Nvidia patents a way for GPU parts to share data more efficiently
Nvidia describes a method for how a main processor in a graphics chip talks to a smaller helper chip. The system sends data to the helper, tells it to work, and then retrieves the finished results using a specific sequence of steps.
In the filing’s own words
Systems and methods for an efficient and robust multiprocessor-coprocessor interface that may be used between a streaming multiprocessor and an acceleration coprocessor in a GPU are provided. According to an example implementation, in order to perform an acceleration of a particular operation using the coprocessor, the multiprocessor: issues a series of write instructions to write input data for the operation into coprocessor-accessible storage locations, issues an operation instruction to cause the coprocessor to execute the particular operation; and then issues a series of read instructions to read result data of the operation from coprocessor-accessible storage locations to multiprocessor-accessible storage locations.
What exactly they claim (claim 1)
1. A method performed by a multiprocessor to execute an operation on a communicatively coupled coprocessor, the method comprising: establishing a connection to the coprocessor; issuing a plurality of write instructions to write input data for the operation into coprocessor-accessible storage locations; issuing an operation instruction to cause the coprocessor to execute the operation using said input data; issuing a plurality of read instructions to read result data of the operation from coprocessor-accessible storage locations to multiprocessor-accessible storage locations; and closing the connection.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- ROBUST, EFFICIENT MULTIPROCESSOR-COPROCESSOR INTERFACE
- Publication number
- US20260319795A1
- Application number
- 19463750
- Filed
- Jan 29, 2026
- Published
- Oct 15, 2026
- Inventors
- 8
- Claims
- 1
Classified under
G06F 9/3004 Physics & computingG06F 9/3877 Physics & computingG06F 15/163 Physics & computingG06T 1/20 Physics & computingG06T 2200/28 Physics & computingMore from Nvidia in Chips & hardware
- 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
- Nvidia patents data center cooling that uses cryogenic fluids Oct 15, 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.