{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:45:36Z","timestamp":1761324336681,"version":"3.37.3"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010661","name":"European Union\u2019s Horizon 2020 Research and Innovation Programme","doi-asserted-by":"publisher","award":["732204 (Bonseyes)"],"award-info":[{"award-number":["732204 (Bonseyes)"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swiss State Secretariat for Education, Research and Innovation","award":["16.0159"],"award-info":[{"award-number":["16.0159"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/tcad.2020.3046568","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T20:47:07Z","timestamp":1608670027000},"page":"2293-2305","source":"Crossref","is-referenced-by-count":8,"title":["Automated Design Space Exploration for Optimized Deployment of DNN on Arm Cortex-A CPUs"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4350-1617","authenticated-orcid":false,"given":"Miguel","family":"de Prado","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0467-653X","authenticated-orcid":false,"given":"Andrew","family":"Mundy","sequence":"additional","affiliation":[]},{"given":"Rabia","family":"Saeed","sequence":"additional","affiliation":[]},{"given":"Maurizo","family":"Denna","sequence":"additional","affiliation":[]},{"given":"Nuria","family":"Pazos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-3806","authenticated-orcid":false,"given":"Luca","family":"Benini","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"journal-title":"Developments in the Arm A-Profile Architecture Armv8 6-A","year":"2019","author":"stephens","key":"ref71"},{"journal-title":"Exploring the Arm dot product instructions","year":"2017","author":"andrews","key":"ref70"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"journal-title":"Pruning neural networks Is it time to nip it in the bud?","year":"2018","author":"crowley","key":"ref32"},{"key":"ref31","first-page":"4978","article-title":"SpArSe: Sparse architecture search for CNNs on resource-constrained microcontrollers","author":"fedorov","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021740"},{"journal-title":"PACT Parameterized Clipping Activation for Quantized Neural Networks","year":"2018","author":"choi","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref35","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Ristretto Hardware-Oriented Approximation of Convolutional Neural Networks","year":"2016","author":"gysel","key":"ref34"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref60"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Designing Neural Network Architectures using Reinforcement Learning","year":"2016","author":"baker","key":"ref61"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref28","first-page":"2888","article-title":"Moonshine: Distilling with cheap convolutions","author":"crowley","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","first-page":"863","author":"wiewiora","year":"2010","journal-title":"Reward Shaping"},{"journal-title":"Distilling a neural network into a soft decision tree","year":"2017","author":"frosst","key":"ref27"},{"journal-title":"Arm Ltd Cortex-A53","year":"2020","key":"ref65"},{"journal-title":"ARM’s Cortex A57 and A53","year":"2012","author":"lal shimpi","key":"ref66"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3134442"},{"journal-title":"Arm Ltd Cortex-A57","year":"2020","key":"ref67"},{"journal-title":"ARM Reveals Cortex-A72 Architecture Details","year":"2015","author":"frumusanu","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3203217.3203282"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref26"},{"journal-title":"Efficient multi-objective neural architecture search via lamarckian evolution","year":"2018","author":"elsken","key":"ref25"},{"journal-title":"OpenBLAS","year":"2020","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref59","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"journal-title":"Deep reinforcement learning An overview","year":"2017","author":"li","key":"ref58"},{"journal-title":"cuDNN Efficient Primitives for Deep Learning","year":"2014","author":"chetlur","key":"ref57"},{"journal-title":"ArmCL","year":"2020","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3076259"},{"key":"ref54","article-title":"Optimising convolutional neural networks inference on low-powered GPUs","author":"rovder","year":"2019","journal-title":"Proc 12th Int Workshop Programmability Archit Heterogeneous Multicores (MULTIPROG)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714959"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding","year":"2015","author":"han","key":"ref11"},{"journal-title":"Mixed precision quantization of convnets via differentiable neural architecture search","year":"2018","author":"wu","key":"ref40"},{"journal-title":"And the bit goes down Revisiting the quantization of neural networks","year":"2019","author":"stock","key":"ref12"},{"journal-title":"Low-memory gemm-based convolution algorithms for deep neural networks","year":"2017","author":"anderson","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/EMC249363.2019.00008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.01.013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.111"},{"journal-title":"Ai pipeline-bringing ai to you End-to-end integration of data algorithms and deployment tools","year":"2019","author":"de prado","key":"ref18"},{"key":"ref19","first-page":"340","article-title":"Optimal DNN primitive selection with partitioned Boolean quadratic programming","author":"anderson","year":"2018","journal-title":"Proc Int Symp Code Generation Optim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s13244-018-0639-9"},{"journal-title":"SqueezeNet AlexNet-level accuracy with 50x fewer parameters and","year":"2016","author":"iandola","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.9790\/9622-0703022024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"journal-title":"High performance zero-memory overhead direct convolutions","year":"2018","author":"zhang","key":"ref49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3309551"},{"journal-title":"Up or down? adaptive rounding for post-training quantization","year":"2020","author":"nagel","key":"ref46"},{"key":"ref45","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","author":"banner","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"FFT vs Direct Convolution","year":"2019","key":"ref48"},{"journal-title":"The indirect convolution algorithm","year":"2019","author":"dukhan","key":"ref47"},{"key":"ref42","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","author":"zhao","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Quantizing deep convolutional networks for efficient inference A whitepaper","year":"2018","author":"krishnamoorthi","key":"ref41"},{"journal-title":"Caffe-Int8-Convert-Tools","year":"2020","key":"ref44"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/9579466\/09302888.pdf?arnumber=9302888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:32Z","timestamp":1652194172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9302888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":73,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2020.3046568","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}