{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:02:28Z","timestamp":1773824548995,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012282","name":"Beijing Innovation Center for Future Chips","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012282","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014121","name":"Tsinghua Xilinx AI Research Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018YFB0105005"],"award-info":[{"award-number":["2018YFB0105005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61622403"],"award-info":[{"award-number":["61622403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61621091"],"award-info":[{"award-number":["61621091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Project of Tsinghua University and Toyota Joint Research Center for AI Technology of Automated Vehicle","doi-asserted-by":"publisher","award":["TT2018-01"],"award-info":[{"award-number":["TT2018-01"]}],"id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tcad.2019.2930577","type":"journal-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T20:37:38Z","timestamp":1563914258000},"page":"2668-2681","source":"Crossref","is-referenced-by-count":70,"title":["DNNVM: End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-Based CNN Accelerators"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7715-2702","authenticated-orcid":false,"given":"Yu","family":"Xing","sequence":"first","affiliation":[]},{"given":"Shuang","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Lingzhi","family":"Sui","sequence":"additional","affiliation":[]},{"given":"Xijie","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Jiantao","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yushun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Shan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","year":"2019","journal-title":"Paddlepaddle"},{"key":"ref38","year":"2003","journal-title":"Scheme48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref32","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","volume":"abs 1603 4467","author":"abadi","year":"2016","journal-title":"CoRR"},{"key":"ref31","author":"redmon","year":"2019","journal-title":"Darknet"},{"key":"ref30","author":"jia","year":"2019","journal-title":"Caffe"},{"key":"ref37","article-title":"Embedded vision with INT8 optimization on Xilinx devices, (v1.0.1)","author":"fu","year":"2017"},{"key":"ref36","author":"tidwell","year":"2005","journal-title":"XAPP706 Alpha Blending Two Data Streams Using a DSP48 DDR Technique"},{"key":"ref35","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume":"abs 1702 3044","author":"zhou","year":"2017","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062244"},{"key":"ref28","article-title":"DLVM: A modern compiler infrastructure for deep learning systems","author":"wei","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref27","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref29","article-title":"Tensor comprehensions: Framework-agnostic high-performance machine","volume":"abs 1802 4730","author":"vasilache","year":"2018","journal-title":"CoRR"},{"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 Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref20","article-title":"Compiling deep learning models for custom hardware accelerators","volume":"abs 1708 117","author":"chang","year":"2017","journal-title":"CoRR"},{"key":"ref22","year":"2019","journal-title":"LLVM"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00077"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178507"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925952"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694364"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.129"},{"key":"ref11","year":"2019","journal-title":"Next-Level Computing Powered by Intel AI"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref12","year":"2019","journal-title":"Voltage"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"ref14","year":"2019","journal-title":"Adaptive Machine Learning Acceleration"},{"key":"ref15","first-page":"291","article-title":"fpgaConvNet: Automated mapping of convolutional neural networks on FPGAs","author":"venieris","year":"2017","journal-title":"Proc FPGA"},{"key":"ref16","article-title":"VTA: An open hardware-software stack for deep learning","volume":"abs 1807 4188","author":"moreau","year":"2018","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref4","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume":"abs 1704 4861","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref6","first-page":"1025","article-title":"Optimizing CNN model inference on CPUs","author":"liu","year":"2019","journal-title":"Proc of USENIX Annual Technical Conf (USENIX)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cps.2016.0020"},{"key":"ref8","year":"2019","journal-title":"NervanaGPU"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00033"},{"key":"ref46","article-title":"Intel nGraph: An intermediate representation, compiler, and executor for deep learning","volume":"abs 1801 8058","author":"cyphers","year":"2018","journal-title":"CoRR"},{"key":"ref45","article-title":"YOLOv3: An incremental improvement","volume":"abs 1804 2767","author":"redmon","year":"2018","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3186332"},{"key":"ref47","year":"2019","journal-title":"XLA Overview"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.75"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/321921.321925"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.14778\/2535568.2448946"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.14778\/2735479.2735493"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/9204502\/08770305.pdf?arnumber=8770305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:05:32Z","timestamp":1651068332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8770305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":49,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2019.2930577","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}