{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:42:50Z","timestamp":1768030970737,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T00:00:00Z","timestamp":1642723200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T00:00:00Z","timestamp":1642723200000},"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":["Cluster Comput"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10586-021-03494-y","type":"journal-article","created":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T00:04:20Z","timestamp":1642723460000},"page":"1459-1473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["cuConv: CUDA implementation of convolution for CNN inference"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1458-7706","authenticated-orcid":false,"given":"Marc","family":"Jord\u00e0","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Valero-Lara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio J.","family":"Pe\u00f1a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,21]]},"reference":[{"key":"3494_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I.J., Harp, A., Irving, G., Isard, M., Jia, Y., J\u00f3zefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D.G., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.A., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F.B., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: Large-scale machine learning on heterogeneous distributed systems. CoRR arXiv:1603.04467 (2016)"},{"key":"3494_CR2","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E.: cuDNN: efficient primitives for deep learning. CoRR (2014)"},{"key":"3494_CR3","unstructured":"D455, I.R.D.C.: https:\/\/www.intelrealsense.com\/depth-camera-d455 (2021)"},{"key":"3494_CR4","doi-asserted-by":"crossref","unstructured":"Dongarra, J.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. In: International conference on computational science (ICCS), pp. 495\u2013504 (2017)","DOI":"10.1016\/j.procs.2017.05.138"},{"key":"3494_CR5","doi-asserted-by":"publisher","unstructured":"Dryden, N., Maruyama, N., Moon, T., Benson, T., Snir, M., Van Essen, B.: Channel and filter parallelism for large-scale CNN training. In: Proceedings of the international conference for high performance computing, networking, storage and analysis, SC 2019. Association for computing machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3295500.3356207","DOI":"10.1145\/3295500.3356207"},{"key":"3494_CR6","unstructured":"Fedorov, I., Adams, R.P., Mattina, M., Whatmough, P.: Sparse: Sparse architecture search for cnns on resource-constrained microcontrollers. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/044a23cadb567653eb51d4eb40acaa88-Paper.pdf"},{"key":"3494_CR7","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/BF00342633","volume":"20","author":"K Fukushima","year":"1975","unstructured":"Fukushima, K.: Cognitron: a self-organizing multilayer neural network. Biol. Cybernet. 20, 121\u2013136 (1975)","journal-title":"Biol. Cybernet."},{"key":"3494_CR8","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1109\/TSMC.1983.6313076","volume":"SMC\u201313","author":"K Fukushima","year":"1983","unstructured":"Fukushima, K., Miyake, S., Ito, T.: Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Trans. Syst. Man Cybernet. SMC\u201313, 826\u2013834 (1983)","journal-title":"IEEE Trans. Syst. Man Cybernet."},{"key":"3494_CR9","doi-asserted-by":"crossref","unstructured":"Geng, T., Wang, T., Wu, C., Yang, C., Song, S., Li, A., Herbordt, M.: LP-BNN: Ultra-low-latency BNN inference with layer parallelism. IEEE 30th international conference on application-specific systems, architectures and processors (ASAP) 2160\u2013052X, 9\u201316 (2019)","DOI":"10.1109\/ASAP.2019.00-43"},{"key":"3494_CR10","unstructured":"Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G.: Recent advances in convolutional neural networks. CoRR arXiv:1512.07108 (2015)"},{"key":"3494_CR11","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. CoRR arXiv:1506.02626 (2015)"},{"key":"3494_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3494_CR13","unstructured":"Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<1\\text{MB}$$ model size. CoRR arXiv:1602.07360 (2016)"},{"key":"3494_CR14","unstructured":"IntelAI: https:\/\/github.com\/IntelAI\/models (2021)"},{"key":"3494_CR15","doi-asserted-by":"publisher","first-page":"70461","DOI":"10.1109\/ACCESS.2019.2918851","volume":"7","author":"M Jorda","year":"2019","unstructured":"Jorda, 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":"3494_CR16","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3494_CR17","doi-asserted-by":"crossref","unstructured":"Lavin, A.: Fast algorithms for convolutional neural networks. CoRR arXiv:1509.09308 (2015)","DOI":"10.1109\/CVPR.2016.435"},{"issue":"11","key":"3494_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"3494_CR19","doi-asserted-by":"crossref","unstructured":"Li, C., Yang, Y., Feng, M., Chakradhar, S., Zhou, H.: Optimizing memory efficiency for deep convolutional neural networks on GPUs. In: Proceedings of the international conference for high performance computing, networking, storage and analysis (SC16), pp. 633\u2013644 (2016)","DOI":"10.1109\/SC.2016.53"},{"key":"3494_CR20","unstructured":"Liu, X., Pool, J., Han, S., Dally, W.J.: Efficient sparse-winograd convolutional neural networks. CoRR arXiv:1802.06367 (2018)"},{"key":"3494_CR21","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through FFTs. CoRR arXiv:1312.5851 (2013)"},{"key":"3494_CR22","doi-asserted-by":"publisher","unstructured":"Mogers, N., Radu, V., Li, L., Turner, J., OBoyle, M., Dubach, C.: Automatic generation of specialized direct convolutions for mobile GPUs. In: Proceedings of the 13th Annual workshop on general purpose processing using graphics processing unit, GPGPU 20, pp. 41\u201350. Association for computing machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3366428.3380771","DOI":"10.1145\/3366428.3380771"},{"key":"3494_CR23","unstructured":"NVIDIA: https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html (2021)"},{"key":"3494_CR24","unstructured":"Park, J., Li, S.R., Wen, W., Tang, P.T.P., Li, H., Chen, Y., Dubey, P.: Faster CNNs with direct sparse convolutions and guided pruning. In: 5th International conference on learning representations, ICLR 2017, Toulon, France, April 24-26, 2017, conference track proceedings (2017). https:\/\/openreview.net\/forum?id=rJPcZ3txx"},{"key":"3494_CR25","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. CoRR arXiv:1710.05941 (2017)"},{"issue":"3","key":"3494_CR26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"3494_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR arXiv:1409.1556 (2014)"},{"key":"3494_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, AAAI17, pp. 4278\u20134284. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"3494_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. CoRR arXiv:1409.4842 (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3494_CR30","unstructured":"Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S., LeCun, Y.: Fast convolutional nets with fbfft: a GPU performance evaluation. CoRR arXiv:1412.7580 (2014)"},{"key":"3494_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-019-01562-w","volume":"51","author":"N Wen","year":"2021","unstructured":"Wen, N., Guo, R., He, B., Fan, Y., Ma, D.: Block-sparse cnn: towards a fast and memory-efficient framework for convolutional neural networks. Appl. Intell. 51, 1\u201312 (2021)","journal-title":"Appl. Intell."},{"key":"3494_CR32","unstructured":"Winograd, S.: Arithmetic complexity of computations. CBMS-NSF regional conference series in applied mathematics. Society for industrial and Applied Mathematics (1980). https:\/\/books.google.es\/books?id=GU1NQJBcWIsC"},{"key":"3494_CR33","doi-asserted-by":"publisher","unstructured":"Yan, D., Wang, W., Chu, X.: Optimizing batched winograd convolution on GPUs. In: Proceedings of the 25th ACM SIGPLAN symposium on principles and practice of parallel programming, PPoPP 20, pp. 32\u201344. Association for computing machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3332466.3374520","DOI":"10.1145\/3332466.3374520"},{"key":"3494_CR34","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1109\/ACCESS.2020.3047144","volume":"9","author":"W You","year":"2021","unstructured":"You, W., Wu, C.: RSNN: a software\/hardware co-optimized framework for sparse convolutional neural networks on FPGAs. IEEE Access 9, 949\u2013960 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2020.3047144","journal-title":"IEEE Access"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03494-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-021-03494-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03494-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T23:05:26Z","timestamp":1674515126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-021-03494-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,21]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["3494"],"URL":"https:\/\/doi.org\/10.1007\/s10586-021-03494-y","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,21]]},"assertion":[{"value":"13 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The datasets generated during and\/or analysed during the current study are available from the corresponding author on reasonable request.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}