{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:53:06Z","timestamp":1771951986711,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSERC","award":["GPIN-06516"],"award-info":[{"award-number":["GPIN-06516"]}]},{"name":"NSFRC DG","award":["GECR00303"],"award-info":[{"award-number":["GECR00303"]}]},{"name":"Canada Research Chairs program,"},{"name":"Ontario Early Researcher Award"},{"name":"NSFRC Discovery","award":["RGPIN-2023-04897"],"award-info":[{"award-number":["RGPIN-2023-04897"]}]},{"name":"NSERC DGECR","award":["DGECR-2023-00133"],"award-info":[{"award-number":["DGECR-2023-00133"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607097","type":"proceedings-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T21:47:06Z","timestamp":1699998426000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2968-5176","authenticated-orcid":false,"given":"Kazem","family":"Cheshmi","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, McMaster University, Hamilton, Canada"},{"name":"McMaster University, Hamilton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7646-4766","authenticated-orcid":false,"given":"Michelle","family":"Strout","sequence":"additional","affiliation":[{"name":"Computer Science, University of Arizona, Tucson, United States of America"},{"name":"Hewlett Packard Enterprise (HPE), Tucson, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2719-8788","authenticated-orcid":false,"given":"Maryam","family":"Mehri Dehnavi","sequence":"additional","affiliation":[{"name":"Computer Science, University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_1_1_1","series-title":"Journal of Physics: Conference Series","volume-title":"Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects","author":"Agullo Emmanuel","year":"2037","unstructured":"Emmanuel Agullo , Jim Demmel , Jack Dongarra , Bilel Hadri , Jakub Kurzak , Julien Langou , Hatem Ltaief , Piotr Luszczek , and Stanimire Tomov . 2009. Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects . In Journal of Physics: Conference Series , Vol. 180 . IOP Publishing , 01 2037 . Emmanuel Agullo, Jim Demmel, Jack Dongarra, Bilel Hadri, Jakub Kurzak, Julien Langou, Hatem Ltaief, Piotr Luszczek, and Stanimire Tomov. 2009. Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects. In Journal of Physics: Conference Series, Vol. 180. IOP Publishing, 012037."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580020"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.69"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827599356900"},{"key":"e_1_3_2_1_5_1","volume-title":"Convex optimization","author":"Boyd Stephen","unstructured":"Stephen Boyd , Stephen P Boyd , and Lieven Vandenberghe . 2004. Convex optimization . Cambridge university press . Stephen Boyd, Stephen P Boyd, and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571927"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126936"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00065"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392486"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508439"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/140968896"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Timothy A Davis. 2006. Direct methods for sparse linear systems. SIAM.  Timothy A Davis. 2006. Direct methods for sparse linear systems. SIAM.","DOI":"10.1137\/1.9780898718881"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMAG.2010.2081662"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532386"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2013.06.001"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494992"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/130930376"},{"key":"e_1_3_2_1_21_1","volume-title":"Computer architecture: a quantitative approach","author":"Hennessy John L","unstructured":"John L Hennessy and David A Patterson . 2017. Computer architecture: a quantitative approach . Elsevier . John L Hennessy and David A Patterson. 2017. Computer architecture: a quantitative approach. Elsevier."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(01)00141-7"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1137\/18M1176865"},{"key":"e_1_3_2_1_24_1","volume-title":"Communication-avoiding Krylov subspace methods","author":"Hoemmen Mark","unstructured":"Mark Hoemmen . 2010. Communication-avoiding Krylov subspace methods . University of California , Berkeley. Mark Hoemmen. 2010. Communication-avoiding Krylov subspace methods. University of California, Berkeley."},{"key":"e_1_3_2_1_25_1","volume-title":"A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices","author":"Karypis George","year":"1998","unstructured":"George Karypis and Vipin Kumar . 1998. A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices . University of Minnesota, Department of Computer Science and Engineering, Army HPC Research Center , Minneapolis, MN ( 1998 ). George Karypis and Vipin Kumar. 1998. A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices. University of Minnesota, Department of Computer Science and Engineering, Army HPC Research Center, Minneapolis, MN (1998)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC '20). USENIX Association.","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey , Jason Anderson , Zhuo Zhen , Pierre Riteau , Paul Ruth , Dan Stanzione , Mert Cevik , Jacob Colleran , Haryadi S. Gunawi , Cody Hammock , Joe Mambretti , Alexander Barnes , Fran\u00e7ois Halbach , Alex Rocha , and Joe Stubbs . 2020 . Lessons Learned from the Chameleon Testbed . In Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC '20). USENIX Association. Kate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau, Paul Ruth, Dan Stanzione, Mert Cevik, Jacob Colleran, Haryadi S. Gunawi, Cody Hammock, Joe Mambretti, Alexander Barnes, Fran\u00e7ois Halbach, Alex Rocha, and Joe Stubbs. 2020. Lessons Learned from the Chameleon Testbed. In Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC '20). USENIX Association."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(78)90098-0"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462181"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1089014.1089017"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMAG.2013.2244861"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314646"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Yousef Saad. 2003. Iterative methods for sparse linear systems. SIAM.  Yousef Saad. 2003. Iterative methods for sparse linear systems. SIAM.","DOI":"10.1137\/1.9780898718003"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60222-4_115"},{"key":"e_1_3_2_1_34_1","unstructured":"Intel Software. 2018. OpenMP potential gain definition in intel VTune. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/documentation\/vtune-help\/top\/reference\/cpu-metrics-reference\/openmp-potential-gain.html  Intel Software. 2018. OpenMP potential gain definition in intel VTune. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/documentation\/vtune-help\/top\/reference\/cpu-metrics-reference\/openmp-potential-gain.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225131"},{"key":"e_1_3_2_1_36_1","volume-title":"OSQP: An operator splitting solver for quadratic programs. Mathematical Programming Computation","author":"Stellato Bartolomeo","year":"2020","unstructured":"Bartolomeo Stellato , Goran Banjac , Paul Goulart , Alberto Bemporad , and Stephen Boyd . 2020 . OSQP: An operator splitting solver for quadratic programs. Mathematical Programming Computation (2020), 1--36. Bartolomeo Stellato, Goran Banjac, Paul Goulart, Alberto Bemporad, and Stephen Boyd. 2020. OSQP: An operator splitting solver for quadratic programs. Mathematical Programming Computation (2020), 1--36."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781142"},{"key":"e_1_3_2_1_38_1","volume-title":"International Workshop on Languages and Compilers for Parallel Computing. Springer, 90--110","author":"Strout Michelle Mills","year":"2002","unstructured":"Michelle Mills Strout , Larry Carter , Jeanne Ferrante , Jonathan Freeman , and Barbara Kreaseck . 2002 . Combining performance aspects of irregular gauss-seidel via sparse tiling . In International Workshop on Languages and Compilers for Parallel Computing. Springer, 90--110 . Michelle Mills Strout, Larry Carter, Jeanne Ferrante, Jonathan Freeman, and Barbara Kreaseck. 2002. Combining performance aspects of irregular gauss-seidel via sparse tiling. In International Workshop on Languages and Compilers for Parallel Computing. Springer, 90--110."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041294"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2857721"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.118"},{"key":"e_1_3_2_1_42_1","volume-title":"Tools for High Performance Computing","author":"Terpstra Dan","year":"2009","unstructured":"Dan Terpstra , Heike Jagode , Haihang You , and Jack Dongarra . 2010. Collecting performance data with PAPI-C . In Tools for High Performance Computing 2009 . Springer , 157--173. Dan Terpstra, Heike Jagode, Haihang You, and Jack Dongarra. 2010. Collecting performance data with PAPI-C. In Tools for High Performance Computing 2009. Springer, 157--173."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2014.06.006"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3014904.3014959"},{"key":"e_1_3_2_1_45_1","unstructured":"Richard Vuduc Shoaib Kamil Jen Hsu Rajesh Nishtala James W Demmel and Katherine A Yelick. 2002. Automatic performance tuning and analysis of sparse triangular solve. ICS.  Richard Vuduc Shoaib Kamil Jen Hsu Rajesh Nishtala James W Demmel and Katherine A Yelick. 2002. Automatic performance tuning and analysis of sparse triangular solve. ICS."},{"key":"e_1_3_2_1_46_1","volume-title":"High-Performance Computing on the Intel\u00ae Xeon Phi\u2122","author":"Wang Endong","unstructured":"Endong Wang , Qing Zhang , Bo Shen , Guangyong Zhang , Xiaowei Lu , Qing Wu , and Yajuan Wang . 2014. Intel math kernel library . In High-Performance Computing on the Intel\u00ae Xeon Phi\u2122 . Springer , 167--188. Endong Wang, Qing Zhang, Bo Shen, Guangyong Zhang, Xiaowei Lu, Qing Wu, and Yajuan Wang. 2014. Intel math kernel library. In High-Performance Computing on the Intel\u00ae Xeon Phi\u2122. Springer, 167--188."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591302"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368474.3368486"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00121"},{"key":"e_1_3_2_1_51_1","unstructured":"Tong Zhou Ruiqin Tian Rizwan A Ashraf Roberto Gioiosa Gokcen Kestor and Vivek Sarkar. 2022. ReACT: Redundancy-Aware Code Generation for Tensor Expressions. (2022).  Tong Zhou Ruiqin Tian Rizwan A Ashraf Roberto Gioiosa Gokcen Kestor and Vivek Sarkar. 2022. ReACT: Redundancy-Aware Code Generation for Tensor Expressions. (2022)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079091"},{"key":"e_1_3_2_1_53_1","volume-title":"d.]. Intel VTune Amplifier","author":"Zone Intel Developer","year":"2017","unstructured":"Intel Developer Zone . [n. d.]. Intel VTune Amplifier , 2017 . Documentation at the URL : https:\/\/software.intel.com\/en-us\/intel-vtune-amplifierxe-support\/documentation ([n. d.]). Intel Developer Zone. [n. d.]. Intel VTune Amplifier, 2017. Documentation at the URL: https:\/\/software.intel.com\/en-us\/intel-vtune-amplifierxe-support\/documentation ([n. d.])."}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607097","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:23Z","timestamp":1750178183000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":51,"alternative-id":["10.1145\/3581784.3607097","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607097","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}