{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T07:21:16Z","timestamp":1770967276942,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032163448","type":"print"},{"value":"9783032163455","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-16345-5_4","type":"book-chapter","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:36:10Z","timestamp":1770964570000},"page":"41-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Mobile Inference Through Fine-Grained CPU-GPU Co-Execution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-0231","authenticated-orcid":false,"given":"Zhuojin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5110-203X","authenticated-orcid":false,"given":"Marco","family":"Paolieri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8353-5040","authenticated-orcid":false,"given":"Leana","family":"Golubchik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Akiba et al.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of KDD, pp. 2623\u20132631 (2019)","DOI":"10.1145\/3292500.3330701"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Chen et al.: HeteroLLM: accelerating large language model inference on mobile SoCs platform with heterogeneous AI accelerators. arXiv:2501.14794 (2025)","DOI":"10.20944\/preprints202501.0901.v1"},{"key":"4_CR3","unstructured":"Dosovitskiy et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"4_CR4","unstructured":"Google: XNNPACK: high-efficiency floating-point neural network inference operators for mobile, server, and web. https:\/\/github.com\/google\/XNNPACK (2023)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR6","unstructured":"Intel: OpenVINO Toolkit (2025). https:\/\/github.com\/openvinotoolkit"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Jang et al.: Sparsity-aware and re-configurable NPU architecture for Samsung flagship mobile SoC. In: Proceedings of ISCA, pp. 15\u201328. IEEE (2021)","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Jayanth, R., Gupta, N., Prasanna, V.: Benchmarking edge AI platforms for high-performance ML inference. arXiv:2409.14803 (2024)","DOI":"10.1109\/HPEC62836.2024.10938499"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Jia et al.: CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices. In: Proceedings of MobiSys, vol.\u00a022, pp. 209\u2013221 (2022)","DOI":"10.1145\/3498361.3538932"},{"key":"4_CR10","unstructured":"Ke et al.: LightGBM: a highly efficient gradient boosting decision tree. Proc. NeurIPS 30 (2017)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Kim, Y., Kim, J., Chae, D., Kim, D., Kim, J.: $$\\mu $$layer: low latency on-device inference using cooperative single-layer acceleration and processor-friendly quantization. In: Proceedings of EuroSys, pp. 1\u201315 (2019)","DOI":"10.1145\/3302424.3303950"},{"key":"4_CR12","unstructured":"Lee et al.: On-device neural net inference with mobile GPUs. arXiv:1907.01989 (2019)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Paolieri, M., Golubchik, L.: Predicting inference latency of neural architectures on mobile devices. In: Proceedings of ICPE, pp. 99\u2013112. ACM (2023)","DOI":"10.1145\/3578244.3583735"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., Paolieri, M., Golubchik, L.: A benchmark for ML inference latency on mobile devices. In: Proceedings of EdgeSys, pp. 31\u201336. ACM (2024)","DOI":"10.1145\/3642968.3654818"},{"key":"4_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2024.102429","volume":"165","author":"Z Li","year":"2024","unstructured":"Li, Z., Paolieri, M., Golubchik, L.: Inference latency prediction for CNNs on heterogeneous mobile devices and ML frameworks. Perform. Eval. 165, 102429 (2024)","journal-title":"Perform. Eval."},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"4_CR17","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of CVPR, pp. 2818\u20132826. IEEE (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"4_CR19","unstructured":"Tang et al.: To bridge neural network design and real-world performance: a behaviour study for neural networks. Proc. MLSys 3, 21\u201337 (2021)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: NN-Stretch: automatic neural network branching for parallel inference on heterogeneous multi-processors. In: Proceedings of MobiSys, pp. 70\u201383 (2023)","DOI":"10.1145\/3581791.3596870"},{"key":"4_CR21","unstructured":"XiaoMi: Mace: a deep learning inference framework for mobile heterogeneous computing platforms (2025). https:\/\/github.com\/XiaoMi\/mace. Accessed 27 Aug 2025"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Zhang et al.: NN-Meter: towards accurate latency prediction of deep-learning model inference on diverse edge devices. In: Proceedings of MobiSys, pp. 81\u201393 (2021)","DOI":"10.1145\/3458864.3467882"}],"container-title":["Lecture Notes in Computer Science","Computer Performance Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-16345-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:36:15Z","timestamp":1770964575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-16345-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032163448","9783032163455"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-16345-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPEW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Workshop on Performance Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Catania","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epew2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epew-workshop.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}