{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T08:27:32Z","timestamp":1786523252018,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","funder":[{"name":"German Research Foundation DFG)","award":["470527619"],"award-info":[{"award-number":["470527619"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767572","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"2100-2113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reduction-Aware Directive-Based Programming via Multi-Dimensional Homomorphisms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7592-6850","authenticated-orcid":false,"given":"Richard","family":"Schulze","sequence":"first","affiliation":[{"name":"University of Muenster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3857-9380","authenticated-orcid":false,"given":"Sergei","family":"Gorlatch","sequence":"additional","affiliation":[{"name":"University of Muenster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0286-0755","authenticated-orcid":false,"given":"Ari","family":"Rasch","sequence":"additional","affiliation":[{"name":"University of Muenster, M\u00fcnster, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"2025. TIOBE \u2013 The Software Quality Company. https:\/\/www.tiobe.com\/tiobe-index\/."},{"key":"e_1_3_3_3_3_2","unstructured":"Apache TVM Community. 2022. Expressing nested reduce operations. https:\/\/discuss.tvm.apache.org\/t\/expressing-nested-reduce-operations\/8784."},{"key":"e_1_3_3_3_4_2","unstructured":"Apache TVM Community. 2022. Invalid comm_reducer. https:\/\/discuss.tvm.apache.org\/t\/invalid-comm-reducer\/12788."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854048"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321441"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741260"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1926354.1926358"},{"key":"e_1_3_3_3_12_2","volume-title":"CHiLL: A framework for composing high-level loop transformations","author":"Chen Chun","year":"2008","unstructured":"Chun Chen, Jacqueline Chame, and Mary Hall. 2008. CHiLL: A framework for composing high-level loop transformations. Technical Report. Technical Report 08-897, U. of Southern California."},{"key":"e_1_3_3_3_13_2","first-page":"578","volume-title":"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. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_3_3_14_2","unstructured":"Johannes Doerfert Kevin Streit Sebastian Hack and Zino Benaissa. 2015. Polly\u2019s Polyhedral Scheduling in the Presence of Reductions. arxiv:https:\/\/arXiv.org\/abs\/1505.07716\u00a0[cs.PL] https:\/\/arxiv.org\/abs\/1505.07716"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314612"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Sylvain Girbal Nicolas Vasilache C\u00e9dric Bastoul Albert Cohen David Parello Marc Sigler and Olivier Temam. 2006. Semi-Automatic Composition of Loop Transformations for Deep Parallelism and Memory Hierarchies. International Journal of Parallel Programming 34 3 (2006) 261\u2013317. 10.1007\/s10766-006-0012-3","DOI":"10.1007\/s10766-006-0012-3"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414632"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3062341.3062354"},{"key":"e_1_3_3_3_20_2","unstructured":"K Hentschel et\u00a0al. 2008. Das Krebsregister-Manual der Gesellschaft der epidemiologischen Krebsregister in Deutschland eV Zuckschwerdt Verlag. (2008)."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_3_3_22_2","volume-title":"A framework for unifying reordering transformations","author":"Kelly Wayne","year":"1998","unstructured":"Wayne Kelly and William Pugh. 1998. A framework for unifying reordering transformations. Technical Report. Technical Report UMIACS-TR-92-126.1."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Malik Khan Protonu Basu Gabe Rudy Mary Hall Chun Chen and Jacqueline Chame. 2013. A Script-Based Autotuning Compiler System to Generate High-Performance CUDA Code. ACM Trans. Archit. Code Optim. 9 4 Article 31 (jan 2013) 25\u00a0pages. 10.1145\/2400682.2400690","DOI":"10.1145\/2400682.2400690"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661182"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833162"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Amanda Liu Gilbert\u00a0Louis Bernstein Adam Chlipala and Jonathan Ragan-Kelley. 2022. Verified Tensor-Program Optimization via High-Level Scheduling Rewrites. Proc. ACM Program. Lang. 6 POPL Article 55 (jan 2022) 28\u00a0pages. 10.1145\/3498717","DOI":"10.1145\/3498717"},{"key":"e_1_3_3_3_27_2","unstructured":"Numba. 2025. Automatic parallelization with @jit. https:\/\/numba.readthedocs.io\/en\/stable\/user\/parallel.html."},{"key":"e_1_3_3_3_28_2","volume-title":"OpenACC: More Science, Less Programming","year":"2025","unstructured":"OpenACC-Standard.org. 2025. OpenACC: More Science, Less Programming. https:\/\/www.openacc.org\/specification"},{"key":"e_1_3_3_3_29_2","volume-title":"OpenMP: The OpenMP API specification for parallel programming","year":"2025","unstructured":"OpenMP. 2025. OpenMP: The OpenMP API specification for parallel programming. https:\/\/www.openmp.org\/specifications\/"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Adam Paszke Daniel\u00a0D. Johnson David Duvenaud Dimitrios Vytiniotis Alexey Radul Matthew\u00a0J. Johnson Jonathan Ragan-Kelley and Dougal Maclaurin. 2021. Getting to the Point: Index Sets and Parallelism-Preserving Autodiff for Pointful Array Programming. Proc. ACM Program. Lang. 5 ICFP Article 88 (aug 2021) 29\u00a0pages. 10.1145\/3473593","DOI":"10.1145\/3473593"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"M. Puschel J.M.F. Moura J.R. Johnson D. Padua M.M. Veloso B.W. Singer Jianxin Xiong F. Franchetti A. Gacic Y. Voronenko K. Chen R.W. Johnson and N. Rizzolo. 2005. SPIRAL: Code Generation for DSP Transforms. Proc. IEEE 93 2 (2005) 232\u2013275. 10.1109\/JPROC.2004.840306","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Ari Rasch. 2024. (De\/Re)-Composition of Data-Parallel Computations via Multi-Dimensional Homomorphisms. ACM Trans. Program. Lang. Syst. 46 3 Article 10 (Oct. 2024) 74\u00a0pages. 10.1145\/3665643","DOI":"10.1145\/3665643"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","unstructured":"Ari Rasch Julian Bigge Martin Wrodarczyk Richard Schulze and Sergei Gorlatch. 2020. dOCAL: high-level distributed programming with OpenCL and CUDA. The Journal of Supercomputing 76 7 (2020) 5117\u20135138. 10.1007\/s11227-019-02829-2","DOI":"10.1007\/s11227-019-02829-2"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297330"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Ari Rasch Richard Schulze Michel Steuwer and Sergei Gorlatch. 2021. Efficient Auto-Tuning of Parallel Programs with Interdependent Tuning Parameters via Auto-Tuning Framework (ATF). ACM Trans. Archit. Code Optim. 18 1 Article 1 (Jan. 2021) 26\u00a0pages. 10.1145\/3427093","DOI":"10.1145\/3427093"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8644541"},{"key":"e_1_3_3_3_38_2","unstructured":"Richard Schulze. 2025. WACCPD25 Artifact. GitLab repository. https:\/\/gitlab.com\/mdh-project\/waccpd25_artifact"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708493.3712682"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2784731.2784754"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","unstructured":"Adilla Susungi Norman\u00a0A. Rink Albert Cohen Jeronimo Castrillon and Claude Tadonki. 2020. Meta-programming for cross-domain tensor optimizations. SIGPLAN Not. 53 9 (apr 2020) 79\u201392. 10.1145\/3393934.3278131","DOI":"10.1145\/3393934.3278131"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24452-0_9"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Nicolas Vasilache Oleksandr Zinenko Theodoros Theodoridis Priya Goyal Zachary Devito William\u00a0S. Moses Sven Verdoolaege Andrew Adams and Albert Cohen. 2019. The Next 700 Accelerated Layers: From Mathematical Expressions of Network Computation Graphs to Accelerated GPU Kernels Automatically. ACM Trans. Archit. Code Optim. 16 4 Article 38 (Oct. 2019) 26\u00a0pages. 10.1145\/3355606","DOI":"10.1145\/3355606"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","unstructured":"Sven Verdoolaege Juan Carlos\u00a0Juega Albert Cohen Jos\u00e9 Ignacio\u00a0G\u00f3mez Christian Tenllado and Francky Catthoor. 2013. Polyhedral parallel code generation for CUDA. ACM Trans. Archit. Code Optim. 9 4 Article 54 (Jan. 2013) 23\u00a0pages. 10.1145\/2400682.2400713","DOI":"10.1145\/2400682.2400713"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","unstructured":"Bram Wasti Jos\u00e9\u00a0Pablo Cambronero Benoit Steiner Hugh Leather and Aleksandar Zlateski. 2022. LoopStack: a Lightweight Tensor Algebra Compiler Stack. 10.48550\/ARXIV.2205.00618","DOI":"10.48550\/ARXIV.2205.00618"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10004"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523437"},{"key":"e_1_3_3_3_48_2","first-page":"863","volume-title":"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\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph\u00a0E. 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. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:33:27Z","timestamp":1786520007000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":47,"alternative-id":["10.1145\/3731599.3767572","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767572","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}