{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:21:13Z","timestamp":1772205673223,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031396977","type":"print"},{"value":"9783031396984","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-39698-4_40","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:02:40Z","timestamp":1692770560000},"page":"592-607","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Im2win: An Efficient Convolution Paradigm on\u00a0GPU"],"prefix":"10.1007","author":[{"given":"Shuai","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luanzheng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3980-9803","authenticated-orcid":false,"given":"Xu T.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"40_CR1","unstructured":"cuBLAS library (2023). https:\/\/docs.nvidia.com\/cuda\/cublas\/"},{"key":"40_CR2","unstructured":"PyTorch (2023). https:\/\/github.com\/pytorch\/pytorch"},{"key":"40_CR3","unstructured":"Abadi, M., Barham, P., Chen, J., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI 2016, pp. 265\u2013283. USENIX Association, USA (2016)"},{"key":"40_CR4","unstructured":"Chellapilla, K., Puri, S., Simard, P.: High performance convolutional neural networks for document processing. In: 10th International Workshop on Frontiers in Handwriting Recognition (2006)"},{"key":"40_CR5","unstructured":"Chetlur, S., et al.: cuDNN: efficient primitives for deep learning. CoRR abs\/1410.0759 (2014)"},{"key":"40_CR6","unstructured":"Cho, M., Brand, D.: MEC: memory-efficient convolution for deep neural network. In: International Conference on Machine Learning (ICML), pp. 815\u2013824. PMLR (2017)"},{"key":"40_CR7","unstructured":"Crowley, E.J., Gray, G., Storkey, A.J.: Moonshine: distilling with cheap convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"40_CR8","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/j.procs.2017.05.138","volume":"108","author":"J Dongarra","year":"2017","unstructured":"Dongarra, J., Hammarling, S., Higham, N.J., Relton, S.D., Valero-Lara, P., Zounon, M.: The design and performance of batched BLAS on modern high-performance computing systems. Procedia Comput. Sci. 108, 495\u2013504 (2017)","journal-title":"Procedia Comput. Sci."},{"key":"40_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/3-540-45545-0_15","volume-title":"Computational Science \u2014 ICCS 2001","author":"JA Gunnels","year":"2001","unstructured":"Gunnels, J.A., Henry, G.M., van de Geijn, R.A.: A family of high-performance matrix multiplication algorithms. In: Alexandrov, V.N., Dongarra, J.J., Juliano, B.A., Renner, R.S., Tan, C.J.K. (eds.) ICCS 2001. LNCS, vol. 2073, pp. 51\u201360. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-45545-0_15"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR11","unstructured":"Huang, J., Yu, C.D., van de Geijn, R.A.: Implementing Strassen\u2019s algorithm with CUTLASS on NVIDIA volta GPUs. CoRR abs\/1808.07984 (2018)"},{"key":"40_CR12","doi-asserted-by":"publisher","first-page":"70461","DOI":"10.1109\/ACCESS.2019.2918851","volume":"7","author":"M Jord\u00e0","year":"2019","unstructured":"Jord\u00e0, M., Valero-Lara, P., Pe\u00f1a, A.J.: Performance evaluation of cuDNN convolution algorithms on NVIDIA Volta GPUs. IEEE Access 7, 70461\u201370473 (2019)","journal-title":"IEEE Access"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4013\u20134021 (2016)","DOI":"10.1109\/CVPR.2016.435"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Lu, S., Chu, J., Liu, X.T.: Im2win: memory efficient convolution on SIMD architectures. In: 2022 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20137 (2022)","DOI":"10.1109\/HPEC55821.2022.9926408"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Oyama, Y., Ben-Nun, T., Hoefler, T., Matsuoka, S.: Accelerating deep learning frameworks with micro-batches. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 402\u2013412 (2018)","DOI":"10.1109\/CLUSTER.2018.00058"},{"key":"40_CR17","unstructured":"Paszke, A., Gross, S., Massa, F., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), pp. 8024\u20138035 (2019)"},{"key":"40_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2015)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Song, Z., et al.: GPNPU: enabling efficient hardware-based direct convolution with multi-precision support in GPU tensor cores. In: 2020 57th ACM\/IEEE Design Automation Conference (DAC), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/DAC18072.2020.9218566"},{"issue":"12","key":"40_CR20","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., Chen, Y.H., Yang, T.J., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295\u20132329 (2017)","journal-title":"Proc. IEEE"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Wolfe, M.: Iteration space tiling for memory hierarchies. In: Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing, pp. 357\u2013361. SIAM, USA (1989)","DOI":"10.1145\/76263.76337"},{"key":"40_CR22","unstructured":"Zhang, J., Franchetti, F., Low, T.M.: High performance zero-memory overhead direct convolutions. In: International Conference on Machine Learning, pp. 5776\u20135785. PMLR (2018)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2023: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39698-4_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:07:46Z","timestamp":1692770866000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39698-4_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031396977","9783031396984"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39698-4_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 August 2023","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":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.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":"164","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":"49","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":"30% - 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":"3.98","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":"4","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)"}}]}}