{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T14:25:38Z","timestamp":1762957538997,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,15]]},"DOI":"10.1145\/3674558.3674562","type":"proceedings-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T12:26:16Z","timestamp":1724675176000},"page":"20-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Layer-wise Exploration of a Neural Processing Unit Compiler's Optimization Space"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2973-4131","authenticated-orcid":false,"given":"Fabrizio","family":"Indirli","sequence":"first","affiliation":[{"name":"Politecnico di Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4293-6224","authenticated-orcid":false,"given":"Andrea Carlo","family":"Ornstein","sequence":"additional","affiliation":[{"name":"STMicroelectronics, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3901-0770","authenticated-orcid":false,"given":"Giuseppe","family":"Desoli","sequence":"additional","affiliation":[{"name":"STMicroelectronics, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4956-7389","authenticated-orcid":false,"given":"Alessandro","family":"Buschini","sequence":"additional","affiliation":[{"name":"STMicroelectronics, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1668-0883","authenticated-orcid":false,"given":"Cristina","family":"Silvano","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-9795","authenticated-orcid":false,"given":"Vittorio","family":"Zaccaria","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"20017. XLA: Optimizing Compiler for Machine Learning. https:\/\/www.tensorflow.org\/xla."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Meghan Cowan Haichen Shen Leyuan Wang Yuwei Hu Luis Ceze Carlos Guestrin and Arvind Krishnamurthy. [n. d.]. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. https:\/\/doi.org\/10.48550\/arXiv.1802.04799 arxiv:1802.04799 [cs]","DOI":"10.48550\/arXiv.1802.04799"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"K. Deb A. Pratap S. Agarwal and T. Meyarivan. [n. d.]. A fast and elitist multiobjective genetic algorithm: NSGA-II. 6 2 ([n. d.]). https:\/\/doi.org\/10.1109\/4235.996017","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870349"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Ahmet Erdem Cristina Silvano Thomas Boesch Andrea\u00a0Carlo Ornstein Surinder-Pal Singh and Giuseppe Desoli. [n. d.]. Runtime Design Space Exploration and Mapping of DCNNs for the Ultra-Low-Power Orlando SoC. 17 2 ([n. d.]). https:\/\/doi.org\/10.1145\/3379933","DOI":"10.1145\/3379933"},{"key":"e_1_3_2_1_6_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. [n. d.]. Deep Residual Learning for Image Recognition. arxiv:1512.03385https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Forrest\u00a0N. Iandola Song Han Matthew\u00a0W. Moskewicz Khalid Ashraf William\u00a0J. Dally and Kurt Keutzer. [n. d.]. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. https:\/\/doi.org\/10.48550\/arXiv.1602.07360 arxiv:1602.07360 [cs]","DOI":"10.48550\/arXiv.1602.07360"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3030548"},{"key":"e_1_3_2_1_10_1","unstructured":"M.\u00a0G.\u00a0Sarwar Murshed Christopher Murphy Daqing Hou Nazar Khan Ganesh Ananthanarayanan and Faraz Hussain. [n. d.]. Machine Learning at the Network Edge: A Survey. ([n. d.]). arxiv:1908.00080http:\/\/arxiv.org\/abs\/1908.00080"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2009.2028681"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Nadav Rotem Jordan Fix Saleem Abdulrasool Garret Catron Summer Deng Roman Dzhabarov Nick Gibson James Hegeman Meghan Lele Roman Levenstein Jack Montgomery Bert Maher Satish Nadathur Jakob Olesen Jongsoo Park Artem Rakhov Misha Smelyanskiy and Man Wang. [n. d.]. Glow: Graph Lowering Compiler Techniques for Neural Networks. https:\/\/doi.org\/10.48550\/arXiv.1805.00907 arxiv:1805.00907 [cs]","DOI":"10.48550\/arXiv.1805.00907"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8837-9_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2007.904345"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2017.7993626"},{"key":"e_1_3_2_1_18_1","unstructured":"Mingxing Tan and Quoc\u00a0V. Le. [n. d.]. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arxiv:1905.11946 [cs stat]http:\/\/arxiv.org\/abs\/1905.11946"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496885"}],"event":{"name":"ICCTA 2024: 2024 10th International Conference on Computer Technology Applications","acronym":"ICCTA 2024","location":"Vienna Austria"},"container-title":["Proceedings of the 2024 10th International Conference on Computer Technology Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674558.3674562","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674558.3674562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:41:37Z","timestamp":1755906097000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674558.3674562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,15]]},"references-count":21,"alternative-id":["10.1145\/3674558.3674562","10.1145\/3674558"],"URL":"https:\/\/doi.org\/10.1145\/3674558.3674562","relation":{},"subject":[],"published":{"date-parts":[[2024,5,15]]},"assertion":[{"value":"2024-08-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}