Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Dynamically partitioning workload in a deep neural network module to reduce power consumption

Dynamically partitioning workload in a deep neural network module to reduce power consumption

US Patent 11476869 · Granted Oct 18, 2022

Estimated economic value: $176,053,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Increased precision neural processing element2024
Increased precision neural processing element2024
Increased precision neural processing element2024
Increased precision neural processing element2024
Increased precision neural processing element2024
Increased precision neural processing element2024
Neural network processor using compression and decompression of activation data 2024
Neural network processor using compression and decompression of activation data 2024
Neural network processor using compression and decompression of activation data 2024
Neural network processor using compression and decompression of activation data 2024
Neural network processor using compression and decompression of activation data 2024
Neural network processor using compression and decompression of activation data 2024