18465764. QUERY PROCESSING ON ACCELERATED PROCESSING UNITS simplified abstract (Microsoft Technology Licensing, LLC)

From WikiPatents
Jump to navigation Jump to search

QUERY PROCESSING ON ACCELERATED PROCESSING UNITS

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Matteo Interlandi of Torrance CA (US)

Wei Cui of Beijing (CN)

Qianxi Zhang of Beijing (CN)

Peng Cheng of Beijing (CN)

Rathijit Sen of Redmond WA (US)

QUERY PROCESSING ON ACCELERATED PROCESSING UNITS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18465764 titled 'QUERY PROCESSING ON ACCELERATED PROCESSING UNITS

Simplified Explanation: The patent application describes a system and method for processing queries, where query information is received over a network and processed using different processing architectures integrated in a hardware chip.

  • The system loads data associated with the query into a shared memory using a first processing architecture.
  • A second processing architecture accesses the data from the shared memory to process the query and generate a query result.
  • The processed query result is then provided back over the network.

Key Features and Innovation:

  • Integration of multiple processing architectures in a hardware chip for query processing.
  • Use of shared memory to efficiently access and process query data.
  • Ability to execute queries based on different processing systems contained within the computing device.

Potential Applications: This technology can be applied in various fields such as database management, data analytics, and information retrieval systems.

Problems Solved:

  • Efficient query processing by utilizing shared memory.
  • Seamless integration of different processing architectures for improved performance.

Benefits:

  • Faster query processing.
  • Enhanced system performance.
  • Reduced latency in generating query results.

Commercial Applications: Potential commercial applications include database management systems, online search engines, and data analytics platforms. This technology can improve the efficiency and speed of query processing in these applications.

Prior Art: Readers can explore prior art related to query processing systems, shared memory utilization, and integrated processing architectures in hardware chips to understand the evolution of this technology.

Frequently Updated Research: Researchers may find updated studies on query processing optimization, shared memory management, and hardware chip design advancements relevant to this technology.

Questions about Query Processing Systems: 1. What are the key advantages of integrating multiple processing architectures in a hardware chip for query processing? 2. How does the use of shared memory enhance the efficiency of query processing in this system?


Original Abstract Submitted

Query processing systems and methods are disclosed herein. In an example system, query information is received over a network for processing a query. A first processing architecture loads a set of data associated with the query into a shared memory. A second processing architecture accesses the set of data from the shared memory. In one example, the first and second processing architectures and the shared memory are integrated in a hardware chip (e.g., a chiplet containing several processor architectures, such as CPU and a graphics processing unit (GPU)). The query is processed based on the set of data accessed from the shared memory using the second processing architecture to generate a query result. The query result is provided over the network. In this manner, a computing device may execute a query based on different processing systems contained therein.