Nvidia patents chip-to-chip encryption using separate keys for sending and receiving
Nvidia describes a method for securing data as it moves between two computer chips. The system uses one specific key to encrypt data being sent and a different key to decrypt data being received.
In the filing’s own words
A device includes memory to store a first session key and a second session key different from the first session key. A transmitter (TX) physical layer is to transmit frames to a second device over a link and a receiver (RX) physical layer is to receive frames from the second device over the link. A TX datalink logic is coupled to the TX physical layer and the memory, the TX datalink logic to cause encryption of frame data transmitted to the second device using the first session key. A RX datalink logic is coupled to the RX physical layer and the memory, the RX datalink logic to cause decryption of frame data received from the second device using the second session key.
What exactly they claim (claim 1)
1. A device comprising: memory to store a first session key and a second session key different from the first session key; a transmitter (TX) physical layer to transmit frames to a second device over a link; a receiver (RX) physical layer to receive frames from the second device over the link; TX datalink logic coupled to the TX physical layer and the memory, the TX datalink logic to cause encryption of frame data transmitted to the second device using the first session key; and RX datalink logic coupled to the RX physical layer and the memory, the RX datalink logic to cause decryption of frame data received from the second device using the second session key.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- SYNCHRONIZING AN ENCRYPTED DATA STREAM ACROSS CHIP-TO-CHIP GROUND REFERENCED SIGNALING INTERCONNECT
- Publication number
- US20260303345A1
- Application number
- 19698366
- Filed
- Jun 4, 2026
- Published
- Oct 1, 2026
- Inventors
- 2
- Claims
- 20
Classified under
H04L 9/12 Electricity & electronicsMore 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.