{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:42:22Z","timestamp":1740181342382,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.U19A2061"],"award-info":[{"award-number":["No.U19A2061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62272190"],"award-info":[{"award-number":["No.62272190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sichuan Major R &D Project","award":["No.22QYCX0168"],"award-info":[{"award-number":["No.22QYCX0168"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s42514-023-00156-w","type":"journal-article","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T10:02:54Z","timestamp":1685095374000},"page":"292-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FASS-pruner: customizing a fine-grained CNN accelerator-aware pruning framework via intra-filter splitting and inter-filter shuffling"],"prefix":"10.1007","volume":"5","author":[{"given":"Xiaohui","family":"Wei","sequence":"first","affiliation":[]},{"given":"Xinyang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Chenyang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guangli","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2189-8385","authenticated-orcid":false,"given":"Hengshan","family":"Yue","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,26]]},"reference":[{"key":"156_CR1","doi-asserted-by":"publisher","unstructured":"Asgari, B., Hadidi, R., Kim, H., et al.: Lodestar: creating locally-dense CNNs for efficient inference on systolic arrays. In: Proceedings of the 56th Annual Design Automation Conference 2019. Association for Computing Machinery, New York, NY, USA, DAC \u201919 (2019). https:\/\/doi.org\/10.1145\/3316781.3322472","DOI":"10.1145\/3316781.3322472"},{"key":"156_CR2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972238","author":"R Burkard","year":"2012","unstructured":"Burkard, R., Dell\u2019Amico, M., Martello, S.: Assignment problems. Soc. Ind. Appl. Math. (2012). https:\/\/doi.org\/10.1137\/1.9781611972238","journal-title":"Soc. Ind. Appl. Math."},{"key":"156_CR3","doi-asserted-by":"crossref","unstructured":"Carreira-Perpinan, M.A., Idelbayev, Y,: Learning-compression algorithms for neural net pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00890"},{"issue":"3","key":"156_CR5","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1145\/3007787.3001177","volume":"44","author":"YH Chen","year":"2016","unstructured":"Chen, Y.H., Emer, J., Sze, V.: Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH Comput. Arch. News 44(3), 367\u2013379 (2016)","journal-title":"ACM SIGARCH Comput. Arch. News"},{"key":"156_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhu, J., Jiang, J., et al.: Tight compression: compressing CNN model tightly through unstructured pruning and simulated annealing based permutation. In: 2020 57th ACM\/IEEE Design Automation Conference (DAC), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/DAC18072.2020.9218701"},{"key":"156_CR6","doi-asserted-by":"publisher","unstructured":"Chitty-Venkata, K.T., Somani, A.K.: Array aware training\/pruning: methods for efficient forward propagation on array-based neural network accelerators. In: 2020 IEEE 31st International Conference on Application-Specific Systems, Architectures and Processors (ASAP), pp. 37\u201344 (2020). https:\/\/doi.org\/10.1109\/ASAP49362.2020.00016","DOI":"10.1109\/ASAP49362.2020.00016"},{"key":"156_CR7","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. arXiv preprint arXiv:1510.00149 (2015a)"},{"key":"156_CR8","volume-title":"Advances in Neural Information Processing Systems","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., et al.: Learning both weights and connections for efficient neural network. In: Cortes, C., Lawrence, N., Lee, D., et al. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc., Red Hook (2015)"},{"key":"156_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., et al.: 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":"156_CR10","doi-asserted-by":"publisher","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398\u20131406 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.155","DOI":"10.1109\/ICCV.2017.155"},{"key":"156_CR11","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision - ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Y., Liu, Z., et al.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., et al. (eds.) Computer Vision - ECCV 2016, pp. 646\u2013661. Springer International Publishing, Cham (2016)"},{"key":"156_CR12","unstructured":"Jouppi, N.P., Young, C., Patil, N., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)"},{"issue":"6","key":"156_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"key":"156_CR14","doi-asserted-by":"crossref","unstructured":"Kung, H., McDanel, B., Zhang, S.Q.: Packing sparse convolutional neural networks for efficient systolic array implementations: column combining under joint optimization. In: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 821\u2013834 (2019)","DOI":"10.1145\/3297858.3304028"},{"issue":"7553","key":"156_CR15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"1","key":"156_CR16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/TSUSC.2021.3060690","volume":"7","author":"J Li","year":"2022","unstructured":"Li, J., Louri, A.: Adaprune: An accelerator-aware pruning technique for sustainable CNN accelerators. IEEE Trans. Sustain. Comput. 7(1), 47\u201360 (2022). https:\/\/doi.org\/10.1109\/TSUSC.2021.3060690","journal-title":"IEEE Trans. Sustain. Comput."},{"issue":"11","key":"156_CR17","doi-asserted-by":"publisher","first-page":"3614","DOI":"10.1109\/TCAD.2020.3013050","volume":"39","author":"G Li","year":"2020","unstructured":"Li, G., Ma, X., Wang, X., et al.: Fusion-catalyzed pruning for optimizing deep learning on intelligent edge devices. IEEE Trans. Comput. Aided Des. Integr. Circ. Syst. 39(11), 3614\u20133626 (2020). https:\/\/doi.org\/10.1109\/TCAD.2020.3013050","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circ. Syst."},{"issue":"102","key":"156_CR18","first-page":"431","volume":"124","author":"G Li","year":"2022","unstructured":"Li, G., Ma, X., Wang, X., et al.: Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning. J. Syst. Archit. 124(102), 431 (2022)","journal-title":"J. Syst. Archit."},{"key":"156_CR19","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.neucom.2021.07.045","volume":"461","author":"T Liang","year":"2021","unstructured":"Liang, T., Glossner, J., Wang, L., et al.: Pruning and quantization for deep neural network acceleration: a survey. Neurocomputing 461, 370\u2013403 (2021)","journal-title":"Neurocomputing"},{"key":"156_CR20","doi-asserted-by":"crossref","unstructured":"Lin, M., Ji, R., Wang, Y., et al.: Hrank: Filter pruning using high-rank feature map. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"156_CR21","doi-asserted-by":"publisher","unstructured":"Liu, Z., Li, J., Shen, Z., et al.: Learning efficient convolutional networks through network slimming. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2755\u20132763 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.298","DOI":"10.1109\/ICCV.2017.298"},{"key":"156_CR22","unstructured":"Lym, S., Erez, M.: Flexsa: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training. arXiv preprint arXiv:2004.13027 (2020)"},{"key":"156_CR23","doi-asserted-by":"crossref","unstructured":"Ma, M., Tan, J., Wei, X., et al.: Process variation mitigation on convolutional neural network accelerator architecture. In: 2019 IEEE 37th International Conference on Computer Design (ICCD), pp. 47\u201355. IEEE (2019)","DOI":"10.1109\/ICCD46524.2019.00015"},{"issue":"9","key":"156_CR24","doi-asserted-by":"publisher","first-page":"4930","DOI":"10.1109\/TNNLS.2021.3063265","volume":"33","author":"X Ma","year":"2022","unstructured":"Ma, X., Lin, S., Ye, S., et al.: Non-structured dnn weight pruning-is it beneficial in any platform? IEEE Trans. Neural Netw. Learn. Syst. 33(9), 4930\u20134944 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2021.3063265","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"156_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/978-3-662-44415-3_4","volume-title":"Structural, Syntactic, and Statistical Pattern Recognition","author":"MI Malinen","year":"2014","unstructured":"Malinen, M.I., Fr\u00e4nti, P.: Balanced k-means for clustering. In: Fr\u00e4nti, P., Brown, G., Loog, M., et al. (eds.) Structural, Syntactic, and Statistical Pattern Recognition, pp. 32\u201341. Springer, Berlin (2014)"},{"key":"156_CR26","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"156_CR27","doi-asserted-by":"publisher","unstructured":"Rhu, M., Gimelshein, N., Clemons, J., et al.: vdnn: Virtualized deep neural networks for scalable, memory-efficient neural network design. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201313 (2016). https:\/\/doi.org\/10.1109\/MICRO.2016.7783721","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"156_CR28","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., et al. (eds.) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, pp. 234\u2013241. Springer International Publishing, Cham (2015)"},{"key":"156_CR29","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M,, et al.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"156_CR30","doi-asserted-by":"crossref","unstructured":"teja Vooturi, D., Varma, G., Kothapalli, K.: Dynamic block sparse reparameterization of convolutional neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00367"},{"key":"156_CR31","doi-asserted-by":"crossref","unstructured":"Yang, T.J., Chen, Y.H., Sze, V.: Designing energy-efficient convolutional neural networks using energy-aware pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5687\u20135695 (2017)","DOI":"10.1109\/CVPR.2017.643"},{"key":"156_CR32","doi-asserted-by":"publisher","unstructured":"Yayla, M., Chen, J.J.: Memory-efficient training of binarized neural networks on the edge. In: Proceedings of the 59th ACM\/IEEE Design Automation Conference. Association for Computing Machinery, New York, NY, USA, DAC \u201922, pp. 661\u2013666 (2022). https:\/\/doi.org\/10.1145\/3489517.3530496","DOI":"10.1145\/3489517.3530496"},{"issue":"2","key":"156_CR33","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1145\/3140659.3080215","volume":"45","author":"J Yu","year":"2017","unstructured":"Yu, J., Lukefahr, A., Palframan, D., et al.: Scalpel: Customizing DNN pruning to the underlying hardware parallelism. SIGARCH Comput. Archit. News 45(2), 548\u2013560 (2017). https:\/\/doi.org\/10.1145\/3140659.3080215","journal-title":"SIGARCH Comput. Archit. News"},{"key":"156_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, J., Gu, H., Zhang, G.L., et al.: Hardware-software codesign of weight reshaping and systolic array multiplexing for efficient CNNs. In: 2021 Design, Automation Test in Europe Conference Exhibition (DATE), pp. 667\u2013672 (2021). https:\/\/doi.org\/10.23919\/DATE51398.2021.9474215","DOI":"10.23919\/DATE51398.2021.9474215"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00156-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-023-00156-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00156-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T08:07:44Z","timestamp":1701677264000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-023-00156-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,26]]},"references-count":34,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["156"],"URL":"https:\/\/doi.org\/10.1007\/s42514-023-00156-w","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2023,5,26]]},"assertion":[{"value":"13 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 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":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}