{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:47:29Z","timestamp":1768517249729,"version":"3.49.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11322894","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Breaking the Fusion Barrier: An Online Algorithm for Fused Normalization and Linear Layers"],"prefix":"10.1109","author":[{"given":"Hanghang","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihao","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanyi","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Xing","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref2","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"cudnn: Efficient primitives for deep learning","author":"Chetlur","year":"2014","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref6","author":"Graef","year":"2025","journal-title":"Flashnorm: fast normalization for 11ms"},{"key":"ref7","author":"Grattafiori","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref8","author":"Gray","year":"2019","journal-title":"Getting started with cuda graphs."},{"key":"ref9","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe","year":"2015"},{"key":"ref10","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Tensorrt: Programmable inference accelerator","year":"2025","journal-title":"NVIDIA"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2193"},{"key":"ref14","year":"2025","journal-title":"Chameleon: Mixed-modal early-fusion foundation models"},{"key":"ref15","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1962.10490022"},{"key":"ref17","first-page":"21","article-title":"Mirage: A \\{Multi-Level\\} superoptimizer for tensor programs","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Wu","year":"2025"},{"key":"ref18","article-title":"Qwen3 technical report","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11322894.pdf?arnumber=11322894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:50:21Z","timestamp":1768463421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11322894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11322894","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}