{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T01:29:45Z","timestamp":1762046985360,"version":"build-2065373602"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Shanghai Committee of Science and Technology China","award":["20DZ110080"],"award-info":[{"award-number":["20DZ110080"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation China","doi-asserted-by":"crossref","award":["U21B2017"],"award-info":[{"award-number":["U21B2017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpds.2021.3138862","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:04:51Z","timestamp":1640725491000},"page":"1-1","source":"Crossref","is-referenced-by-count":7,"title":["NeoFlow: A Flexible Framework for Enabling Efficient Compilation for High Performance DNN Training"],"prefix":"10.1109","author":[{"given":"Size","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renze","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicheng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref38","article-title":"Optimizing DNN computation with relaxed graph substitutions","author":"jia","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459852"},{"article-title":"Ansor: Generating high-performance tensor programs for deep learning","year":"2020","author":"zheng","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref30","article-title":"Chameleon: Adaptive code optimization for expedited deep neural network compilation","author":"ahn","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref37","article-title":"Autograd: Effortless gradients in numpy","author":"maclaurin","year":"2015","journal-title":"Proc Int Conf Mach Learn Workshop"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref35","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc 4th Int Conf Learn Representations"},{"article-title":"Automatic differentiation for tensor algebras","year":"2017","author":"urban","key":"ref34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"year":"2020","key":"ref27","article-title":"Onednn"},{"key":"ref29","first-page":"3393","article-title":"Learning to optimize tensor programs","author":"chen","year":"2018","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"year":"2020","key":"ref20","article-title":"PyTorch TVM integration"},{"article-title":"Intel ngraph: An intermediate representation, compiler, and executor for deep learning","year":"2018","author":"cyphers","key":"ref22"},{"article-title":"Relay: A high-level IR for deep learning","year":"2019","author":"roesch","key":"ref21"},{"year":"2020","key":"ref24","article-title":"TensorFlow XLA"},{"key":"ref23","first-page":"23","article-title":"Compiling machine learning programs via high-level tracing","author":"frostig","year":"2018","journal-title":"Machine Learning and Systems"},{"year":"2020","key":"ref26","article-title":"MKL"},{"year":"2021","key":"ref25","article-title":"CUBLAS"},{"article-title":"Xception: Deep learning with depthwise separable convolutions","year":"2016","author":"chollet","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"article-title":"DLVM: A modern compiler infrastructure for deep learning systems","year":"2017","author":"wei","key":"ref54"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1177\/1094342019866247"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908105"},{"article-title":"cuDNN: Efficient primitives for deep learning","year":"2014","author":"chetlur","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref12","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref13","article-title":"Matrix capsules with EM routing","author":"hinton","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","first-page":"2856","article-title":"On multiplicative integration with recurrent neural networks","author":"wu","year":"2016","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref15","article-title":"Learning longer memory in recurrent neural networks","author":"mikolov","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref17","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 13th USENIX Symp Oper Syst Des Implementation"},{"year":"2020","key":"ref18","article-title":"PlaidML"},{"article-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions","year":"2018","author":"vasilache","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"article-title":"Language models are few-shot learners","year":"2020","author":"brown","key":"ref6"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref5"},{"key":"ref8","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Oper Syst Des Implementation"},{"key":"ref7","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref49"},{"article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","year":"2015","author":"chen","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"year":"2021","key":"ref45","article-title":"CUDA grah"},{"year":"2020","key":"ref48"},{"key":"ref47","first-page":"272","article-title":"Cortical microcircuits as gated-recurrent neural networks","author":"costa","year":"2017","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"article-title":"Dissecting the NVIDIA volta GPU architecture via microbenchmarking","year":"2018","author":"jia","key":"ref42"},{"article-title":"Deep learning using rectified linear units (ReLU)","year":"2018","author":"agarap","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"year":"0","key":"ref43","article-title":"CUDA NVCC compiler"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/09664259.pdf?arnumber=9664259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T15:57:31Z","timestamp":1653580651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9664259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3138862","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2021]]}}}