{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11948224","patent":{"patent_number":"US-11948224","title":"Compute optimizations for low precision machine learning operations","assignee":null,"inventors":[],"filing_date":"2022-11-01T00:00:00.000Z","publication_date":"2024-04-02T00:00:00.000Z","cpc_codes":["G06T","G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","G06F","G06F","G06T","G06T"],"num_claims":20,"abstract":"One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instruction, multiple thread (SIMT) architecture, the parallel processor coupled to the memory stack via one or more memory interfaces. At least one multiprocessor comprises a multiply-accumulate circuit to perform multiply-accumulate operations on matrix data in a stage of a neural network implementation to produce a result matrix comprising a plurality of matrix data elements at a first precision, precision tracking logic to evaluate metrics associated with the matrix data elements and indicate if an optimization is to be performed for representing data at a second stage of the neural network implementation, and a numerical transform unit to dynamically perform a numerical transform operation on the matrix data elements based on the indication to produce transformed matrix data elements at a second precision."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Compute optimizations for low precision machine learning operations","description":"One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instru","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11948224","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-11948224","citation_suggestion":"Patentable. \"Compute optimizations for low precision machine learning operations\" (US-11948224). https://patentable.app/patents/US-11948224","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11948224","json":"https://patentable.app/api/llm-context/US-11948224","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T03:22:42.413Z"}