{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T23:54:50Z","timestamp":1770681290749,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":87,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2020-113614RB-C21"],"award-info":[{"award-number":["PID2020-113614RB-C21"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2211982"],"award-info":[{"award-number":["2211982"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3588195.3592984","type":"proceedings-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T20:47:00Z","timestamp":1691441220000},"page":"45-57","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Performance Optimization using Multimodal Modeling and Heterogeneous GNN"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0947-1182","authenticated-orcid":false,"given":"Akash","family":"Dutta","sequence":"first","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9640-6763","authenticated-orcid":false,"given":"Jordi","family":"Alcaraz","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3678-5730","authenticated-orcid":false,"given":"Ali","family":"TehraniJamsaz","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9729-8557","authenticated-orcid":false,"given":"Eduardo","family":"Cesar","sequence":"additional","affiliation":[{"name":"Universitat Aut\u00f2noma de Barcelona, Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0090-4109","authenticated-orcid":false,"given":"Anna","family":"Sikora","sequence":"additional","affiliation":[{"name":"Universitat Aut\u00f2noma de Barcelona, Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8672-5317","authenticated-orcid":false,"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29400-7_6"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP52278.2021.00019"},{"key":"e_1_3_2_1_3_1","volume-title":"Predicting number of threads using balanced datasets for openMP regions. Computing","author":"Alcaraz Jordi","year":"2022","unstructured":"Jordi Alcaraz, Ali TehraniJamsaz, Akash Dutta, Anna Sikora, Ali Jannesari, Joan Sorribes, and Eduardo Cesar. 2022. Predicting number of threads using balanced datasets for openMP regions. Computing (2022), 1--19."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_3_2_1_5_1","volume-title":"Learning to represent programs with graphs. arXiv preprint arXiv:1711.00740","author":"Allamanis Miltiadis","year":"2017","unstructured":"Miltiadis Allamanis, Marc Brockschmidt, and Mahmoud Khademi. 2017. Learning to represent programs with graphs. arXiv preprint arXiv:1711.00740 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296979.3192412"},{"key":"e_1_3_2_1_7_1","unstructured":"AMD. [n.d.]. AMD OpenCL accelerated parallel processing SDK. https:\/\/developer.amd.com\/amd-accelerated-parallel-processing-app-sdk\/."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_9_1","unstructured":"P Balaprakash R Egele and P Hovland. 2020. ytopt. https:\/\/github.com\/ytopt-team\/ytopt (GitHub repository). Argonne National Laboratory. (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.39"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2019.04.002"},{"key":"e_1_3_2_1_12_1","unstructured":"E Barszcz J Barton L Dagum P Frederickson T Lasinski R Schreiber V Venkatakrishnan S Weeratunga D Bailey D Browning et al. 1991. The nas parallel benchmarks. In The International Journal of Supercomputer Applications. Citeseer."},{"key":"e_1_3_2_1_13_1","first-page":"3585","article-title":"Neural Code Comprehension: A Learnable Representation of Code Semantics","volume":"31","author":"Ben-Nun Tal","year":"2018","unstructured":"Tal Ben-Nun, Alice Shoshana Jakobovits, and Torsten Hoefler. 2018. Neural Code Comprehension: A Learnable Representation of Code Semantics. Advances in Neural Information Processing Systems, Vol. 31 (2018), 3585--3597.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Noise reduction in speech processing","author":"Benesty Jacob","unstructured":"Jacob Benesty, Jingdong Chen, Yiteng Huang, and Israel Cohen. 2009. Pearson correlation coefficient. In Noise reduction in speech processing. Springer, 1--4."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377555.3377894"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"e_1_3_2_1_18_1","unstructured":"Tianqi Chen Tong He Michael Benesty Vadim Khotilovich Yuan Tang Hyunsu Cho Kailong Chen et al. 2015. Xgboost: extreme gradient boosting. R package version 0.4--2 Vol. 1 4 (2015) 1--4."},{"key":"e_1_3_2_1_19_1","unstructured":"NVIDIA Corporation. [n.d.]. CUDA. http:\/\/developer.nvidia.com\/object\/cuda.html."},{"key":"e_1_3_2_1_20_1","volume-title":"PROGRAML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations. In International Conference on Machine Learning. PMLR, 2244--2253","author":"Cummins Chris","year":"2021","unstructured":"Chris Cummins, Zacharias V Fisches, Tal Ben-Nun, Torsten Hoefler, Michael FP O'Boyle, and Hugh Leather. 2021. PROGRAML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations. In International Conference on Machine Learning. PMLR, 2244--2253."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.24"},{"key":"e_1_3_2_1_22_1","unstructured":"Christopher Edward Cummins. 2020. Deep learning for compilers. (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Truyen Tran, John Grundy, Aditya Ghose, Taeksu Kim, and Chul-Joo Kim.","author":"Dam Hoa Khanh","year":"2018","unstructured":"Hoa Khanh Dam, Trang Pham, Shien Wee Ng, Truyen Tran, John Grundy, Aditya Ghose, Taeksu Kim, and Chul-Joo Kim. 2018. A deep tree-based model for software defect prediction. arXiv preprint arXiv:1802.00921 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (ATC). 1--14","author":"Duplyakin Dmitry","year":"2019","unstructured":"Dmitry Duplyakin, Robert Ricci, Aleksander Maricq, Gary Wong, Jonathon Duerig, Eric Eide, Leigh Stoller, Mike Hibler, David Johnson, Kirk Webb, Aditya Akella, Kuangching Wang, Glenn Ricart, Larry Landweber, Chip Elliott, Michael Zink, Emmanuel Cecchet, Snigdhaswin Kar, and Prabodh Mishra. 2019. The Design and Operation of CloudLab. In Proceedings of the USENIX Annual Technical Conference (ATC). 1--14. https:\/\/www.flux.utah.edu\/paper\/duplyakin-atc19"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/AI4S56813.2022.00010"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00060"},{"key":"e_1_3_2_1_28_1","volume-title":"Margot: a dynamic autotuning framework for self-aware approximate computing","author":"Gadioli Davide","year":"2018","unstructured":"Davide Gadioli, Emanuele Vitali, Gianluca Palermo, and Cristina Silvano. 2018. Margot: a dynamic autotuning framework for self-aware approximate computing. IEEE transactions on computers, Vol. 68, 5 (2018), 713--728."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 1263--1272","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263--1272."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Scott Grauer-Gray Lifan Xu Robert Searles Sudhee Ayalasomayajula and John Cavazos. 2012. Auto-tuning a high-level language targeted to GPU codes. In 2012 innovative parallel computing (InPar). Ieee 1--10.","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494993"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168824"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377928"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025--1035","author":"Hamilton William L","year":"2017","unstructured":"William L Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025--1035."},{"key":"e_1_3_2_1_35_1","volume-title":"miniFE. https:\/\/github.com\/Mantevo\/miniFE. GitHub repository","author":"Hammond Si","year":"2022","unstructured":"Si Hammond, Christian Trott, and Noah Evans. 2022. miniFE. https:\/\/github.com\/Mantevo\/miniFE. GitHub repository (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Unicorn: Runtime provenance-based detector for advanced persistent threats. arXiv preprint arXiv:2001.01525","author":"Han Xueyuan","year":"2020","unstructured":"Xueyuan Han, Thomas Pasquier, Adam Bates, James Mickens, and Margo Seltzer. 2020. Unicorn: Runtime provenance-based detector for advanced persistent threats. arXiv preprint arXiv:2001.01525 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.60"},{"key":"e_1_3_2_1_38_1","unstructured":"Michael Jahrer. 2017. Porto Seguro's Safe Driver Prediction. https:\/\/www.kaggle.com\/c\/porto-seguro-safe-driver-prediction\/discussion\/44629. (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.115"},{"key":"e_1_3_2_1_40_1","volume-title":"Technical Report.","author":"Karlin Ian","unstructured":"Ian Karlin, Jeff Keasler, and J Robert Neely. 2013b. Lulesh 2.0 updates and changes. Technical Report. Lawrence Livermore National Lab.(LLNL), Livermore, CA (United States)."},{"key":"e_1_3_2_1_41_1","volume-title":"Towards autotuning of OpenMP applications on multicore architectures. arXiv preprint arXiv:1401.4063","author":"Katarzy'nski Jakub","year":"2014","unstructured":"Jakub Katarzy'nski and Maciej Cytowski. 2014. Towards autotuning of OpenMP applications on multicore architectures. arXiv preprint arXiv:1401.4063 (2014)."},{"key":"e_1_3_2_1_42_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_43_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_44_1","volume-title":"Customized Monte Carlo Tree Search for LLVM\/Polly's Composable Loop Optimization Transformations. arXiv preprint arXiv:2105.04555","author":"Koo Jaehoon","year":"2021","unstructured":"Jaehoon Koo, Prasanna Balaprakash, Michael Kruse, Xingfu Wu, Paul Hovland, and Mary Hall. 2021. Customized Monte Carlo Tree Search for LLVM\/Polly's Composable Loop Optimization Transformations. arXiv preprint arXiv:2105.04555 (2021)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6495004"},{"key":"e_1_3_2_1_46_1","unstructured":"Lawrence Livermore National Lab. 2022. Quicksilver. https:\/\/github.com\/LLNL\/Quicksilver."},{"key":"e_1_3_2_1_47_1","volume-title":"International conference on machine learning. PMLR, 3835--3845","author":"Li Yujia","year":"2019","unstructured":"Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. 2019. Graph matching networks for learning the similarity of graph structured objects. In International conference on machine learning. PMLR, 3835--3845."},{"key":"e_1_3_2_1_48_1","volume-title":"Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493","author":"Li Yujia","year":"2015","unstructured":"Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. 2015. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126958"},{"key":"e_1_3_2_1_50_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628087"},{"key":"e_1_3_2_1_53_1","volume-title":"1995 a. Memory Bandwidth and Machine Balance in Current High Performance Computers","author":"McCalpin John D.","year":"1995","unstructured":"John D. McCalpin. 1995 a. Memory Bandwidth and Machine Balance in Current High Performance Computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter (Dec. 1995), 19--25."},{"key":"e_1_3_2_1_54_1","volume-title":"1995 b. Stream benchmark. Link: www. cs. virginia. edu\/stream\/ref. html# what","author":"McCalpin John D","year":"1995","unstructured":"John D McCalpin. 1995 b. Stream benchmark. Link: www. cs. virginia. edu\/stream\/ref. html# what, Vol. 22, 7 (1995)."},{"key":"e_1_3_2_1_55_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis, Cambridge Yang, Yewen Pu, Dr Amarasinghe, Michael Carbin, et al. 2019. Compiler auto-vectorization with imitation learning. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00090"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the department of defense HPCMP users group conference","volume":"710","author":"Mucci Philip J","year":"1999","unstructured":"Philip J Mucci, Shirley Browne, Christine Deane, and George Ho. 1999. PAPI: A portable interface to hardware performance counters. In Proceedings of the department of defense HPCMP users group conference, Vol. 710. Citeseer."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21487-5_12"},{"key":"e_1_3_2_1_59_1","unstructured":"Jiquan Ngiam Aditya Khosla Mingyu Kim Juhan Nam Honglak Lee and Andrew Y Ng. 2011. Multimodal deep learning. In ICML."},{"key":"e_1_3_2_1_60_1","volume-title":"Polybench: The polyhedral benchmark suite. URL: http:\/\/www. cs. ucla. edu\/pouchet\/software\/polybench","author":"Pouchet Louis-No\u00ebl","year":"2012","unstructured":"Louis-No\u00ebl Pouchet et al. 2012. Polybench: The polyhedral benchmark suite. URL: http:\/\/www. cs. ucla. edu\/pouchet\/software\/polybench, Vol. 437 (2012), 1--1."},{"key":"e_1_3_2_1_61_1","volume-title":"Deep multimodal learning: A survey on recent advances and trends","author":"Ramachandram Dhanesh","year":"2017","unstructured":"Dhanesh Ramachandram and Graham W Taylor. 2017. Deep multimodal learning: A survey on recent advances and trends. IEEE signal processing magazine, Vol. 34, 6 (2017), 96--108."},{"key":"e_1_3_2_1_62_1","volume-title":"Rigel: A Framework for OpenMP PerformanceTuning. In 2019 IEEE 21st International Conference on High Performance Computing and Communications","author":"Rameshka Piyumi","year":"2019","unstructured":"Piyumi Rameshka, Pasindu Senanayake, Thulana Kannangara, Praveen Seneviratne, Sanath Jayasena, Tharindu Rusira, and Mary Hall. 2019. Rigel: A Framework for OpenMP PerformanceTuning. In 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS). IEEE, 2093--2102."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2775051.2677009"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454109"},{"key":"e_1_3_2_1_65_1","unstructured":"Aparna Sasidharan and Marc Snir. 2016. MiniAMR-A miniapp for Adaptive Mesh Refinement. (2016)."},{"key":"e_1_3_2_1_66_1","volume-title":"Deep learning in neural networks: An overview. Neural networks","author":"Schmidhuber J\u00fcrgen","year":"2015","unstructured":"J\u00fcrgen Schmidhuber. 2015. Deep learning in neural networks: An overview. Neural networks, Vol. 61 (2015), 85--117."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2011.6114174"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28596-8_4"},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Steiner Benoit","year":"2021","unstructured":"Benoit Steiner, Chris Cummins, Horace He, and Hugh Leather. 2021. Value learning for throughput optimization of deep learning workloads. Proceedings of Machine Learning and Systems, Vol. 3 (2021)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.29"},{"key":"e_1_3_2_1_71_1","first-page":"27","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","volume":"127","author":"Stratton John A","year":"2012","unstructured":"John A Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, and Wen-mei W Hwu. 2012. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing, Vol. 127 (2012), 27.","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"e_1_3_2_1_72_1","volume-title":"Songyuan Li, and Jabbar Abdul.","author":"Summaira Jabeen","year":"2021","unstructured":"Jabeen Summaira, Xi Li, Amin Muhammad Shoib, Songyuan Li, and Jabbar Abdul. 2021. Recent Advances and Trends in Multimodal Deep Learning: A Review. arXiv preprint arXiv:2105.11087 (2021)."},{"key":"e_1_3_2_1_73_1","volume-title":"Multi-graph convolutional neural networks for representation learning in recommendation","author":"Sun Jianing","unstructured":"Jianing Sun and Yingxue Zhang. 2019. Multi-graph convolutional neural networks for representation learning in recommendation. In IEEE ICDM."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2002.10062"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00120"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205321"},{"key":"e_1_3_2_1_77_1","volume-title":"International Conference on Exascale Applications and Software. Springer, 39--56","author":"Tramm John R","year":"2014","unstructured":"John R Tramm, Andrew R Siegel, Benoit Forget, and Colin Josey. 2014a. Performance analysis of a reduced data movement algorithm for neutron cross section data in monte carlo simulations. In International Conference on Exascale Applications and Software. Springer, 39--56."},{"key":"e_1_3_2_1_78_1","volume-title":"XSBench-the development and verification of a performance abstraction for Monte Carlo reactor analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR)","author":"Tramm John R","year":"2014","unstructured":"John R Tramm, Andrew R Siegel, Tanzima Islam, and Martin Schulz. 2014b. XSBench-the development and verification of a performance abstraction for Monte Carlo reactor analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR) (2014)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2010.38"},{"key":"e_1_3_2_1_80_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Petar Velivc","year":"2017","unstructured":"Petar Velivc kovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3418463"},{"key":"e_1_3_2_1_82_1","volume-title":"A survey on heterogeneous graph embedding: methods, techniques, applications and sources. arXiv preprint arXiv:2011.14867","author":"Wang Xiao","year":"2020","unstructured":"Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye, and Philip S Yu. 2020. A survey on heterogeneous graph embedding: methods, techniques, applications and sources. arXiv preprint arXiv:2011.14867 (2020)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/2633046"},{"key":"e_1_3_2_1_84_1","volume-title":"Artemis: Automatic Runtime Tuning of Parallel Execution Parameters Using Machine Learning. In International Conference on High Performance Computing. Springer, 453--472","author":"Wood Chad","year":"2021","unstructured":"Chad Wood, Giorgis Georgakoudis, David Beckingsale, David Poliakoff, Alfredo Gimenez, Kevin Huck, Allen Malony, and Todd Gamblin. 2021. Artemis: Automatic Runtime Tuning of Parallel Execution Parameters Using Machine Learning. In International Conference on High Performance Computing. Springer, 453--472."},{"key":"e_1_3_2_1_85_1","volume-title":"Autotuning PolyBench Benchmarks with LLVM Clang\/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version). arXiv preprint arXiv:2104.13242","author":"Wu Xingfu","year":"2021","unstructured":"Xingfu Wu, Michael Kruse, Prasanna Balaprakash, Hal Finkel, Paul Hovland, Valerie Taylor, and Mary Hall. 2021. Autotuning PolyBench Benchmarks with LLVM Clang\/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version). arXiv preprint arXiv:2104.13242 (2021)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_87_1","unstructured":"Tomofumi Yuki and Louis-No\u00ebl Pouchet. 2015. Polybench 4.0."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276491"}],"event":{"name":"HPDC '23: The 32nd International Symposium on High-Performance Parallel and Distributed Computing","location":"Orlando FL USA","acronym":"HPDC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592984","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588195.3592984","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588195.3592984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:25Z","timestamp":1750178845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":87,"alternative-id":["10.1145\/3588195.3592984","10.1145\/3588195"],"URL":"https:\/\/doi.org\/10.1145\/3588195.3592984","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}