{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:22:20Z","timestamp":1776468140980,"version":"3.51.2"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/icess.2019.8782480","type":"proceedings-article","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T20:01:41Z","timestamp":1564689701000},"page":"1-8","source":"Crossref","is-referenced-by-count":12,"title":["An In-depth Comparison of Compilers for Deep Neural Networks on Hardware"],"prefix":"10.1109","author":[{"given":"Yu","family":"Xing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingzhi","family":"Sui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2016.05.004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115709"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref32","author":"yizhi","year":"2018","journal-title":"Optimizing CNN model inference on CPUs"},{"key":"ref31","year":"0","journal-title":"Nvidia tensorrt"},{"key":"ref30","year":"0","journal-title":"Chainer"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1145\/354222.353187","article-title":"OoLaLa: An object oriented analysis and design of numerical linear algebra","volume":"35","author":"an","year":"2000","journal-title":"ACM SIGPLAN Notices"},{"key":"ref36","author":"truong","year":"2016","journal-title":"Latte A language compiler and runtime for elegant and efficient deep neural networks"},{"key":"ref35","author":"moreau","year":"2018","journal-title":"Vta An open hardware-software stack for deep learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"ref28","first-page":"1","article-title":"DaDianNao: A neural network supercomputer","volume":"66","author":"tao","year":"2016","journal-title":"TOC"},{"key":"ref27","author":"cyphers","year":"2018","journal-title":"Intel nGraph An intermediate representation compiler and executor for deep learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925952"},{"key":"ref2","year":"0","journal-title":"Caffe"},{"key":"ref1","year":"0","journal-title":"TensorFlow&#x2122;"},{"key":"ref20","year":"0","journal-title":"Mxnet"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211348"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-006-0012-3"},{"key":"ref24","year":"0","journal-title":"The Llvm Compiler Infrastructure"},{"key":"ref23","article-title":"Polly - polyhedral optimization in LLVM","author":"pouchet","year":"0","journal-title":"Impact"},{"key":"ref26","author":"munshi","year":"2011","journal-title":"OpenCL"},{"key":"ref25","year":"0","journal-title":"Cuda"},{"key":"ref10","year":"0","journal-title":"MKL"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178507"},{"key":"ref11","year":"0","journal-title":"OpenBLAS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref13","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"0","journal-title":"Proc of USENIX OSDI"},{"key":"ref14","author":"wei","year":"2017","journal-title":"DLVM A Modern Compiler Infrastructure for Deep Learning Systems"},{"key":"ref15","author":"vasilache","year":"2018","journal-title":"Tensor Comprehensions Framework-Agnostic High-Performance Machine Learning Abstractions"},{"key":"ref16","year":"0","journal-title":"XLA"},{"key":"ref17","year":"0","journal-title":"xfDNN"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2930577"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref3","year":"0","journal-title":"PyTorch"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.22"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3197978"},{"key":"ref49","author":"iandola","year":"2016","journal-title":"Squeezenet Alexnet-level accuracy with 50x fewer parameters and< 0 5 mb model size"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref9","year":"0","journal-title":"Eigen"},{"key":"ref46","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Computer Science"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","author":"howard","year":"2017","journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","author":"verdoolaege","year":"2017","journal-title":"Scheduling for PPCG"},{"key":"ref41","article-title":"Pencil:a platform-neutral compute intermediate language for accelerator programming","author":"baghdadi","year":"0","journal-title":"PACT-15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1987.13876"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"}],"event":{"name":"2019 IEEE International Conference on Embedded Software and Systems (ICESS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2019,6,2]]},"end":{"date-parts":[[2019,6,3]]}},"container-title":["2019 IEEE International Conference on Embedded Software and Systems (ICESS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8771047\/8782437\/08782480.pdf?arnumber=8782480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:49:17Z","timestamp":1658141357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8782480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icess.2019.8782480","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}