{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:40:59Z","timestamp":1762522859189,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"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":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s42514-023-00167-7","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T14:01:53Z","timestamp":1695218513000},"page":"32-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ConvDarts: a fast and exact convolutional algorithm selector for deep learning frameworks"],"prefix":"10.1007","volume":"6","author":[{"given":"Lu","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3250-0435","authenticated-orcid":false,"given":"Weixing","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilai","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanyi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"167_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"167_CR2","unstructured":"Chen, T., Moreau, T., Jiang, Z., Zheng, L., Yan, E., Cowan, M., Shen, H., Wang, L., Hu, Y., Ceze, L., Guestrin, C., Krishnamurthy, A.: Tvm: An automated end-to-end optimizing compiler for deep learning. In: Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation. OSDI\u201918, pp. 579\u2013594. USENIX Association, USA (2018)"},{"key":"167_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Peng, H., Fu, J., Ling, H.: Autoformer: Searching transformers for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12270\u201312280 (2021)","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"167_CR4","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E.: cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)"},{"key":"167_CR5","unstructured":"Collobert, R., Bengio, S., Mari\u00e9thoz, J.: Torch: a modular machine learning software library. Technical report, Idiap (2002)"},{"key":"167_CR6","unstructured":"Dukhan, M.: The indirect convolution algorithm. arXiv preprint arXiv:1907.02129 (2019)"},{"key":"167_CR7","unstructured":"Erickson, N., Mueller, J., Shirkov, A., Zhang, H., Larroy, P., Li, M., Smola, A.: Autogluon-tabular: Robust and accurate automl for structured data. arXiv preprint arXiv:2003.06505 (2020)"},{"key":"167_CR8","unstructured":"Goldsborough, P.: A tour of tensorflow. arXiv preprint arXiv:1610.01178 (2016)"},{"key":"167_CR9","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic Neural Networks: A Survey. arXiv (2021)"},{"key":"167_CR10","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: A survey. arXiv preprint arXiv:2102.04906 (2021)"},{"key":"167_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"167_CR12","doi-asserted-by":"crossref","unstructured":"Jia, Z., Padon, O., Thomas, J., Warszawski, T., Zaharia, M., Aiken, A.: Taso: optimizing deep learning computation with automatic generation of graph substitutions, pp. 47\u201362 (2019)","DOI":"10.1145\/3341301.3359630"},{"key":"167_CR13","unstructured":"Jia, Y.: Learning semantic image representations at a large scale. PhD thesis. University of California, Berkeley (2014)"},{"key":"167_CR14","doi-asserted-by":"crossref","unstructured":"Jord\u00e0, M., Valero-Lara, P., Pe\u00f1a, A.J.: cuconv: A cuda implementation of convolution for cnn inference. arXiv preprint arXiv:2103.16234 (2021)","DOI":"10.1007\/s10586-021-03494-y"},{"key":"167_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., Pena, A.J.: Performance evaluation of cudnn convolution algorithms on nvidia volta gpus. IEEE Access 7, 70461\u201370473 (2019)","journal-title":"IEEE Access"},{"key":"167_CR16","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":"167_CR17","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y.: Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30 (2017)"},{"key":"167_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)"},{"key":"167_CR19","doi-asserted-by":"crossref","unstructured":"Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134021 (2016)","DOI":"10.1109\/CVPR.2016.435"},{"key":"167_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, G., Huang, H.H., Wang, Z., Zheng, W.: Performance analysis of gpu-based convolutional neural networks. In: 2016 45th International Conference on Parallel Processing (ICPP), pp. 67\u201376 (2016)","DOI":"10.1109\/ICPP.2016.15"},{"issue":"1","key":"167_CR21","first-page":"105","volume":"1","author":"Y Ma","year":"2019","unstructured":"Ma, Y., Yu, D., Wu, T., Wang, H.: Paddlepaddle: An open-source deep learning platform from industrial practice. Front. Data Domput. 1(1), 105\u2013115 (2019)","journal-title":"Front. Data Domput."},{"key":"167_CR22","unstructured":"Mathieu, M., Henaff, M., LeCun, Y.: Fast training of convolutional networks through ffts. arXiv preprint arXiv:1312.5851 (2013)"},{"issue":"3","key":"167_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439726","volume":"54","author":"S Minaee","year":"2021","unstructured":"Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., Gao, J.: Deep learning-based text classification: A comprehensive review. ACM Computing Surveys (CSUR) 54(3), 1\u201340 (2021)","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"167_CR24","unstructured":"NVML API Reference Guide (2022). https:\/\/docs.nvidia.com\/deploy\/nvml-api\/index.html"},{"key":"167_CR25","doi-asserted-by":"crossref","unstructured":"Oyama, Y., Ben-Nun, T., Hoefler, T., Matsuoka, S.: $$\\mu$$-cudnn: Accelerating deep learning frameworks with micro-batching. arXiv preprint arXiv:1804.04806 (2018)","DOI":"10.1109\/CLUSTER.2018.00058"},{"key":"167_CR26","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in pytorch (2017)"},{"key":"167_CR27","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)"},{"key":"167_CR28","doi-asserted-by":"crossref","unstructured":"Pourghassemi, B., Zhang, C., Lee, J.H., Chandramowlishwaran, A.: Brief announcement: On the limits of parallelizing convolutional neural networks on gpus. CoRR (2020)","DOI":"10.1145\/3350755.3400266"},{"key":"167_CR31","unstructured":"PyTorch: What does torch.backends.cudnn.benchmark do? (2017). https:\/\/discuss.pytorch.org\/t\/what-does-torch-backends-cudnn-benchmark-do\/5936. Accessed 22 Nov 2021"},{"key":"167_CR29","unstructured":"PyTorch: Cudnn.benchmark Slowing Execution Down (2018). https:\/\/discuss.pytorch.org\/t\/cudnn-benchmark-slowing-execution-down\/31762"},{"key":"167_CR30","unstructured":"PyTorch: Set Torch.backends.cudnn.benchmark = True Consumes Huge Amount of Memory (2021). https:\/\/discuss.pytorch.org\/t\/set-torch-backends-cudnn-benchmark-true-consumes-huge-amount-of-memory\/131010"},{"key":"167_CR32","doi-asserted-by":"crossref","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. PLDI \u201913, pp. 519\u2013530. Association for Computing Machinery, New York, NY, USA (2013)","DOI":"10.1145\/2491956.2462176"},{"key":"167_CR33","doi-asserted-by":"crossref","unstructured":"Sun, F., Liu, J., Wu, J., Pei, C., Lin, X., Ou, W., Jiang, P.: Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1441\u20131450 (2019)","DOI":"10.1145\/3357384.3357895"},{"key":"167_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"167_CR35","unstructured":"Wang, H., Zhai, J., Gao, M., Ma, Z., Tang, S., Zheng, L., Li, Y., Rong, K., Chen, Y., Jia, Z.: Pet: Optimizing tensor programs with partially equivalent transformations and automated corrections. In: 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21), pp. 37\u201354 (2021)"},{"key":"167_CR36","doi-asserted-by":"crossref","unstructured":"Xu, R., Ma, S., Guo, Y.: Performance analysis of different convolution algorithms in gpu environment. In: 2018 IEEE International Conference on Networking, Architecture and Storage (NAS), pp. 1\u201310 (2018). IEEE","DOI":"10.1109\/NAS.2018.8515695"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00167-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-023-00167-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00167-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T09:08:50Z","timestamp":1715245730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-023-00167-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["167"],"URL":"https:\/\/doi.org\/10.1007\/s42514-023-00167-7","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"7 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest Statement"}}]}}