{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:07:15Z","timestamp":1767992835643,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"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":[[2024,3,2]]},"DOI":"10.1109\/cgo57630.2024.10444871","type":"proceedings-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:47:35Z","timestamp":1709146055000},"page":"460-470","source":"Crossref","is-referenced-by-count":15,"title":["oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation"],"prefix":"10.1109","author":[{"given":"Jianhui","family":"Li","sequence":"first","affiliation":[{"name":"Intel,US"}]},{"given":"Zhennan","family":"Qin","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Yijie","family":"Mei","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Jingze","family":"Cui","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Yunfei","family":"Song","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Ciyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Longsheng","family":"Du","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Xianhang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Baihui","family":"Jin","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Jason","family":"Ye","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Eric","family":"Lin","sequence":"additional","affiliation":[{"name":"Intel,China"}]},{"given":"Dan","family":"Lavery","sequence":"additional","affiliation":[{"name":"Intel,US"}]}],"member":"263","reference":[{"key":"ref6","article-title":"MLIR: A Compiler Infrastructure for the End of Moores Law","volume":"abs\/2002.11054","author":"Lattner","year":"2020","journal-title":"CoRR"},{"key":"ref7","first-page":"578","article-title":"TVM: An automated endto-end optimizing compiler for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"ref9","article-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions","volume":"abs\/1802.04730","author":"Vasilache","year":"2018","journal-title":"CoRR"},{"key":"ref10","first-page":"233","article-title":"ROLLER: Fast and Efficient Tensor Compilation for Deep Learning","volume-title":"OSDI 2022","author":"Zhu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517770"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3433103"},{"key":"ref17","article-title":"AITemplate: Faster, more flexible inference on GPUs using AITemplate","journal-title":"a revolutionary new inference engine"},{"key":"ref18","article-title":"Deep learning recommendation model for personalization and recommendation systems","volume":"abs\/1906.00091","author":"Naumov","year":"2019","journal-title":"CoRR"},{"issue":"1","key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.51130\/graphicon-2020-2-2-2"},{"key":"ref21","author":"Vasilache","journal-title":"Composable and Modular Code Generation in MLIR: A Structured and Retargetable Approach to Tensor Compiler Construction"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476206"},{"issue":"49","key":"ref25","first-page":"863","article-title":"Ansor: generating high-performance tensor programs for deep learning","volume-title":"OSDI20: Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation","author":"Zheng"},{"key":"ref26","article-title":"The Deep Learning Compiler: A Comprehensive Survey","volume":"abs\/2002.03794","author":"Li","year":"2020","journal-title":"CoRR"},{"key":"ref27","article-title":"Learning to optimize tensor programs","volume-title":"Nips18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsDecember 2018 Pages 3393\u20133404","author":"Chen"},{"key":"ref28","article-title":"Stripe: Tensor compilation via the nested polyhedral model","volume":"abs\/1903.06498","author":"Zerrell","year":"2019","journal-title":"CoRR"},{"key":"ref29","volume-title":"Intel Extension for PyTorch"}],"event":{"name":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Edinburgh, United Kingdom","start":{"date-parts":[[2024,3,2]]},"end":{"date-parts":[[2024,3,6]]}},"container-title":["2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10444766\/10444770\/10444871.pdf?arnumber=10444871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:48:31Z","timestamp":1709272111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cgo57630.2024.10444871","relation":{},"subject":[],"published":{"date-parts":[[2024,3,2]]}}}