{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:49:04Z","timestamp":1761324544452,"version":"3.40.3"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031427848"},{"type":"electronic","value":"9783031427855"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-42785-5_2","type":"book-chapter","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T12:03:37Z","timestamp":1692965017000},"page":"18-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Comparative Study of Neural Network Compilers on ARMv8 Architecture"],"prefix":"10.1007","author":[{"given":"Theologos","family":"Anthimopulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Keramidas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasilios","family":"Kelefouras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iakovos","family":"Stamoulis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,26]]},"reference":[{"key":"2_CR1","unstructured":"Aakanksha, C., Warden, P., Shlens, J., Howard, A., Rhodes, R.:  Visual wake words dataset. arXiv preprint arXiv:1906.05721 (2019)"},{"key":"2_CR2","unstructured":"AlexNet. url: https:\/\/cvml.ista.ac.at\/courses\/DLWT_W17\/material\/AlexNet.pdf"},{"key":"2_CR3","unstructured":"Cafee2 framework. url: https:\/\/caffe2.ai\/"},{"key":"2_CR4","unstructured":"Chen, T., et al.: An automated end-to-end optimizing compiler for deep learning. arXiv preprint arXiv:1802.04799 (2018)"},{"key":"2_CR5","unstructured":"Cheng, Y.,  Wang, D.,  Zhou, P., Zhang, T.:  A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)"},{"key":"2_CR6","unstructured":"CuDNN. url: https:\/\/developer.nvidia.com\/cudnn"},{"key":"2_CR7","unstructured":"David, R., et al.: TensorFlow Lite Micro: Embedded machine learning on TinyML systems. arXiv preprint arXiv:2010.08678 (2020)"},{"key":"2_CR8","unstructured":"Diniz, P.C., Cardoso, J.M.P., Coutinho, J.G.F.: Embedded computing for high performance (2017)"},{"key":"2_CR9","unstructured":"GLOW graph-level optimization. url: https:\/\/github.com\/pytorch\/glow\/blob\/master\/docs\/Optimizations.md"},{"key":"2_CR10","unstructured":"GLOW. url: https:\/\/github.com\/pytorch\/glow"},{"key":"2_CR11","unstructured":"GLOW with CMSIS support. url: https:\/\/github.com\/Theoo1997\/glow"},{"key":"2_CR12","unstructured":"Graph Optimizations url: https:\/\/onnxruntime.ai\/docs\/performance\/model-optimizations\/graph-optimizations.html#graph-optimization-levels"},{"key":"2_CR13","unstructured":"Halide library. url: https:\/\/halide-lang.org\/"},{"key":"2_CR14","unstructured":"HLO IR. url: https:\/\/github.com\/tensorflow\/mlir-hlo"},{"key":"2_CR15","unstructured":"Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017"},{"key":"2_CR16","unstructured":"Intel ngraph: An intermediate representation, compiler, and executor for deep learning. url: https:\/\/github.com\/NervanaSystems\/ngraph"},{"key":"2_CR17","unstructured":"Jiang, X., et al.: MNN: a universal and efficient inference engine. arXiv preprint arXiv: 2002.12418v1 (2020)"},{"key":"2_CR18","unstructured":"Keras FLOPs. url: https:\/\/pypi.org\/project\/keras-flops\/"},{"key":"2_CR19","unstructured":"Koizumi, Y., et al.: Unsupervised anomalous sound detection for machine condition monitoring. arXiv:2006.05822 (2020)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Koizumi, Y., Saito, S., Harada, N  Uematsu, H.,  Imoto, K.:  ToyADMOS: A dataset of miniature-machine operating sounds for anomalous sound detection. Workshop on Applications of Signal Processing to Audio and Acoustics (2019)","DOI":"10.1109\/WASPAA.2019.8937164"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.:  Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"key":"2_CR22","unstructured":"Lai, L., Suda, N., Chandra, V.: CMSIS-NN: efficient neural network kernels for Arm Cortex-M CPUs. arXiv preprint arXiv:1801.06601, 2018"},{"key":"2_CR23","unstructured":"Lattner, C., et al.: MLIR: A compiler infrastructure for the end of moore's law. arXiv preprint arxiv:2002.11054 (2020)"},{"key":"2_CR24","unstructured":"Leary, C., Wang, T.: XLA: TensorFlow (2017)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y.,  Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","DOI":"10.1109\/5.726791"},{"key":"2_CR26","unstructured":"LeCun, Y., Cortes, C., Burges, J.C.: The MNIST database of handwritten digits. Microsoft Res. 1998"},{"key":"2_CR27","unstructured":"M. Li, et al.: The deep learning compiler: a comprehensive survey. arXiv preprint arXiv: 2002.03794 (2020)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Lin, W.F., et al.: ONNC: a compilation framework connecting ONNX to proprietary deep learning accelerators. In: 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) (2019)","DOI":"10.1109\/AICAS.2019.8771510"},{"key":"2_CR29","unstructured":"Luo, C.,  He, X., Zhan, J., Wang, L., Gao, W., Dai, J.:  Comparison and benchmarking of AI models and frameworks on mobile devices. arXiv preprint arXiv: 2005.05085 (2020)"},{"key":"2_CR30","unstructured":"nGraph IR. url: https:\/\/docs.openvino.ai\/2020.2\/_docs_IE_DG_nGraph_Flow.html"},{"key":"2_CR31","unstructured":"NNAPI. url: https:\/\/developer.android.com\/ndk\/guides\/neuralnetworks"},{"key":"2_CR32","unstructured":"oneAPI. url: https:\/\/github.com\/oneapi-src\/oneDNN"},{"key":"2_CR33","unstructured":"ONNX. url: https:\/\/onnx.ai\/"},{"key":"2_CR34","unstructured":"OpenVino toolkit: Neural network compression framework (NNCF). url: https:\/\/docs.openvino.ai\/2022.1\/docs_nncf_introduction.html"},{"key":"2_CR35","unstructured":"Paszke, A., et al.: PyTorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv: 1912.01703 (2019)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Purohit, H., et al.: MIMII dataset: sound dataset for malfunctioning industrial machine investigation and inspection. In: Workshop on Detection & Classification of Acoustic Scenes and Events (2019)","DOI":"10.33682\/m76f-d618"},{"key":"2_CR37","unstructured":"PyTorch Mobile. url: https:\/\/pytorch.org\/mobile\/home\/"},{"key":"2_CR38","unstructured":"Roesch, J., et al.: Relay: a high-level compiler for deep learning. arXiv preprint arXiv:1904.08368 (2019)"},{"key":"2_CR39","unstructured":"M. Sponner, B. Waschneck, and A. Kumar. Compiler toolchains for deep learning workloads on embedded platforms. arXiv preprint arXiv:2104.04576, 2021"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2_CR41","unstructured":"Tan, M.,  Le, Q.V.:  EfficientNet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946arXiv: 1905.11946, 2019"},{"key":"2_CR42","unstructured":"Tensor comprehensions. url: https:\/\/github.com\/facebookresearch\/TensorComprehensions"},{"key":"2_CR43","unstructured":"TensorFlow. url: https:\/\/www.tensorflow.org"},{"key":"2_CR44","unstructured":"TensorRT constant folding example. url: https:\/\/www.ccoderun.ca\/programming\/doxygen\/tensorrt\/md_TensorRT_tools_onnx-graphsurgeon_examples_05_folding_constants_README.html"},{"key":"2_CR45","unstructured":"TinyIREE. url: https:\/\/openxla.github.io\/iree\/"},{"key":"2_CR46","unstructured":"TinyML Benchmarks. url: https:\/\/github.com\/mlcommons\/tiny"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Grosser, T., Gr\u00f6\u00dflinger, A., Lengauer, C.: Polly - performing polyhedral optimizations on a low-level intermediate representation. Parallel Processing Letters (2012)","DOI":"10.1142\/S0129626412500107"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Tollenaere, N., et al.: Autotuning convolutions is easier than you think. ACM Trans. Archit. Code Optimizations 20, 1\u201324 (2023)","DOI":"10.1145\/3570641"},{"key":"2_CR49","unstructured":"The CIFAR-10 dataset. url: http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Wade, A.W., Kulkarni, P.A., Jantz, M.R.: AOT vs. JIT: Impact of profile data on code quality, In: Proceedings of the 18th ACM SIGPLAN\/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems (2017)","DOI":"10.1145\/3078633.3081037"},{"key":"2_CR51","unstructured":"Warden, P.: Speech commands: a dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209, 2018"},{"key":"2_CR52","unstructured":"Xia, X., et al.: TRT-ViT: TensorRT-oriented vision transformer. arXiv preprint arXiv: 2205.09579 (2022)"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Yi, X., et al.: Optimizing DNN compilation for distributed training with joint OP and tensor fusion. arXiv preprint arXiv:2209.12769 (2022)","DOI":"10.1109\/TPDS.2022.3201531"},{"key":"2_CR54","unstructured":"L. Zheng, et al.: Ansor: generating high-performance tensor programs for deep learning. In: 14th USENIX symposium on operating systems design and implementation (OSDI 20) (2020)"}],"container-title":["Lecture Notes in Computer Science","Architecture of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42785-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T12:03:56Z","timestamp":1692965036000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42785-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031427848","9783031427855"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42785-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Architecture of Computing Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arcs2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/arcs-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"29","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}