Databricks‘s patented system involves receiving and processing queries, determining node types, and generating execution plans. The method includes identifying nodes supported by specific engines, transforming them into vectorized operations, and executing them on the corresponding engines. This innovation enhances query processing efficiency. GlobalData’s report on Databricks gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Databricks, was a key innovation area identified from patents. Databricks's grant share as of February 2024 was 56%. Grant share is based on the ratio of number of grants to total number of patents.
Optimizing database query execution using multiple engine types
A recently granted patent (Publication Number: US11874832B2) outlines a method for optimizing database queries by utilizing a cluster resource with different sets of execution engines. The method involves receiving a database query specified in a declarative database query language, generating an execution plan represented as a graph data structure, identifying nodes supported by specific engine types, and executing vectorized operations based on inputs. The approach includes transforming nodes supported by a second engine type into a sequence of vectorized operations for efficient processing.
Furthermore, the patent details the configuration of a cluster resource with shared memory pools for different engine types, enabling the generation of code for specific nodes and executing operations to produce outputs. The method also involves converting outputs from row-wise to columnar format for seamless integration with the second set of execution engines. The patent emphasizes the utilization of vectorized operations such as scan, filter, project, and grouping aggregate operations to enhance query performance. Overall, the patented method aims to streamline database query processing by leveraging the capabilities of different execution engines within a cluster resource efficiently.
To know more about GlobalData’s detailed insights on Databricks, buy the report here.
Premium Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
