Nvidia patents method for GPU threads to launch and wait on child tasks
This patent describes a way for a graphics processing unit (GPU) to run complex, multi-step calculations without constantly checking in with the main computer processor. It allows a running task to start a new set of sub-tasks and pause until those sub-tasks finish, keeping the work organized on the GPU.
In the filing’s own words
One embodiment of the present invention sets forth a technique for performing nested kernel execution within a parallel processing subsystem. The technique involves enabling a parent thread to launch a nested child grid on the parallel processing subsystem, and enabling the parent thread to perform a thread synchronization barrier on the child grid for proper execution semantics between the parent thread and the child grid. This technique advantageously enables the parallel processing subsystem to perform a richer set of programming constructs, such as conditionally executed and nested operations and externally defined library functions without the additional complexity of CPU involvement.
What exactly they claim (claim 1)
1. A computer-readable storage medium having stored thereon instructions, which if performed by one or more processors, cause the one or more processors to at least: launch a kernel to execute a parent thread within a multiprocessor; launch, from within the kernel, a child thread grid comprising one or more child thread arrays within the multiprocessor; in response to a synchronization function call, block execution of the parent thread while waiting for the child thread grid to complete; and de-allocate resources used by the parent thread.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Technique for computational nested parallelism
- Patent number
- US12801436B2
- Application number
- 16746714
- Filed
- Jan 17, 2020
- Granted
- Nov 17, 2026
- Inventors
- 7
- Claims
- 23
Classified under
G06F 9/5027 Physics & computingG06F 9/522 Physics & computingG06T 1/20 Physics & computingG06F 2209/483 Physics & computingMore from Nvidia in Chips & hardware
- Nvidia stacks memory directly on chips to boost data speed Nov 10, 2026
- Nvidia patents method to skip zero data in neural network math Oct 13, 2026
- Nvidia patents hardware to speed up motion blur in ray tracing Oct 13, 2026
- Nvidia patents method to sync data across split processor chips Sep 17, 2026
- Nvidia patents chip math trick to speed up AI calculations Oct 8, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
