{"@context": "https://schema.org", "@type": "BreadcrumbList", "itemListElement": [{"@type": "ListItem", "position": 1, "name": "Home", "item": "https://www.patentleaderboard.com/"}, {"@type": "ListItem", "position": 2, "name": "Exploiting input data sparsity in neural network compute units", "item": "https://www.patentleaderboard.com/patent/11106606"}]}
Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Exploiting input data sparsity in neural network compute units

Exploiting input data sparsity in neural network compute units

US Patent 11106606 · Granted Aug 31, 2021

Estimated economic value: $105,739,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Redistributing tensor elements between machine learning computing units2025
Redistributing tensor elements between machine learning computing units2025
Neural network compute tile2025
Neural network compute tile2025
Virtualizing external memory as local to a machine learning accelerator2025
Permuting in a matrix-vector processor2025
Scheduling neural network processing2025
Preemption in a machine learning hardware accelerator2025
Processing sequential inputs using neural network accelerators2024
Apparatus and mechanism for processing neural network tasks using a single chip 2024
Apparatus and mechanism for processing neural network tasks using a single chip 2024
Neural network instruction set architecture2024