparse row (CSR) encoding, of a type of edge of a heterogenous graph. In an embodiment, a computer obtains a mapping of a relational schema to a graph data model. The relational schema defines vertex tables that correspond to vertex types in the graph data model, and edge tables that correspond to edge types in the graph data model. Each edge type is associated with a source vertex type and a target vertex type. For each vertex type, a sequence of persistent identifiers of vertices is obtained. Based on the mapping and for a CSR representation of each edge type, a source array is populated that, for a same vertex ordering as the sequence of persistent identifiers for the source vertex type, is based on counts of edges of the edge type that originate from vertices of the source vertex type. For the CSR, the computer populates, in parallel and based on said mapping, a destination array that contains canonical offsets as sequence positions within the sequence of persistent identifiers of the vertices.

公开(公告)号：US20210081428A1

公开(公告)日：2021-03-18

申请号：US16904392

申请日：2020-06-17

Applicant: Oracle International Corporation

Inventor： Siva Ravada ,  Ying Hu ,  Zhen Hua Liu ,  Shasank Kisan Chavan ,  Aurosish Mishra ,  Vikas Arora

IPC: G06F16/25 ,  G06F16/22 ,  G06F16/2457 ,  G06F16/242 ,  G06F9/38

Abstract: Techniques are introduced herein for maintaining geometry-type data on persistent storage and in memory. Specifically, a DBMS that maintains a database table, which includes at least one column storing spatial data objects (SDOs), also maintains metadata for the database table that includes definition data for one or more virtual columns of the table. According to an embodiment, the definition data includes one or more expressions that calculate minimum bounding box values for SDOs stored in the geometry-type column in the table. The one or more expressions in the metadata maintained for the table are used to create one or more in-memory columns that materialize the bounding box data for the represented SDOs. When a query that uses spatial-type operators to perform spatial filtering over data in the geometry-type column is received, the DBMS replaces the spatial-type operators with operators that operate over the scalar bounding box information materialized in memory.

公开(公告)号：US20210081410A1

公开(公告)日：2021-03-18

申请号：US17018018

申请日：2020-09-11

Applicant: Oracle International Corporation

Inventor： Shasank Kisan Chavan ,  JAMES KEARNEY ,  WEIWEI GONG

IPC: G06F16/2455 ,  G06F16/22 ,  G06F16/25 ,  G06F9/38 ,  G06F9/30

Abstract: The present invention relates to hash join acceleration. In an embodiment, a computer receives a request to join build data rows with probe data rows. Each data row is associated with a respective join key value. From multiple buckets of a hash table, a bucket is selected that contains entries of multiple respective join key values in respective locations within the bucket. Whether or not the bucket contains an entry of the join key value of a build data row is detected. While building, multiple locations within the bucket are concurrently inspected to find an empty location in which to store the entry of the join key value of the build data row. The bucket is concurrently probed to detect whether or not the entries in the bucket include an entry of a join key value of a probe data row. For the join request, a response is sent that is based on the concurrent probing of the bucket.

公开(公告)号：US10467243B2

公开(公告)日：2019-11-05

申请号：US15162235

申请日：2016-05-23

Applicant: Oracle International Corporation

Inventor： Zhen Hua Liu ,  Shasank Kisan Chavan ,  Aurosish Mishra

IPC: G06F17/30 ,  G06F7/00 ,  G06F16/25 ,  G06F16/84 ,  G06F16/22 ,  G06F16/33 ,  G06F16/28 ,  G06F16/215

Abstract: Techniques are described herein for maintaining two copies of the same semi-structured data, where each copy is organized in a different format. One copy is in a first-format that may be convenient for storage, but inefficient for query processing. For example, the first-format may be a textual format that needs to be parsed every time a query needs to access individual data items within a semi-structured object. The database system intelligently loads semi-structured first-format data into volatile memory and, while doing so, converts the semi-structured first-format data to a second-format. Because the data in volatile memory is in the second-format, processing queries against the second-format data both allows disk I/O to be avoided, and increases the efficiency of the queries themselves. For example, the parsing that may be necessary to run a query against a cached copy of the first-format data is avoided.

公开(公告)号：US09697221B2

公开(公告)日：2017-07-04

申请号：US14337113

申请日：2014-07-21

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Anindya Patthak ,  Victor Chen ,  Shasank Kisan Chavan ,  Jesse Kamp ,  Amit Ganesh ,  Vineet Marwah

IPC: G06F17/30 ,  H03M7/30 ,  G06F12/04

CPC classification number: G06F17/30153 ,  G06F12/04 ,  H03M7/3066 ,  H03M7/3088 ,  H03M7/6005 ,  H03M7/6011

Abstract: A method, apparatus, and system for OZIP, a data compression and decompression codec, is provided. OZIP utilizes a fixed size static dictionary, which may be generated from a random sampling of input data to be compressed. Compression by direct token encoding to the static dictionary streamlines the encoding and avoids expensive conditional branching, facilitating hardware implementation and high parallelism. By bounding token definition sizes and static dictionary sizes to hardware architecture constraints such as word size or processor cache size, hardware implementation can be made fast and cost effective. For example, decompression may be accelerated by using SIMD instruction processor extensions. A highly granular block mapping in optional stored metadata allows compressed data to be accessed quickly at random, bypassing the processing overhead of dynamic dictionaries. Thus, OZIP can support low latency random data access for highly random workloads, such as for OLTP systems.