/Patent Tracker
NvidiaPatent applicationChips & hardwareInterest 6/10

Nvidia patents way to link different chips so they share data pointers

Patent drawing
Patent drawing from the official filing.

Nvidia describes a method for connecting multiple specialized computer chips, or accelerators, within a single system. The technique creates a link between the memory addresses used by one chip and the addresses used by another, allowing the second chip to directly access data managed by the first.

Why it mattersThis could make high-performance computing systems more efficient by allowing different types of processors to work together without needing complex data copying steps.

In the filing’s own words

Apparatuses, systems, and techniques to use a plurality of accelerators together in a system. In at least one embodiment, a pointer generated for a first accelerator is mapped to a pointer for a second accelerator so that the second accelerator may utilize the pointer for the first accelerator to access stored data.

What exactly they claim (claim 1)

1. One or more processors, comprising: circuitry to generate one or more first pointers usable by one or more first accelerators to access data stored in storage allocated by one or more second accelerators based, at least in part, on one or more corresponding second pointers usable by the one or more second accelerators to access the data.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
TECHNIQUES FOR INTEGRATION OF MULTIPLE ACCELERATORS
Publication number
US20260319843A1
Application number
19648837
Filed
Apr 15, 2026
Published
Oct 15, 2026
Inventors
3
Claims
20

Classified under

G06F 9/5016 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia in Chips & hardware

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.