{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:49:55Z","timestamp":1756460995087,"version":"3.28.0"},"reference-count":87,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/asap.2018.8445088","type":"proceedings-article","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T00:35:47Z","timestamp":1535416547000},"page":"1-8","source":"Crossref","is-referenced-by-count":12,"title":["Hardware Compilation of Deep Neural Networks: An Overview"],"prefix":"10.1109","author":[{"given":"Ruizhe","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuanglong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-Cheung","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James J.","family":"Davis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huifeng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George A.","family":"Constantinides","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter Y. K.","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref73","DOI":"10.1109\/ASAP.2017.7995253"},{"key":"ref72","first-page":"227","article-title":"Instruction Driven Cross-Layer CNN Accelerator with Winograd Transformation on FPGA","author":"yu","year":"2017","journal-title":"ICFPT"},{"key":"ref71","first-page":"101","article-title":"Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs.","author":"lu","year":"2017","journal-title":"FCCM"},{"key":"ref70","first-page":"55","article-title":"An OpenCL (TM) Deep Learning Accelerator on Arria 10","author":"aydonat","year":"2017","journal-title":"FPGA"},{"doi-asserted-by":"publisher","key":"ref76","DOI":"10.1145\/3174243.3174265"},{"key":"ref77","first-page":"1","author":"highlander","year":"2016","journal-title":"Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.1109\/HPEC.2014.7040967"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/MICRO.2016.7783720"},{"doi-asserted-by":"publisher","key":"ref75","DOI":"10.1145\/3020078.3021727"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.23919\/FPL.2017.8056824"},{"key":"ref78","article-title":"Optimizing Frequency Domain Implementation of CNNs on FPGAs","author":"zeng","year":"2017","journal-title":"Tech Rep"},{"doi-asserted-by":"publisher","key":"ref79","DOI":"10.1109\/ISCAS.2010.5537908"},{"key":"ref33","first-page":"31","article-title":"A Soft Processor Overlay with Tightly-coupled FPGA Accelerator","author":"ng","year":"2016","journal-title":"International Workshop on Overlay Architectures for FPGA (OLAF)"},{"key":"ref32","first-page":"209","article-title":"Latte: a language, compiler, and runtime for elegant and efficient deep neural networks","author":"truong","year":"2016","journal-title":"PLDI"},{"key":"ref31","first-page":"1","author":"vasilache","year":"2018","journal-title":"Tensor Comprehensions Framework-Agnostic High-Performance Machine Learning Abstractions"},{"year":"2017","author":"wei","journal-title":"DLVM A Modern Compiler Infrastructure for Deep Learning Systems","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1145\/3020078.3021736"},{"key":"ref36","first-page":"1","article-title":"Scalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA","author":"ma","year":"2016","journal-title":"FPL"},{"key":"ref35","article-title":"Polyhedral-based Dynamic Loop Pipelining for High-Level Synthesis","author":"liu","year":"2017","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"ref34","first-page":"56","article-title":"QuickDough: A Rapid FPGA Loop Accelerator Design Framework Using Soft CGRA Overlay","author":"liu","year":"2015","journal-title":"ICFPT"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1145\/355841.355847"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1007\/BF02163269"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"ref28","first-page":"1","author":"chen","year":"2018","journal-title":"TVM End-to-End Optimization Stack for Deep Learning"},{"doi-asserted-by":"publisher","key":"ref64","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref27","article-title":"Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA","author":"zhao","year":"2018","journal-title":"FPL"},{"key":"ref65","first-page":"1737","article-title":"Deep Learning with Limited Numerical Precision","author":"gupta","year":"2015","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref66","DOI":"10.1145\/2847263.2847276"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1145\/2491956.2462176"},{"doi-asserted-by":"publisher","key":"ref67","DOI":"10.1109\/FCCM.2017.25"},{"key":"ref68","first-page":"107","article-title":"A Customizable Matrix Multiplication Framework for the Intel HARPv2 Xeon + FPGA Platform A Deep Learning Case Study","author":"moss","year":"2018","journal-title":"FPGA"},{"doi-asserted-by":"publisher","key":"ref69","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref2","first-page":"189","article-title":"ADAM: Automated Design Analysis and Merging for Speeding Up FPGA Development","author":"ng","year":"2018","journal-title":"FPGA"},{"key":"ref1","first-page":"1","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref20","article-title":"Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning","author":"molchanov","year":"2017","journal-title":"ICLRE"},{"year":"2017","author":"zhang","journal-title":"ShuffleNet An Extremely Efficient Convolutional Neural Network for Mobile Devices","key":"ref22"},{"year":"2017","author":"howard","journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications","key":"ref21"},{"key":"ref24","first-page":"1","author":"zoph","year":"2016","journal-title":"Neural architecture search with reinforcement learning"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2017.195"},{"year":"2017","author":"zoph","journal-title":"Learning Transferable Architectures for Scalable Image Recognition","key":"ref26"},{"year":"2018","author":"sandler","journal-title":"MobileNetV2 Inverted Residuals and Linear Bottlenecks","key":"ref25"},{"key":"ref50","first-page":"1","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref51","first-page":"1","author":"lin","year":"2013","journal-title":"Network in Network"},{"year":"2016","author":"yang","journal-title":"A Systematic Approach to Blocking Convolutional Neural Networks","key":"ref59"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1145\/2435264.2435271"},{"key":"ref57","first-page":"29","author":"pouchet","year":"2013","journal-title":"Polyhedral-based Data Reuse Optimization for Configurable Computing"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1145\/3061639.3062244"},{"key":"ref55","article-title":"Fused-Layer CNN Accelerators","author":"manoj","year":"2016","journal-title":"Micro"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1145\/3061639.3062207"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1145\/3020078.3021698"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/ICCD.2013.6657019"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/FCCM.2016.22"},{"year":"0","author":"redmon","journal-title":"Darknct Open xource Neural Networks In C","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1145\/3174243.3174257"},{"year":"0","journal-title":"Mocha Deep Learning Framework for Julia","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/3005348"},{"key":"ref14","article-title":"Deep Compression-Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","author":"han","year":"2016","journal-title":"ICLRE"},{"year":"0","journal-title":"ONNX Open Neural Network Exchange Format","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref82","DOI":"10.1109\/HPCA.2016.7446050"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref81","first-page":"457","article-title":"Diastolic arrays: Throughput-driven Reconfigurable Computing","author":"cho","year":"2008","journal-title":"ICCAD"},{"key":"ref17","first-page":"2818","article-title":"Rethmkmg the Inception Architecture or Computer vision","author":"he","year":"2016","journal-title":"CVPR"},{"doi-asserted-by":"publisher","key":"ref84","DOI":"10.1145\/3020078.3021791"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"publisher","key":"ref83","DOI":"10.1007\/978-1-4757-2117-1"},{"key":"ref19","article-title":"Pruning Filters for Efficient Convnets","author":"li","year":"2017","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref80","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"ref4","article-title":"An Introduction to Computational Networks and the Computational Network Toolkit","volume":"112","author":"yu","year":"2015","journal-title":"Microsoft Technical Report"},{"year":"2015","author":"abadi","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems","key":"ref3"},{"key":"ref6","first-page":"3","article-title":"Theano: A CPU and GPU Math Compiler in Python","author":"bergstra","year":"2010","journal-title":"Proceedings of the 9th Python in Science Conference"},{"key":"ref5","article-title":"Torch7: A Matlab-like Environment for Machine Learning","author":"collobert","year":"2011","journal-title":"BigLearn NIPS Workshop"},{"doi-asserted-by":"publisher","key":"ref85","DOI":"10.23919\/FPL.2017.8056828"},{"key":"ref8","first-page":"1","author":"chen","year":"2015","journal-title":"Mxnet A flexible and efficient machine learning library for heterogeneous distributed systems"},{"doi-asserted-by":"publisher","key":"ref86","DOI":"10.1145\/3020078.3021744"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1145\/2647868.2654889"},{"key":"ref49","first-page":"32","article-title":"CNP: An FPGA-based processor for Convolutional Networks","author":"poulet","year":"2009","journal-title":"FPL"},{"year":"2016","author":"huang","journal-title":"Densely Connected Convolutional Networks","key":"ref87"},{"key":"ref9","first-page":"12: 1","article-title":"Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks","author":"zhang","year":"2016","journal-title":"ICCAD"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1145\/1815961.1815993"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/FPT.2013.6718414"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1145\/1854273.1854309"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/ASAP.2009.25"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ASPDAC.2016.7428073"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1145\/2684746.2689060"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1145\/1498765.1498785"},{"key":"ref43","first-page":"1147","article-title":"Design Space Exploration of FPGA Accelerators for Convolutional Neural Networks","author":"rahman","year":"2017","journal-title":"DATE"}],"event":{"name":"2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)","start":{"date-parts":[[2018,7,10]]},"location":"Milan","end":{"date-parts":[[2018,7,12]]}},"container-title":["2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8424123\/8445082\/08445088.pdf?arnumber=8445088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:04:42Z","timestamp":1643184282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8445088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/asap.2018.8445088","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}