{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T22:40:05Z","timestamp":1756334405656,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030856649"},{"type":"electronic","value":"9783030856656"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-85665-6_15","type":"book-chapter","created":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T03:06:52Z","timestamp":1630120012000},"page":"232-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Flexible and Compiler-Friendly Layer Fusion for CNNs on Multicore CPUs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5992-3913","authenticated-orcid":false,"given":"Zhongyi","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos","family":"Georganas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6582-8237","authenticated-orcid":false,"given":"John D.","family":"Owens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,25]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, pp. 265\u2013283. OSDI 2016, USA (2016). https:\/\/doi.org\/10.5555\/3026877.3026899","DOI":"10.5555\/3026877.3026899"},{"issue":"4","key":"15_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322967","volume":"38","author":"A Adams","year":"2019","unstructured":"Adams, A., et al.: Learning to optimize Halide with tree search and random programs. ACM Trans. Graph. 38(4), 1\u201312 (2019). https:\/\/doi.org\/10.1145\/3306346.3322967","journal-title":"ACM Trans. Graph."},{"key":"15_CR3","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), October 2016. https:\/\/doi.org\/10.1109\/micro.2016.7783725","DOI":"10.1109\/micro.2016.7783725"},{"key":"15_CR4","unstructured":"Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. CoRR arXiv:1512.01274, December 2015"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: TVM: end-to-end optimization stack for deep learning. CoRR arXiv:1802.04799, February 2018","DOI":"10.1145\/3149166.3149174"},{"key":"15_CR6","doi-asserted-by":"publisher","unstructured":"Chen, T., et al.: Learning to optimize tensor programs. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 3393\u20133404. NIPS 2018, Red Hook, NY, USA (2018). https:\/\/doi.org\/10.5555\/3327144.3327258","DOI":"10.5555\/3327144.3327258"},{"key":"15_CR7","unstructured":"Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. CoRR arXiv:1410.0759 (Oct 2014)"},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"Georganas, E., et al.: Anatomy of high-performance deep learning convolutions on SIMD architectures. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 830\u2013841, November 2018. https:\/\/doi.org\/10.1109\/sc.2018.00069","DOI":"10.1109\/sc.2018.00069"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Georganas, E., et al.: Harnessing deep learning via a single building block. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 222\u2013233 (2020). https:\/\/doi.org\/10.1109\/IPDPS47924.2020.00032","DOI":"10.1109\/IPDPS47924.2020.00032"},{"key":"15_CR10","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), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Heinecke, A., Henry, G., Hutchinson, M., Pabst, H.: LIBXSMM: accelerating small matrix multiplications by runtime code generation. In: SC16: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 981\u2013991 (2016). https:\/\/doi.org\/10.1109\/SC.2016.83","DOI":"10.1109\/SC.2016.83"},{"key":"15_CR12","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR arXiv:1704.04861, April 2017"},{"key":"15_CR13","unstructured":"Jia, Z., Thomas, J., Warszawski, T., Gao, M., Zaharia, M., Aiken, A.: Optimizing DNN computation with relaxed graph substitutions. In: Talwalkar, A., Smith, V., Zaharia, M. (eds.) Proceedings of Machine Learning and Systems, pp. 27\u201339 (2019)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Lavin, A.: Fast algorithms for convolutional neural networks. CoRR arXiv:1509.09308, September 2015","DOI":"10.1109\/CVPR.2016.435"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wang, Y., Yu, R., Li, M., Sharma, V., Wang, Y.: Optimizing CNN model inference on CPUs, pp. 1025\u20131040. USENIX ATC 2019, USA (2019). https:\/\/doi.org\/10.5555\/3358807.3358895","DOI":"10.5555\/3358807.3358895"},{"key":"15_CR16","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through FFTs. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, 14\u201316 April 2014, Banff, AB, Canada, Conference Track Proceedings (2014)"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Mullapudi, R.T., Adams, A., Sharlet, D., Ragan-Kelley, J., Fatahalian, K.: Automatically scheduling halide image processing pipelines 35(4), July 2016. https:\/\/doi.org\/10.1145\/2897824.2925952","DOI":"10.1145\/2897824.2925952"},{"key":"15_CR18","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035 (2019)"},{"key":"15_CR19","doi-asserted-by":"publisher","unstructured":"Ragan-Kelley, J., Adams, A., Paris, S., Levoy, M., Amarasinghe, S., Durand, F.: Decoupling algorithms from schedules for easy optimization of image processing pipelines. ACM Trans. Graph. 31(4), 32:1\u201332:12, July 2012. https:\/\/doi.org\/10.1145\/2185520.2185528","DOI":"10.1145\/2185520.2185528"},{"key":"15_CR20","doi-asserted-by":"publisher","unstructured":"Ragan-Kelley, J., Barnes, C., Adams, A., Paris, S., Durand, F., Amarasinghe, S.: Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. In: Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 519\u2013530. PLDI 2013, Jun 2013. https:\/\/doi.org\/10.1145\/2491956.2462176","DOI":"10.1145\/2491956.2462176"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"15_CR22","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. https:\/\/doi.org\/10.1109\/cvpr.2016.308","DOI":"10.1109\/cvpr.2016.308"},{"key":"15_CR23","doi-asserted-by":"publisher","unstructured":"Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2815\u20132823. Los Alamitos, CA, USA, June 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00293","DOI":"10.1109\/CVPR.2019.00293"},{"key":"15_CR24","doi-asserted-by":"publisher","unstructured":"Wang, X., Li, G., Dong, X., Li, J., Liu, L., Feng, X.: Accelerating deep learning inference with cross-layer data reuse on GPUs. In: Euro-Par 2020: Parallel Processing, pp. 219\u2013233 (2020). https:\/\/doi.org\/10.1007\/978-3-030-57675-2_14","DOI":"10.1007\/978-3-030-57675-2_14"},{"key":"15_CR25","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52, 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun. ACM"},{"key":"15_CR26","unstructured":"Zheng, L., et al.: Ansor: generating high-performance tensor programs for deep learning. In: 14th USENIX Symposium on Operating Systems Design and Implementation, pp. 863\u2013879. OSDI 2020, November 2020"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2021: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85665-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T22:02:15Z","timestamp":1756332135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85665-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030856649","9783030856656"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85665-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 August 2021","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":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2021.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":"136","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":"38","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":"28% - 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":"6","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 COVID-19 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)"}}]}}