/Patent Tracker
NvidiaGranted patentAI & softwareInterest 4/10

Nvidia patents method to split neural networks across processors

Patent drawing
Patent drawing from the official filing.

Nvidia describes a technique where a compiler automatically divides a neural network into smaller sections. These sections are then assigned to different processors to run at the same time, using data about the size of inputs and outputs to make the split.

Why it mattersThis improves how software prepares complex math tasks for hardware, potentially making AI models run more efficiently on existing chips.

In the filing’s own words

Apparatuses, systems, and techniques are presented schedule operations to be performed. In at least one embodiment, two or more data partitions of a neural network are caused to be automatically scheduled to be performed by two or more corresponding logical processors in parallel.

What exactly they claim (claim 1)

1. A processor, comprising: one or more circuits to: generate, as part of a first stage of a compiler, an intermediate representation of code to perform a neural network, the intermediate representation comprising one or more values indicating respective shape information of input values or output values of one or more intermediate computations; select two or more data partitions for the neural network to schedule performance by two or more processors in parallel, based, at least in part on the one or more values of the intermediate representation; and complete, as part of one or more second stages of the compiler, a schedule to perform the neural network by the two or more processors in parallel according to the selected two or more data partitions.

Facts

Company
Nvidia (Nvidia Corporation)
Official title
Automated partitioning for one or more neural networks
Patent number
US12754769B1
Application number
17957540
Filed
Sep 30, 2022
Granted
Oct 6, 2026
Inventors
3
Claims
30

Classified under

G06F 9/5027 Physics & computingG06N 3/02 Physics & computing

More from Nvidia in AI & software

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.