{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:50:00Z","timestamp":1771951800668,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"DFG, German Research Foundation","award":["470527619"],"award-info":[{"award-number":["470527619"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,17]]},"DOI":"10.1145\/3578360.3580269","type":"proceedings-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T20:20:06Z","timestamp":1676665206000},"page":"61-72","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["(De\/Re)-Compositions Expressed Systematically via MDH-Based Schedules"],"prefix":"10.1145","author":[{"given":"Ari","family":"Rasch","sequence":"first","affiliation":[{"name":"University of Muenster, Muenster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Schulze","sequence":"additional","affiliation":[{"name":"University of Muenster, Muenster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denys","family":"Shabalin","sequence":"additional","affiliation":[{"name":"Google, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne","family":"Elster","sequence":"additional","affiliation":[{"name":"NTNU, Trondheim, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergei","family":"Gorlatch","sequence":"additional","affiliation":[{"name":"University of Muenster, Muenster, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Appache TVM Community. 2020. Non top-level reductions in compute statements. https:\/\/discuss.tvm.apache.org\/t\/non-top-level-reductions-in-compute-statements\/5693"},{"key":"e_1_3_2_1_2_1","unstructured":"Appache TVM Community. 2022. Bind reduce axis to blocks. https:\/\/discuss.tvm.apache.org\/t\/bind-reduce-axis-to-blocks\/2907"},{"key":"e_1_3_2_1_3_1","unstructured":"Appache TVM Community. 2022. Expressing nested reduce operations. https:\/\/discuss.tvm.apache.org\/t\/expressing-nested-reduce-operations\/8784"},{"key":"e_1_3_2_1_4_1","unstructured":"Appache TVM Community. 2022. Implementing Array Packing via cache_read. https:\/\/discuss.tvm.apache.org\/t\/implementing-array-packing-via-cache-read\/13360"},{"key":"e_1_3_2_1_5_1","unstructured":"Appache TVM Community. 2022. Undetected parallelization issue. https:\/\/discuss.tvm.apache.org\/t\/undetected-parallelization-issue\/13224"},{"key":"e_1_3_2_1_6_1","unstructured":"Appache TVM Community. 2022. Undetected type issue. https:\/\/discuss.tvm.apache.org\/t\/undetected-type-issue\/13223"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Artifact Implementation. 2022. https:\/\/doi.org\/10.1145\/3554351 10.1145\/3554351","DOI":"10.1145\/3554351"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2841200"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Uday Bondhugula. 2020. High Performance Code Generation in MLIR: An Early Case Study with GEMM. https:\/\/doi.org\/10.48550\/ARXIV.2003.00532","DOI":"10.48550\/ARXIV.2003.00532"},{"key":"e_1_3_2_1_12_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA. 578\u2013594. isbn:978-1-939133-08-3 https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. Learning to Optimize Tensor Programs. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.). 31, Curran Associates, Inc.. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/8b5700012be65c9da25f49408d959ca0-Paper.pdf"},{"key":"e_1_3_2_1_14_1","unstructured":"Vincent Dumoulin and Francesco Visin. 2018. A guide to convolution arithmetic for deep learning. arxiv:stat.ML\/1603.07285."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314612"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188543"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.04296"},{"key":"e_1_3_2_1_18_1","volume-title":"Encyclopedia of parallel computing","author":"Gorlatch Sergei","unstructured":"Sergei Gorlatch and Murray Cole. 2011. Parallel skeletons. In Encyclopedia of parallel computing. Springer-Verlag GmbH, 1417\u20131422."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/504210.504213"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414632"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410227"},{"key":"e_1_3_2_1_23_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. arxiv:1512.03385"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140587.3062354"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_1_26_1","volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR, abs\/1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR, abs\/1704.04861 (2017), arXiv:1704.04861. arxiv:1704.04861"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400690"},{"key":"e_1_3_2_1_28_1","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger (Eds.). 25, Curran Associates, Inc.. https:\/\/proceedings.neurips.cc\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494986"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498717"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/233561.233564"},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2018. Warp-level Primitives. https:\/\/developer.nvidia.com\/blog\/using-cuda-warp-level-primitives\/"},{"key":"e_1_3_2_1_34_1","unstructured":"NVIDIA. 2022. CUDA Toolkit Documentation. https:\/\/docs.nvidia.com\/cuda\/"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3473593"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"S. J. Pennycook J. D. Sewall and V. W. Lee. 2016. A Metric for Performance Portability. https:\/\/doi.org\/10.48550\/ARXIV.1611.07409","DOI":"10.48550\/ARXIV.1611.07409"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304059"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377555.3377896"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02829-2"},{"key":"e_1_3_2_1_41_1","volume-title":"Multi-Dimensional Homomorphisms and Their Implementation in OpenCL. In International Workshop on High-Level Parallel Programming and Applications (HLPP). 101\u2013119","author":"Rasch Ari","year":"2016","unstructured":"Ari Rasch and Sergei Gorlatch. 2016. Multi-Dimensional Homomorphisms and Their Implementation in OpenCL. In International Workshop on High-Level Parallel Programming and Applications (HLPP). 101\u2013119."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2019.00035"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the International Workshop on Polyhedral Compilation Techniques (IMPACT\u201920)","author":"Rasch Ari","year":"2020","unstructured":"Ari Rasch, Richard Schulze, and Sergei Gorlatch. 2020. md_poly: A Performance-Portable Polyhedral Compiler based on Multi-Dimensional Homomorphisms. In Proceedings of the International Workshop on Polyhedral Compilation Techniques (IMPACT\u201920). 1\u20134."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297330"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427093"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. https:\/\/doi.org\/10.48550\/ARXIV.1409.1556","DOI":"10.48550\/ARXIV.1409.1556"},{"key":"e_1_3_2_1_47_1","unstructured":"TensorFlow. 2022. MobileNet v1 models for Keras. https:\/\/github.com\/keras-team\/keras\/blob\/master\/keras\/applications\/mobilenet.py"},{"key":"e_1_3_2_1_48_1","unstructured":"TensorFlow. 2022. ResNet models for Keras. https:\/\/github.com\/keras-team\/keras\/blob\/master\/keras\/applications\/resnet.py"},{"key":"e_1_3_2_1_49_1","unstructured":"TensorFlow. 2022. VGG16 model for Keras. https:\/\/github.com\/keras-team\/keras\/blob\/master\/keras\/applications\/vgg16.py"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.00618"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.97902"},{"key":"e_1_3_2_1_52_1","first-page":"67","article-title":"Numerical Optimization","volume":"35","author":"Wright Stephen","year":"1999","unstructured":"Stephen Wright and Jorge Nocedal. 1999. Numerical Optimization. Springer Science, 35, 67\u201368 (1999), 7.","journal-title":"Springer Science"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523437"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434301"},{"key":"e_1_3_2_1_55_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 863\u2013879. isbn:978-1-939133-19-9 https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"}],"event":{"name":"CC '23: 32nd ACM SIGPLAN International Conference on Compiler Construction","location":"Montr\u00e9al QC Canada","acronym":"CC '23","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 32nd ACM SIGPLAN International Conference on Compiler Construction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578360.3580269","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578360.3580269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:52Z","timestamp":1750178812000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578360.3580269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":55,"alternative-id":["10.1145\/3578360.3580269","10.1145\/3578360"],"URL":"https:\/\/doi.org\/10.1145\/3578360.3580269","relation":{},"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"2023-02-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}