{"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/shared-microexponents-a-little-shifting-goes","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","arxiv_id":"2302.08007","date":"2023-02-16","proceeding":null,"authors":["Bita Rouhani","Ritchie Zhao","Venmugil Elango","Rasoul Shafipour","Mathew Hall","Maral Mesmakhosroshahi","Ankit More","Levi Melnick","Maximilian Golub","Girish Varatkar","Lei Shao","Gaurav Kolhe","Dimitry Melts","Jasmine Klar","Renee L'Heureux","Matt Perry","Doug Burger","Eric Chung","Zhaoxia Deng","Sam Naghshineh","Jongsoo Park","Maxim Naumov"],"abstract":"This paper introduces Block Data Representations (BDR), a framework for exploring and evaluating a wide spectrum of narrow-precision formats for deep learning. It enables comparison of popular quantization standards, and through BDR, new formats based on shared microexponents (MX) are identified, which outperform other state-of-the-art quantization approaches, including narrow-precision floating-point and block floating-point. MX utilizes multiple levels of quantization scaling with ultra-fine scaling factors based on shared microexponents in the hardware. The effectiveness of MX is demonstrated on real-world models including large-scale generative pretraining and inferencing, and production-scale recommendation systems.","url_abs":"https://arxiv.org/abs/2302.08007v2","url_pdf":"https://arxiv.org/pdf/2302.08007v2.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":"abstracts"},"code_links":[{"paper_slug":"shared-microexponents-a-little-shifting-goes","repo_url":"https://github.com/rocm/tensorcast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.08007","atlas_url":"https://app.syntology.ai/?focus=2302.08007","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}