{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:35:53Z","timestamp":1730266553526,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10649961","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["OAA: An Abstraction for Efficient Accelerator Adaptation in Deep Learning Frameworks"],"prefix":"10.1109","author":[{"given":"Zhengxian","family":"Lu","sequence":"first","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengkun","family":"Du","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueshuo","family":"Xie","sequence":"additional","affiliation":[{"name":"Haihe Lab of ITAI,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiankun","family":"Dong","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Nankai University,College of Software,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref6","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282907"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref10","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"issue":"2","key":"ref11","doi-asserted-by":"crossref","DOI":"10.1145\/3377454","article-title":"A survey on distributed machine learning","volume":"53","author":"Verbraeken","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref12","first-page":"578","article-title":"Tvm: An automated end-to-end optimizing compiler for deep learning","volume-title":"13th USENIX Symp. OSDI","author":"Chen"},{"journal-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions","year":"2018","author":"Vasilache","key":"ref13"},{"key":"ref14","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"14th USENIX Symp. OSDI","author":"Zheng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582061"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476206","article-title":"Tensor processing primitives: A programming abstraction for efficiency and portability in deep learning workloads","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage and Anal","author":"Georganas"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref18","first-page":"804","article-title":"Tensorir: An abstraction for automatic ten-sorized program optimization","volume-title":"Proc. 28th ACM Int. Conf. ASPLOS","volume":"2","author":"Feng"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455972"},{"journal-title":"Oneflow: Redesign the distributed deep learning framework from scratch","year":"2021","author":"Yuan","key":"ref21"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref23"},{"key":"ref24","article-title":"Mixed precision training","author":"Micikevicius","year":"2018","journal-title":"ICLR"},{"key":"ref25","article-title":"Large scale distributed deep networks","volume":"25","author":"Dean","year":"2012","journal-title":"NeurIPS"},{"journal-title":"Fast training of convolutional networks through ffts","year":"2013","author":"Mathieu","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"journal-title":"cudnn: Efficient primitives for deep learning","year":"2014","author":"Chetlur","key":"ref28"},{"journal-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","year":"2015","author":"Chen","key":"ref29"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s42514-023-00168-6"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10649961.pdf?arnumber=10649961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:52:51Z","timestamp":1725943971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10649961","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}