Method and system of scalable acceleration of database query operations

A query operation and database technology, which is applied in the fields of electrical digital data processing, digital data information retrieval, special data processing applications, etc., and can solve the problems of reducing the amount of resources and low performance gain.
CN104346433AActive Publication Date: 2015-02-11IBM CORP
5 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
IBM CORP
Publication Date
2015-02-11

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

Embodiments include methods, systems and computer program products for offloading multiple processing operations to an accelerator. Aspects include receiving a database query from an application, performing an analysis on the query, and identifying a plurality of available accelerators. Aspects further include retrieving cost information for one or more templates available on each of the plurality of available accelerators, determining a query execution plan based on the cost information and the analysis on the query, and offloading one or more query operations to at least one of the plurality of accelerators based on the query execution plan.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to accelerating multiple query processing operations, and more particularly, to an accelerator system for scalable acceleration of database query operations. Background technique

[0002] In general, a single database query includes multiple query processing operations. These query processing operations include, but are not limited to, sorting operations, decompression operations, predicate evaluation operations, and join operations. Hardware acceleration of query operations shows significant performance improvements over software implementations. This performance improvement is due to the custom data paths and parallelism available in hardware implementations.

[0003] Currently, query operators are computed against a single hardware accelerator. The resources available on a single accelerator can limit the performance gain provided by that accelerator. Although more operations need to be offloaded from the host to th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More