System, method, and computer program product for applying a callback function to data values

• US 9,015,643 B2
• Filed: 03/15/2013
• Issued: 04/21/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Alfieri, Robert Anthony
• Primary Examiner(s): Rossoshek, Helen
• Application Number:
  US13/844,437
• Publication Number:
  US 20140282313A1
• Time in Patent Office: 767 Days
• Field of Search: 716/103, 716/104, 716/106, 716/111, 716/113, 716/136, 703/13, 703/14, 703/16
• US Class Current: 716/106
• CPC Class Codes: G06F 30/30 Circuit design
• CPC Class Codes: G06F 30/33 Design verification, e.g. functional simulation or model checking
• CPC Class Codes: G06F 30/3308 using simulation
• CPC Class Codes: G06F 30/367 Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods

Abstract

A system, method, and computer program product are provided for applying a callback function to data values. In use, a plurality of data values and a callback function are identified. Additionally, the callback function is recursively applied to the plurality of data values in order to determine a result. Further, the result is returned.

Claims

1. A method, comprising:

identifying, by a processor, a callback function and a plurality of data values corresponding to signals of a hardware design;

providing the plurality of data values and the callback function to a compute construct, wherein the compute construct is configured to check that an unconnected data flow is indicated as a deferred data flow and comprises a first parameter configured to perform control of data flow through the hardware design by automatically stalling an input data flow within the compute construct; and

executing, by the processor, the compute construct to recursively apply the callback function to the plurality of data values in order to determine a result.

2. The method of claim 1, wherein the plurality of data values include subflows within a numerical hierarchy data flow.

3. The method of claim 1, wherein applying the callback function to the plurality of data values includes performing a reduction operation on the plurality of data values.

4. The method of claim 1, wherein applying the callback function to the plurality of data values includes identifying the each of the plurality of data values as leaf nodes of a tree-based data structure.

5. The method of claim 4, wherein consecutive rounds of comparisons are performed by the callback function at each level of the tree-based structure until a single output is produced for a particular round of comparisons.

6. The method of claim 1, wherein applying the callback function to the plurality of data values includes performing a first round of comparisons.

7. The method of claim 6, wherein performing the first round of comparisons results in one or more outputs.

8. The method of claim 6, wherein the first round of comparisons are performed at a first level of a tree-based data structure.

9. The method of claim 1, wherein applying the callback function to the plurality of data values includes performing a second round of comparisons.

10. The method of claim 1, wherein applying the callback function to the plurality of data values is performed by a tree function included within the compute construct.

11. The method of claim 10, wherein the tree function is utilized by one or more of a Min( )function that returns a minimum value from a hierarchical data flow with multiple numerically named subflows and a Max( )function that returns a maximum value from a hierarchical data flow with multiple numerically named subflows.

12. The method of claim 10, wherein the tree function is utilized by one or more of a Prio_Min( )function that returns a minimum priority value from a numerical hierarchy data flow containing priority values and a Prio_Max( )function that returns a maximum priority value from a numerical hierarchy data flow containing priority values.

13. The method of claim 1, wherein the tree function is utilized by a scatter-gather function.

14. The method of claim 1, wherein the callback function represents a combinational circuit function configured to operate on the input data flow.

15. The method of claim 1, wherein the compute construct further comprises a second parameter that is configured to perform control a depth of an output first-in first-out buffer for each output data flow.

16. The method of claim 1, wherein the compute construct further comprises a second parameter that is configured to register an output data flow.

17. The method of claim 1, wherein the compute construct further comprises a second parameter that is configured to register a ready signal of an output data flow.

18. A computer program product embodied on a non-transitory computer readable medium, comprising:

code for identifying a callback function and a plurality of data values corresponding to signals of a hardware design;

code for providing the plurality of data values and the callback function to a compute construct, wherein the compute construct is configured to check that an unconnected data flow is indicated as a deferred data flow and comprises a first parameter configured to perform control of data flow through the hardware design by automatically stalling an input data flow within the compute construct; and

code for recursively applying the callback function to the plurality of data values in order to determine a result.

19. A system, comprising:

a processor configured to;

identify a callback function and a plurality of data values corresponding to signals of a hardware design,

provide the plurality of data values and the callback function to a compute construct, wherein the compute construct is configured to check that an unconnected data flow is indicated as a deferred data flow and comprises a first parameter configured to perform control of data flow through the hardware design by automatically stalling an input data flow within the compute construct; and

execute the compute construct to recursively apply the callback function to the plurality of data values in order to determine a result.