Graph-based data multi-operation system
A graph-based data multi-operation system includes a data multi-operation management subsystem coupled to an application and accelerator subsystems. The data multi-operation management subsystem receives a data multi-operation graph from the application that identifies first data and defines operations for performance on the first data to transform the first data into second data. The data multi-operation management subsystem assigns each of the operations to at least one of the accelerator systems, and configures the accelerator subsystems to perform the operations in a sequence that transforms the first data into the second data, When the data multi-operation management subsystem determine a completion status for the performance of the operations by the accelerator subsystems, it transmits a completion status communication to the application that indicates the completion status of the performance of the plurality of operations by the plurality of accelerator subsystems.
1. A graph-based data multi-operation system, comprising:
an application;
a plurality of accelerator subsystems; and
a data multi-operation management subsystem that is coupled to the application and the plurality of accelerator subsystems, wherein the data multi-operation management subsystem is configured to:
receive, from the application, a data multi-operation graph that identifies first data and defines a plurality of operations for performance on the first data to transform the first data into second data;
assign each of the plurality of operations defined by the data multi-operation graph to at least one of the plurality of accelerator systems;
configure the plurality of accelerator subsystems to perform the plurality of operations defined by the data multi-operation graph in a sequence that transforms the first data into the second data;
determine a completion status for the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data; and
transmit, to the application, a completion status communication that indicates the completion status of the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data.
2. The system of claim 1 , wherein the data multi-operation graph identifies:
a data source location for the first data;
a plurality of first data operations that are included in the plurality of operations for performance on the first data to transform the first data into the second data; and
a data destination location for the second data.
3. The system of claim 1 , wherein the data multi-operation graph identifies:
a plurality of second data operations that are included in the plurality of operations for performance on the first data to transform the first data into third data; and
a data analytics location for the third data.
4. The system of claim 1 , wherein the data multi-operation management subsystem is configured to:
identify at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one hardware accelerator subsystem.
5. The system of claim 1 , wherein the data multi-operation management subsystem is configured to:
configure at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured hardware accelerator subsystem; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured hardware accelerator subsystem.
6. The system of claim 1 , wherein the data multi-operation management subsystem is configured to:
configure at least one software accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured software accelerator subsystem; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured software accelerator subsystem.
7. An Information Handling System (IHS), comprising:
a processing subsystem; and
a memory subsystem that is coupled to the processing subsystem and that includes instructions that, when executed by the processing subsystem, cause the processing subsystem to provide a data multi-operation management engine that is configured to:
receive, from an application, a data multi-operation graph that identifies first data and defines a plurality of operations for performance on the first data to transform the first data into second data;
assign each of the plurality of operations defined by the data multi-operation graph to at least one of a plurality of accelerator systems coupled to the processing system;
configure the plurality of accelerator subsystems to perform the plurality of operations defined by the data multi-operation graph in a sequence that transforms the first data into the second data;
determine a completion status for the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data; and
transmit, to the application, a completion status communication that indicates the completion status of the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data.
8. The IHS of claim 7 , wherein the data multi-operation graph identifies:
a data source location for the first data;
a plurality of first data operations that are included in the plurality of operations for performance on the first data to transform the first data into the second data; and
a data destination location for the second data.
9. The IHS of claim 8 , wherein the data multi-operation graph identifies:
a plurality of second data operations that are included in the plurality of operations for performance on the first data to transform the first data into third data; and
a data analytics location for the third data.
10. The IHS of claim 7 , wherein the data multi-operation management engine is configured to:
identify at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one hardware accelerator subsystem.
11. The IHS of claim 7 , wherein the data multi-operation management engine is configured to:
configure at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured hardware accelerator subsystem; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured hardware accelerator subsystem.
12. The IHS of claim 7 , wherein the data multi-operation management engine is configured to:
configure at least one software accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured software accelerator subsystem; and
assign at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured software accelerator subsystem.
13. The IHS of claim 7 , wherein the data multi-operation management engine is configured to:
configure at least two of the plurality of accelerator subsystems to perform a subset of the plurality of operations defined by the data multi-operation graph in parallel.
14. A method for providing graph-based data multi-operations, comprising:
receiving, by a data multi-operation management subsystem from an application, a data multi-operation graph that identifies first data and defines a plurality of operations for performance on the first data to transform the first data into second data;
assigning, by the data multi-operation management subsystem, each of the plurality of operations defined by the data multi-operation graph to at least one of a plurality of accelerator systems coupled to the processing system;
configuring, by the data multi-operation management subsystem, the plurality of accelerator subsystems to perform the plurality of operations defined by the data multi-operation graph in a sequence that transforms the first data into the second data;
determining, by the data multi-operation management subsystem, a completion status for the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data; and
transmitting, by the data multi-operation management subsystem to the application, a completion status communication that indicates the completion status of the performance of the plurality of operations by the plurality of accelerator subsystems to transform the first data into the second data.
15. The method of claim 14 , wherein the data multi-operation graph identifies:
a data source location for the first data;
a plurality of first data operations that are included in the plurality of operations for performance on the first data to transform the first data into the second data; and
a data destination location for the second data.
16. The method of claim 15 , wherein the data multi-operation graph identifies:
a plurality of second data operations that are included in the plurality of operations for performance on the first data to transform the first data into third data; and
a data analytics location for the third data.
17. The method of claim 14 , further comprising:
identifying, by the data multi-operation management subsystem, at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems; and
assigning, by the data multi-operation management subsystem, at least one of the plurality of operations defined by the data multi-operation graph to the at least one hardware accelerator subsystem.
18. The method of claim 14 , further comprising:
configuring, by the data multi-operation management subsystem, at least one hardware accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured hardware accelerator subsystem; and
assigning, by the data multi-operation management subsystem, at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured hardware accelerator subsystem.
19. The method of claim 14 , further comprising:
configuring, by the data multi-operation management subsystem, at least one software accelerator subsystem that is included in the plurality of accelerator subsystems to provide at least one configured software accelerator subsystem; and
assigning, by the data multi-operation management subsystem, at least one of the plurality of operations defined by the data multi-operation graph to the at least one configured software accelerator subsystem.
20. The method of claim 14 , further comprising:
configuring, by the data multi-operation management subsystem, at least two of the plurality of accelerator subsystems to perform a subset of the plurality of operations defined by the data multi-operation graph in parallel.