Nvidia patents method to decode data using repeated pattern shuffling
Nvidia describes a technique for decoding digital data that has been protected by a specific type of error-correcting code. The system uses a component called an interleaver to rearrange the data into different orders, reusing the same interleaver multiple times to create these variations. It then tries to decode each version and picks the result that best matches the original data.
In the filing’s own words
Apparatuses, systems, and techniques to decode codewords encoded using linear block codes. In at least one embodiment, a codeword encoded using a linear block code is decoded by at least using one or more interleavers to generate a plurality of permutations based, at least in part, on automorphisms of the linear block code and the codeword, wherein at least one interleaver of the one or more interleavers is to be re-used multiple times as part of generating the plurality of permutations.
What exactly they claim (claim 1)
1. One or more processors, comprising: circuitry to: obtain a codeword generated based, at least in part, on a linear block code; use one or more interleavers to generate a plurality of permutations based, at least in part, on automorphisms of the linear block code and the codeword, wherein at least one interleaver is to be used a plurality of times to generate the plurality of permutations; perform a plurality of decoding operations based, at least in part, on the plurality of permutations to generate a plurality of output sequences; determine one or more values based, at least in part, on the plurality of output sequences and the codeword; and select an output sequence of the plurality of output sequences based, at least in part, on the one or more values.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- DECODING CODEWORDS ENCODED USING LINEAR BLOCK CODES
- Publication number
- US20260303126A1
- Application number
- 19334375
- Filed
- Sep 19, 2025
- Published
- Oct 1, 2026
- Inventors
- 3
- Claims
- 20
Classified under
H03M 13/2778 Electricity & electronicsH03M 13/37 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.