Query planner
An accelerated database management system including at least one processor including circuitry and a memory. The memory includes instructions that when executed by the circuitry cause the at least one processor to: receive an initial database query: generate a main query based on the initial database query; analyze the main query, and based on the analysis of the main query, generate at least a first sub-query and a second sub-query, wherein the second sub-query differs from the first sub-query; process the first sub-query along a first processing path to provide a first input to an execution module; process the second sub-query along a second processing path, different from the first processing path, to provide a second input to the execution module; and based on the first input and the second input received by the execution module, generate a main query result.
1. An accelerated database management system, comprising:
at least one processor including circuitry and a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processor to:
receive an initial database query;
generate a main query based on the initial database query;
analyze the main query, and based on the analysis of the main query, generate at least a first sub-query and a second sub-query, wherein
the first sub-query includes a residual sub-query based on a portion of the main query other than the second sub-query, and
the first sub-query includes a reference to the second sub-query;
process the first sub-query along a first processing path to provide a first input to an execution module;
process the second sub-query along a second processing path, different from the first processing path, to provide a second input to the execution module, wherein
the first input includes a residual plan of the residual query and the second input includes one or more intermediate data tables from an accelerator unit, and
the execution module is configured to execute the residual plan relative to a residual database separate from an accelerator database associated with the accelerator unit; and
based on the first input and the second input received by the execution module, generate a main query result.
2. The accelerated database management system of claim 1 , further comprising an accelerator unit configured for receiving and processing an accelerator sub-query included in the second sub-query.
3. The accelerated database management system of claim 1 , wherein the first sub-query includes a residual sub-query based on a portion of the main query other than the second sub-query.
4. The accelerated database management system of claim 3 , wherein the residual sub-query includes the reference to the second sub-query.
5. The accelerated database management system of claim 1 , wherein the first processing path includes a query planner module configured to output the residual query plan based on the first sub-query.
6. The accelerated database management system of claim 5 , wherein the residual query plan is provided to the execution module as the first input.
7. The accelerated database management system of claim 5 , wherein the residual query plan includes the reference to the second sub-query.
8. The accelerated database management system of claim 7 , wherein the reference to the second sub-query includes an indication of an accelerator output to be received by the execution module as the second input.
9. The accelerated database management system of claim 1 , wherein the second processing path includes at least one accelerator unit.
10. The accelerated database management system of claim 1 , wherein the one or more intermediate data tables are provided to the execution module as the second input to the execution module.
11. The accelerated database management system of claim 1 , wherein the one or more intermediate data tables include intermediate data results generated by the at least one accelerator unit based on operations relative to data stored in the accelerator unit database.
12. The accelerated database management system of claim 1 , wherein the one or more intermediate data tables are generated by at least one accelerator execution module associated with the at least one accelerator unit.
13. The accelerated database management system of claim 1 , wherein the processing of the second-sub query along the second processing path is performed in parallel to the processing of the first sub-query along the first processing path.
14. The accelerated database management system of claim 1 , wherein the execution module is configured to execute the residual plan relative to the output from the accelerator unit.
15. The accelerated database management system of claim 1 , wherein the execution module is configured to execute the residual plan without reliance upon the output from the accelerator unit.
16. The accelerated database management system of claim 1 , wherein the execution module is configured to:
execute the residual plan relative to the residual database to provide a residual plan result; and
combine the residual plan result with the output from the accelerator unit to provide the main query result.
17. The accelerated database management system of claim 1 , wherein in response to the main query, the at least one processor is configured to:
determine, using a planner module, that a portion of the main query is performed by the accelerator unit; and
generate the second sub-query in order to perform the portion of the main query using the accelerator unit along the second processing path.
18. A computer-implemented method comprising:
receiving an initial database query;
generating a main query based on the initial database query;
analyzing the main query, and based on the analysis of the main query, generating at least a first sub-query and a second sub-query, wherein
the first sub-query includes a residual sub-query based on a portion of the main query other than the second sub-query, and
the first sub-query includes a reference to the second sub-query;
processing the first sub-query along a first processing path to provide a first input to an execution module;
processing the second sub-query along a second processing path, different from the first processing path, to provide a second input to the execution module, wherein
the first input includes a residual plan of the residual query and the second input includes one or more intermediate data tables from an accelerator unit, and
the execution module is configured to execute the residual plan relative to a residual database separate from an accelerator database associated with the accelerator unit; and
based on the first input and the second input received by the execution module, generating a main query result.
19. A non-transitory computer-readable medium having stored thereon computer-readable instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving an initial database query;
generating a main query based on the initial database query;
analyzing the main query, and based on the analysis of the main query, generating at least a first sub-query and a second sub-query, wherein
the first sub-query includes a residual sub-query based on a portion of the main query other than the second sub-query, and
the first sub-query includes a reference to the second sub-query;
processing the first sub-query along a first processing path to provide a first input to an execution module;
processing the second sub-query along a second processing path, different from the first processing path, to provide a second input to the execution module, wherein
the first input includes a residual plan of the residual query and the second input includes one or more intermediate data tables from an accelerator unit, and
the execution module is configured to execute the residual plan relative to a residual database separate from an accelerator database associated with the accelerator unit; and
based on the first input and the second input received by the execution module, generating a main query result.