{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/validating-utf-8-in-less-than-one-instruction","title":"Validating UTF-8 In Less Than One Instruction Per Byte","arxiv_id":"2010.03090","date":"2020-10-06","proceeding":null,"authors":["John Keiser","Daniel Lemire"],"abstract":"The majority of text is stored in UTF-8, which must be validated on ingestion. We present the lookup algorithm, which outperforms UTF-8 validation routines used in many libraries and languages by more than 10 times using commonly available SIMD instructions. To ensure reproducibility, our work is freely available as open source software.","url_abs":"https://arxiv.org/abs/2010.03090v4","url_pdf":"https://arxiv.org/pdf/2010.03090v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"validating-utf-8-in-less-than-one-instruction","repo_url":"https://github.com/lemire/validateutf8-experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"validating-utf-8-in-less-than-one-instruction","repo_url":"https://github.com/lemire/simdjson","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"validating-utf-8-in-less-than-one-instruction","repo_url":"https://github.com/rusticstuff/simdutf8","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"validating-utf-8-in-less-than-one-instruction","repo_url":"https://github.com/simdjson/simdjson","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}