{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:01:13Z","timestamp":1774893673509,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584109","type":"print"},{"value":"9789819584116","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\/978-981-95-8411-6_19","type":"book-chapter","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:09:09Z","timestamp":1774890549000},"page":"246-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Heterogeneous PUs Scheduling for\u00a0Layer-Wise DNN Acceleration"],"prefix":"10.1007","author":[{"given":"Youmei","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanjiang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"issue":"10","key":"19_CR1","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.3390\/e24101346","volume":"24","author":"J An","year":"2022","unstructured":"An, J., Zhang, D., Xu, K., Wang, D.: An opencl-based fpga accelerator for faster r-cnn. Entropy 24(10), 1346 (2022)","journal-title":"Entropy"},{"issue":"1","key":"19_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"19_CR3","unstructured":"Busetti, F.: Simulated annealing overview. World Wide Web, 4 (2003).https:\/\/www.geocities.com\/francorbusetti\/saweb.pdf"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Rhu, M.: Prema: a predictive multi-task scheduling algorithm for preemptible neural processing units. In: 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 220\u2013233. IEEE (2020)","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"19_CR5","unstructured":"Collobert, R., Farabet, C., Kavukcuo\u011flu, K.: Torch| scientific computing for luajit. In: NIPS Workshop on Machine Learning Open Source Software (2008)"},{"issue":"6","key":"19_CR6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng, L.: The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29(6), 141\u2013142 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"19_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2023.100280","volume":"17","author":"J Elcock","year":"2023","unstructured":"Elcock, J., Edward, N.: An efficient aco-based algorithm for task scheduling in heterogeneous multiprocessing environments. Array 17, 100280 (2023)","journal-title":"Array"},{"key":"19_CR8","doi-asserted-by":"publisher","first-page":"54773","DOI":"10.1109\/ACCESS.2023.3281839","volume":"11","author":"X Gao","year":"2023","unstructured":"Gao, X.: Tas: a temperature-aware scheduling for heterogeneous computing. IEEE Access 11, 54773\u201354781 (2023)","journal-title":"IEEE Access"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Jia, F., et al.: Codl: efficient cpu-gpu co-execution for deep learning inference on mobile devices. In: MobiSys, vol.\u00a022, pp. 209\u2013221 (2022)","DOI":"10.1145\/3498361.3538932"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on Multimedia, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"19_CR11","doi-asserted-by":"publisher","first-page":"43980","DOI":"10.1109\/ACCESS.2020.2977496","volume":"8","author":"D Kang","year":"2020","unstructured":"Kang, D., Oh, J., Choi, J., Yi, Y., Ha, S.: Scheduling of deep learning applications onto heterogeneous processors in an embedded device. IEEE Access 8, 43980\u201343991 (2020)","journal-title":"IEEE Access"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Kang, W., Lee, K., Lee, J., Shin, I., Chwa, H.S.: Lalarand: flexible layer-by-layer cpu\/gpu scheduling for real-time dnn tasks. In: 2021 IEEE Real-Time Systems Symposium (RTSS), pp. 329\u2013341. IEEE (2021)","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"19_CR13","doi-asserted-by":"publisher","first-page":"8091","DOI":"10.1007\/s11042-020-10139-6","volume":"80","author":"S Katoch","year":"2021","unstructured":"Katoch, S., Chauhan, S.S., Kumar, V.: A review on genetic algorithm: past, present, and future. Multimedia Tools Appli. 80, 8091\u20138126 (2021)","journal-title":"Multimedia Tools Appli."},{"issue":"2","key":"19_CR14","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1109\/LRA.2021.3057845","volume":"6","author":"B Plancher","year":"2021","unstructured":"Plancher, B., Neuman, S.M., Bourgeat, T., Kuindersma, S., Devadas, S., Reddi, V.J.: Accelerating robot dynamics gradients on a CPU, GPU, and FPGA. IEEE Robot. Autom. Lett. 6(2), 2335\u20132342 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Taufique, Z., Vyas, A., Miele, A., Liljeberg, P., Kanduri, A.: Hidp: hierarchical dnn partitioning for distributed inference on heterogeneous edge platforms. In: 2025 Design, Automation & Test in Europe Conference (DATE), pp.\u00a01\u20137. IEEE (2025)","DOI":"10.23919\/DATE64628.2025.10992692"},{"key":"19_CR16","unstructured":"TensorFlow Developers: Tensorflow guide: GPU support and manual device placement (2023). https:\/\/www.tensorflow.org\/guide\/gpu\/#manual_device_placement"},{"key":"19_CR17","unstructured":"TensorFlow Team: Tensorflow: An end-to-end open source platform for machine learning (2023). https:\/\/tensorflow.google.cn\/"},{"key":"19_CR18","unstructured":"Wang, Y.E., Wei, G.Y., Brooks, D.: Benchmarking tpu, gpu, and cpu platforms for deep learning. arXiv preprint arXiv:1907.10701 (2019)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Kim, H.: Pipelined data-parallel cpu\/gpu scheduling for multi-dnn real-time inference. In: 2019 IEEE Real-Time Systems Symposium (RTSS), pp. 392\u2013405. IEEE (2019)","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"19_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, C., Yu, H., Zhou, Y., Jiang, H.: High-performance and energy-efficient fpga-gpu-cpu heterogeneous system implementation. In: Arabnia, H.R., et al. (eds.) Advances in Parallel & Distributed Processing, and Applications. Transactions on Computational Science and Computational Intelligence. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69984-0_35","DOI":"10.1007\/978-3-030-69984-0_35"},{"key":"19_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126661","volume":"555","author":"J Zhang","year":"2023","unstructured":"Zhang, J., et al.: Pipepar: enabling fast dnn pipeline parallel training in heterogeneous gpu clusters. Neurocomputing 555, 126661 (2023)","journal-title":"Neurocomputing"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8411-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:09:10Z","timestamp":1774890550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8411-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584109","9789819584116"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8411-6_19","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":"31 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}