Nvidia patents system that plans data paths for its graphics chips
This filing describes a method for a main processor to prepare instructions for Nvidia's specialized chips, known as accelerators. It involves mapping out exactly how data moves through the chip's internal components to ensure the tasks match what the hardware can actually do.
In the filing’s own words
In various examples, systems and methods are disclosed that relate to programming multi-dimensional single instruction, multiple data (SIMD) processors (also referred to as an accelerator). In one example, a processor can obtain instructions to be performed by the accelerator. The processor can determine one or more operations to be performed by the accelerator based at least on the instructions and generate a set of accelerator instructions. In examples, the processor can then provide data associated with the accelerator instructions to cause the accelerator to perform at least a portion of the one or more operations.
What exactly they claim (claim 1)
1. One or more processors comprising: one or more circuits to: generate a set of accelerator instructions for an accelerator based at least on a datapath associated with the accelerator, and one or more operations to be performed by the accelerator that are compatible with operations that the accelerator is to execute, the datapath representing one or more transfers of data within the accelerator via one or more components of the accelerator, and the data having a datatype that is compatible with the accelerator; and provide the data associated with the set of accelerator instructions to a system to cause the system to coordinate an operation of the accelerator in accordance with the set of accelerator instructions.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- DIRECT MEMORY ACCESS SYSTEMS
- Publication number
- US20260288675A1
- Application number
- 19689518
- Filed
- May 27, 2026
- Published
- Sep 24, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 15/8023 Physics & computingG06F 9/30181 Physics & computingG06F 9/3897 Physics & computingG06F 9/3887 Physics & computingG06F 15/80 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.