{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11528033","patent":{"patent_number":"US-11528033","title":"Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization","assignee":null,"inventors":[],"filing_date":"2018-04-13T00:00:00.000Z","publication_date":"2022-12-13T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","G06N","G06N","G06N","H04L","H04L","H04L","G06F","G06F","G06F","G06F","G06F","G06F","H04L"],"num_claims":20,"abstract":"A deep neural network (“DNN”) module compresses and decompresses neuron-generated activation data to reduce the utilization of memory bus bandwidth. The compression unit receives an uncompressed chunk of data generated by a neuron in the DNN module. The compression unit generates a mask portion and a data portion of a compressed output chunk. The mask portion encodes the presence and location of the zero and non-zero bytes in the uncompressed chunk of data. The data portion stores truncated non-zero bytes from the uncompressed chunk of data. A decompression unit receives a compressed chunk of data from memory in the DNN processor or memory of an application host. The decompression unit decompresses the compressed chunk of data using the mask portion and the data portion."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization","description":"A deep neural network (“DNN”) module compresses and decompresses neuron-generated activation data to reduce the utilization of memory bus bandwidth. The compression unit receives an uncompressed chunk","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11528033","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-11528033","citation_suggestion":"Patentable. \"Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization\" (US-11528033). https://patentable.app/patents/US-11528033","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11528033","json":"https://patentable.app/api/llm-context/US-11528033","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T06:52:02.761Z"}