{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:45:53Z","timestamp":1765827953080,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030576745"},{"type":"electronic","value":"9783030576752"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-57675-2_14","type":"book-chapter","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T23:12:33Z","timestamp":1597705953000},"page":"219-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs"],"prefix":"10.1007","author":[{"given":"Xueying","family":"Wang","sequence":"first","affiliation":[]},{"given":"Guangli","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Jiansong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiaobing","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Alwani, M., Chen, H., Ferdman, M., Milder, P.: Fused-layer CNN accelerators. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, October 2016. https:\/\/doi.org\/10.1109\/micro.2016.7783725","key":"14_CR1","DOI":"10.1109\/micro.2016.7783725"},{"unstructured":"Chen, T., et al.: Tvm: an automated end-to-end optimizing compiler for deep learning. In: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, pp. 579\u2013594. USENIX Association (2018)","key":"14_CR2"},{"key":"14_CR3","volume-title":"Professional Cuda C Programming","author":"J Cheng","year":"2014","unstructured":"Cheng, J., Grossman, M., McKercher, T.: Professional Cuda C Programming. Wiley, Hoboken (2014)"},{"unstructured":"Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)","key":"14_CR4"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.parco.2017.11.003","volume":"71","author":"M Fang","year":"2018","unstructured":"Fang, M., Fang, J., Zhang, W., Zhou, H., Liao, J., Wang, Y.: Benchmarking the gpu memory at the warp level. Parallel Comput. 71, 23\u201341 (2018). https:\/\/doi.org\/10.1016\/j.parco.2017.11.003","journal-title":"Parallel Comput."},{"issue":"10","key":"14_CR6","doi-asserted-by":"publisher","first-page":"3934","DOI":"10.1007\/s11227-015-1483-z","volume":"71","author":"J Filipovi\u010d","year":"2015","unstructured":"Filipovi\u010d, J., Madzin, M., Fousek, J., Matyska, L.: Optimizing CUDA code by kernel fusion: application on BLAS. J. Supercomputing 71(10), 3934\u20133957 (2015). https:\/\/doi.org\/10.1007\/s11227-015-1483-z","journal-title":"J. Supercomputing"},{"doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, June 2016. https:\/\/doi.org\/10.1109\/cvpr.2016.90","key":"14_CR7","DOI":"10.1109\/cvpr.2016.90"},{"unstructured":"Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)","key":"14_CR8"},{"unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and$$<$$ 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)","key":"14_CR9"},{"doi-asserted-by":"publisher","unstructured":"Li, C., Yang, Y., Feng, M., Chakradhar, S., Zhou, H.: Optimizing memory efficiency for deep convolutional neural networks on GPUs. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, November 2016. https:\/\/doi.org\/10.1109\/sc.2016.53","key":"14_CR10","DOI":"10.1109\/sc.2016.53"},{"unstructured":"Liu, H., Simonyan, K., Vinyals, O., Fernando, C., Kavukcuoglu, K.: Hierarchical representations for efficient architecture search. arXiv preprint arXiv:1711.00436 (2017)","key":"14_CR11"},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-29400-7_16","volume-title":"Euro-Par 2019: Parallel Processing","author":"A Mazaheri","year":"2019","unstructured":"Mazaheri, A., Schulte, J., Moskewicz, M.W., Wolf, F., Jannesari, A.: Enhancing the programmability and performance portability of GPU tensor operations. In: Yahyapour, R. (ed.) Euro-Par 2019. LNCS, vol. 11725, pp. 213\u2013226. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-29400-7_16"},{"unstructured":"Nvidia CUDA: Compute unified device architecture programming guide (2007)","key":"14_CR13"},{"doi-asserted-by":"publisher","unstructured":"Qiao, B., Reiche, O., Hannig, F., Teich, J.: From loop fusion to kernel fusion: a domain-specific approach to locality optimization. In: 2019 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, February 2019. https:\/\/doi.org\/10.1109\/cgo.2019.8661176","key":"14_CR14","DOI":"10.1109\/cgo.2019.8661176"},{"issue":"6","key":"14_CR15","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/2499370.2462176","volume":"48","author":"J Ragan-Kelley","year":"2013","unstructured":"Ragan-Kelley, J., Barnes, C., Adams, A., Paris, S., Durand, F., Amarasinghe, S.: Halide. ACM SIGPLAN Not. 48(6), 519\u2013530 (2013). https:\/\/doi.org\/10.1145\/2499370.2462176","journal-title":"ACM SIGPLAN Not."},{"doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, June 2015. https:\/\/doi.org\/10.1109\/cvpr.2015.7298594","key":"14_CR16","DOI":"10.1109\/cvpr.2015.7298594"},{"doi-asserted-by":"publisher","unstructured":"Wahib, M., Maruyama, N.: Scalable kernel fusion for memory-bound GPU applications. In: SC14: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, November 2014. https:\/\/doi.org\/10.1109\/sc.2014.21","key":"14_CR17","DOI":"10.1109\/sc.2014.21"},{"doi-asserted-by":"publisher","unstructured":"Wang, X.: Artifact and instructions to generate experimental results for conference proceeding 2020 paper: accelerating deep learning inference with cross-layer data reuse on GPUs, July 2020. https:\/\/doi.org\/10.6084\/m9.figshare.12571928. https:\/\/springernature.figshare.com\/articles\/software\/Artifact_and_instructions_to_generate_experimental_results_for_conference_proceeding_2020_paper_Accelerating_Deep_Learning_Inference_with_Cross-Layer_Data_Reuse_on_GPUs\/12571928\/1","key":"14_CR18","DOI":"10.6084\/m9.figshare.12571928"},{"doi-asserted-by":"publisher","unstructured":"Wu, H., Diamos, G., Wang, J., Cadambi, S., Yalamanchili, S., Chakradhar, S.: Optimizing data warehousing applications for GPUs using kernel fusion\/fission. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum. IEEE, May 2012. https:\/\/doi.org\/10.1109\/ipdpsw.2012.300","key":"14_CR19","DOI":"10.1109\/ipdpsw.2012.300"},{"doi-asserted-by":"publisher","unstructured":"Zhou, X., Giacalone, J.P., Garzar\u00e1n, M.J., Kuhn, R.H., Ni, Y., Padua, D.: Hierarchical overlapped tiling. In: Proceedings of the Tenth International Symposium on Code Generation and Optimization. ACM Press (2012). https:\/\/doi.org\/10.1145\/2259016.2259044","key":"14_CR20","DOI":"10.1145\/2259016.2259044"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2020: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-57675-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:03:21Z","timestamp":1723939401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-57675-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030576745","9783030576752"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-57675-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 August 2020","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":"Warsaw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2020.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"158","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":"39","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":"25% - 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":"4","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":"2.5","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)"}},{"value":"The conference was held virtually due to the coronavirus pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}