{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T10:29:33Z","timestamp":1766399373260,"version":"3.41.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031901997","type":"print"},{"value":"9783031902000","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-90200-0_30","type":"book-chapter","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T16:42:53Z","timestamp":1749573773000},"page":"375-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["StarONNX: A\u00a0Dynamic Scheduler for\u00a0Low Latency and\u00a0High Throughput Inference on\u00a0Heterogeneous Resources"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2741-6228","authenticated-orcid":false,"given":"Olivier","family":"Beaumont","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4943-3214","authenticated-orcid":false,"given":"Jean-Fran\u00e7ois","family":"David","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2475-3309","authenticated-orcid":false,"given":"Lionel","family":"Eyraud-Dubois","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6411-809X","authenticated-orcid":false,"given":"Samuel","family":"Thibault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Jang, W., Jeong, H., Kang, K., Dutt, N., Kim, J.-C.: R-TOD: real-time object detector with minimized end-to-end delay for autonomous driving. In: 2020 IEEE Real-Time Systems Symposium (RTSS). IEEE (2020)","DOI":"10.1109\/RTSS49844.2020.00027"},{"key":"30_CR2","unstructured":"ONNX Runtime: Cross-platform, high performance scoring engine for ml models. https:\/\/onnxruntime.ai\/. Accessed 20 Mar 2024"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. In: 15th International Euro-Par Conference (2009)","DOI":"10.1007\/978-3-642-03869-3_80"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Fang, Z., Yu, T., Mengshoel, O.J., Gupta, R.K.: QoS-aware scheduling of heterogeneous servers for inference in deep neural networks. In: 2017 ACM on Conference on Information and Knowledge Management (2017)","DOI":"10.1145\/3132847.3133045"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Kang, W., Lee, K., Lee, J., Shin, I., Chwa, H.\u00a0S.: LaLaRAND: flexible layer-by-layer CPU\/GPU scheduling for real-time DNN tasks. In: 2021 IEEE Real-Time Systems Symposium (RTSS). IEEE (2021)","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Aghapour, E., Sapra, D., Pimentel, A., Pathania, A.: CPU-GPU layer-switched low latency CNN inference. In: 2022 25th Euromicro Conference on Digital System Design (DSD). IEEE (2022)","DOI":"10.1109\/DSD57027.2022.00051"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Dhakal, A., Kulkarni, S.G.,\u00a0Ramakrishnan, K.K.: GSLICE: controlled spatial sharing of GPUs for a scalable inference platform. In: ACM Symposium on Cloud Computing, pp. 492\u2013506 (2020)","DOI":"10.1145\/3419111.3421284"},{"key":"30_CR8","unstructured":"Han, M., Zhang, H., Chen, R., Chen, H.: Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022) (2022)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Wu, H.-I., Guo, D.-Y., Chin, H.-H., Tsay, R.-S.: A pipeline-based scheduler for optimizing latency of convolution neural network inference over heterogeneous multicore systems. In: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) (2020)","DOI":"10.1109\/AICAS48895.2020.9073977"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Automated runtime-aware scheduling for multi-tenant DNN inference on GPU. In: International Conference on Computer Aided Design (ICCAD) (2021)","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Kundu, T., Shu, T.: HIOS: hierarchical inter-operator scheduler for real-time inference of DAG-structured deep learning models on multiple GPUs. In: IEEE International Conference on Cluster Computing (CLUSTER) (2023)","DOI":"10.1109\/CLUSTER52292.2023.00016"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Malik, B.H., Amir, M., Mazhar, B., Ali, S., Jalil, R., Khalid, J.: Comparison of task scheduling algorithms in cloud environment. Int. J. Adv. Comput. Sci. Appl. (2018)","DOI":"10.14569\/IJACSA.2018.090550"},{"issue":"02","key":"30_CR13","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran, A., et al.: OmpSs: a proposal for programming heterogeneous multi-core architectures. Parallel Process. Lett. 21(02), 173\u2013193 (2011)","journal-title":"Parallel Process. Lett."},{"key":"30_CR14","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MCSE.2013.98","volume":"15","author":"G Bosilca","year":"2013","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., H\u00e9rault, T., Dongarra, J.J.: Exploiting heterogeneity to enhance scalability. Comput. Sci. Eng. 15, 36\u201345 (2013)","journal-title":"Comput. Sci. Eng."},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Dagli, I., Cieslewicz, A., McClurg, J., Belviranli, M.E.: AxoNN: energy-aware execution of neural network inference on multi-accelerator heterogeneous SOCs. In: 59th ACM\/IEEE Design Automation Conference (2022)","DOI":"10.1145\/3489517.3530572"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"30_CR17","unstructured":"Triton Inference Server: Open-source AI inference serving. https:\/\/developer.nvidia.com\/nvidia-triton-inference-server. Accessed 20 June 2024"},{"key":"30_CR18","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"30_CR19","unstructured":"Tan, M.,\u00a0Le, Q.V.: EfficientnetV2: smaller models and faster training. arxiv 2021. arXiv preprint arXiv:2104.00298"},{"issue":"2","key":"30_CR20","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TAFFC.2021.3122146","volume":"14","author":"F Ma","year":"2021","unstructured":"Ma, F., Sun, B., Li, S.: Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans. Affect. Comput. 14(2), 1236\u20131248 (2021)","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-90200-0_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T16:42:58Z","timestamp":1749573778000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-90200-0_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031901997","9783031902000"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-90200-0_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"11 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}