{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11954025","patent":{"patent_number":"US-11954025","title":"Systems and methods for reading and writing sparse data in a neural network accelerator","assignee":null,"inventors":[],"filing_date":"2023-03-24T00:00:00.000Z","publication_date":"2024-04-09T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06N","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N"],"num_claims":20,"abstract":"Disclosed herein includes a system, a method, and a device for reading and writing sparse data in a neural network accelerator. A mask identifying byte positions within a data word having non-zero values in memory can be accessed. Each bit of the mask can have a first value or a second value, the first value indicating that a byte of the data word corresponds to a non-zero byte value, the second value indicating that the byte of the data word corresponds to a zero byte value. The data word can be modified to have non-zero byte values stored at an end of a first side of the data word in the memory, and any zero byte values stored in a remainder of the data word. The modified data word can be written to the memory via at least a first slice of a plurality of slices that is configured to access the first side of the data word in the memory."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Systems and methods for reading and writing sparse data in a neural network accelerator","description":"Disclosed herein includes a system, a method, and a device for reading and writing sparse data in a neural network accelerator. A mask identifying byte positions within a data word having non-zero val","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11954025","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11954025","citation_suggestion":"Patentable. \"Systems and methods for reading and writing sparse data in a neural network accelerator\" (US-11954025). https://patentable.app/patents/US-11954025","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11954025","json":"https://patentable.app/api/llm-context/US-11954025","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T14:02:23.595Z"}