Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Providing flexible matrix processors for performing neural network convolution in matrix-processor-based devices

Providing flexible matrix processors for performing neural network convolution in matrix-processor-based devices

US Patent 10936943 · Granted Mar 2, 2021

Estimated economic value: $26,072,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Training neural networks based on dual pipeline architectures2025
Single instruction multiple data (SIMD) sparse decompression with variable densi2025
Hardware-based image/video processing in machine learning-accelerator system-on-2025
Hardware-based image/video processing in machine learning-accelerator system-on-2025
Sparsity-based neural network mapping to computing units in a system-on-chip2025
Memory storage format for supporting machine learning acceleration2024
Memory storage format for supporting machine learning acceleration2024
Inline decompression2024
Inline decompression2024
Method and apparatus for compressing and decompressing sparse data sets2024
Split network acceleration architecture2024
Compression circuits and methods using tree based encoding of bit masks2024