{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:40:08Z","timestamp":1783438808656,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Research Foundation (DFG)","award":["449683531"],"award-info":[{"award-number":["449683531"]}]},{"name":"German Federal Ministry of Education and Research (BMBF)","award":["NHR2021HE"],"award-info":[{"award-number":["NHR2021HE"]}]},{"name":"German Federal Ministry of Education and Research (BMBF)","award":["Software Campus"],"award-info":[{"award-number":["Software Campus"]}]},{"name":"Hessian Ministry of Science and Research, Art and Culture (HMWK)","award":["NHR4CES"],"award-info":[{"award-number":["NHR4CES"]}]},{"name":"Gauss Centre for Supercomputing e.V.","award":["JUWELS"],"award-info":[{"award-number":["JUWELS"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673107","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"168-178","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Dissecting Convolutional Neural Networks for Runtime and Scalability Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1783-172X","authenticated-orcid":false,"given":"Tim","family":"Beringer","sequence":"first","affiliation":[{"name":"Technical University of Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3374-4472","authenticated-orcid":false,"given":"Jakob","family":"Stock","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-4710","authenticated-orcid":false,"given":"Arya","family":"Mazaheri","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-3599","authenticated-orcid":false,"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. CoRR abs\/1710.05420","author":"Cai Ermao","year":"2017","unstructured":"Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, and Diana Marculescu. 2017. NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. CoRR abs\/1710.05420 (2017). arXiv:1710.05420"},{"key":"e_1_3_2_2_2_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Cai Han","year":"2020","unstructured":"Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2020. Once for All: Train One Network and Specialize it for Efficient Deployment. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_3_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Cai Han","year":"2019","unstructured":"Han Cai, Ligeng Zhu, and Song Han. 2019. ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_4_1","volume-title":"Fast and Accurate Model Scaling. CoRR abs\/2103.06877","author":"Doll\u00e1r Piotr","year":"2021","unstructured":"Piotr Doll\u00e1r, Mannat Singh, and Ross\u00a0B. Girshick. 2021. Fast and Accurate Model Scaling. CoRR abs\/2103.06877 (2021). arXiv:2103.06877"},{"key":"e_1_3_2_2_5_1","first-page":"1","article-title":"Neural Architecture Search: A Survey","volume":"20","author":"Elsken Thomas","year":"2019","unstructured":"Thomas Elsken, Jan\u00a0Hendrik Metzen, and Frank Hutter. 2019. Neural Architecture Search: A Survey. Journal of Machine Learning Research 20, 1 (jan 2019), 1997\u20132017.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"e_1_3_2_2_7_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385 (2015). arXiv:1512.03385"},{"key":"e_1_3_2_2_8_1","volume-title":"Searching for MobileNetV3. CoRR abs\/1905.02244","author":"Howard Andrew","year":"2019","unstructured":"Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc\u00a0V. Le, and Hartwig Adam. 2019. Searching for MobileNetV3. CoRR abs\/1905.02244 (2019). arXiv:1905.02244"},{"key":"e_1_3_2_2_9_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR abs\/1602.07360","author":"Iandola N.","year":"2016","unstructured":"Forrest\u00a0N. Iandola, Matthew\u00a0W. Moskewicz, Khalid Ashraf, Song Han, William\u00a0J. Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR abs\/1602.07360 (2016). arXiv:1602.07360"},{"key":"e_1_3_2_2_10_1","volume-title":"Predicting the Computational Cost of Deep Learning Models. CoRR abs\/1811.11880","author":"Justus Daniel","year":"2018","unstructured":"Daniel Justus, John Brennan, Stephen Bonner, and Andrew\u00a0Stephen McGough. 2018. Predicting the Computational Cost of Deep Learning Models. CoRR abs\/1811.11880 (2018). arXiv:1811.11880"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460644"},{"key":"e_1_3_2_2_12_1","volume-title":"One weird trick for parallelizing convolutional neural networks. CoRR abs\/1404.5997","author":"Krizhevsky Alex","year":"2014","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. CoRR abs\/1404.5997 (2014). arXiv:1404.5997"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3161187"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916550"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"e_1_3_2_2_16_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). PMLR, 4095\u20134104","author":"Pham Hieu","year":"2018","unstructured":"Hieu Pham, Melody Guan, Barret Zoph, Quoc Le, and Jeff Dean. 2018. Efficient neural architecture search via parameters sharing. In Proc. of International Conference on Machine Learning (ICML). PMLR, 4095\u20134104."},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Qi Hang","year":"2017","unstructured":"Hang Qi, Evan\u00a0R. Sparks, and Ameet Talwalkar. 2017. Paleo: A Performance Model for Deep Neural Networks. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_18_1","volume-title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. CoRR abs\/2008.12260","author":"Qiao Aurick","year":"2020","unstructured":"Aurick Qiao, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory\u00a0R. Ganger, and Eric\u00a0P. Xing. 2020. Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. CoRR abs\/2008.12260 (2020). arXiv:2008.12260"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00197"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_2_21_1","volume-title":"Designing Network Design Spaces. CoRR abs\/2003.13678","author":"Radosavovic Ilija","year":"2020","unstructured":"Ilija Radosavovic, Raj\u00a0Prateek Kosaraju, Ross\u00a0B. Girshick, Kaiming He, and Piotr Doll\u00e1r. 2020. Designing Network Design Spaces. CoRR abs\/2003.13678 (2020). arXiv:2003.13678"},{"key":"e_1_3_2_2_22_1","volume-title":"Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR abs\/1801.04381","author":"Sandler Mark","year":"2018","unstructured":"Mark Sandler, Andrew\u00a0G. Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR abs\/1801.04381 (2018). arXiv:1801.04381"},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. of Euro-Par 2023: Parallel Processing, Jos\u00e9 Cano, Marios\u00a0D. Dikaiakos, George\u00a0A. Papadopoulos, Miquel Peric\u00e0s, and Rizos Sakellariou (Eds.). 3\u201316","author":"Selvam Panner","year":"2023","unstructured":"Panner Selvam, Karthick, and Mats Brorsson. 2023. DIPPM: A Deep Learning Inference Performance Predictive Model Using Graph Neural Networks. In Proc. of Euro-Par 2023: Parallel Processing, Jos\u00e9 Cano, Marios\u00a0D. Dikaiakos, George\u00a0A. Papadopoulos, Miquel Peric\u00e0s, and Rizos Sakellariou (Eds.). 3\u201316."},{"key":"e_1_3_2_2_24_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike\u00a0Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_2_25_1","volume-title":"Measuring the Effects of Data Parallelism on Neural Network Training. CoRR abs\/1811.03600","author":"Shallue J.","year":"2018","unstructured":"Christopher\u00a0J. Shallue, Jaehoon Lee, Joseph\u00a0M. Antognini, Jascha Sohl-Dickstein, Roy Frostig, and George\u00a0E. Dahl. 2018. Measuring the Effects of Data Parallelism on Neural Network Training. CoRR abs\/1811.03600 (2018)."},{"key":"e_1_3_2_2_26_1","volume-title":"Proc. of 3rd International Conference on Learning Representations (ICLR), Yoshua Bengio and Yann LeCun (Eds.).","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proc. of 3rd International Conference on Learning Representations (ICLR), Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_2_27_1","volume-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. CoRR abs\/1905.11946","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc\u00a0V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. CoRR abs\/1905.11946 (2019). arXiv:1905.11946"},{"key":"e_1_3_2_2_28_1","volume-title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search. CoRR abs\/1812.03443","author":"Wu Bichen","year":"2018","unstructured":"Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, and Kurt Keutzer. 2018. FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search. CoRR abs\/1812.03443 (2018). arXiv:1812.03443"},{"key":"e_1_3_2_2_29_1","volume-title":"Aggregated Residual Transformations for Deep Neural Networks. CoRR abs\/1611.05431","author":"Xie Saining","year":"2016","unstructured":"Saining Xie, Ross\u00a0B. Girshick, Piotr Doll\u00e1r, Zhuowen Tu, and Kaiming He. 2016. Aggregated Residual Transformations for Deep Neural Networks. CoRR abs\/1611.05431 (2016). arXiv:1611.05431"},{"key":"e_1_3_2_2_30_1","volume-title":"Computational Performance Predictions for Deep Neural Network Training: A Runtime-Based Approach. CoRR abs\/2102.00527","author":"Yu X.","year":"2021","unstructured":"Geoffrey\u00a0X. Yu, Yubo Gao, Pavel Golikov, and Gennady Pekhimenko. 2021. Computational Performance Predictions for Deep Neural Network Training: A Runtime-Based Approach. CoRR abs\/2102.00527 (2021). arXiv:2102.00527"},{"key":"e_1_3_2_2_31_1","volume-title":"Proc. of 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Yu X.","year":"2021","unstructured":"Geoffrey\u00a0X. Yu, Yubo Gao, Pavel Golikov, and Gennady Pekhimenko. 2021. Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training. In Proc. of 2021 USENIX Annual Technical Conference (USENIX ATC 21). 503\u2013521."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673107","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:33:39Z","timestamp":1758648819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":32,"alternative-id":["10.1145\/3673038.3673107","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673107","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}