{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T11:39:14Z","timestamp":1793101154230,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-18-3-0007"],"award-info":[{"award-number":["HR0011-18-3-0007"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,25]]},"DOI":"10.1145\/3572848.3577434","type":"proceedings-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T11:02:30Z","timestamp":1676977350000},"page":"79-91","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A Programming Model for GPU Load Balancing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1616-6817","authenticated-orcid":false,"given":"Muhammad","family":"Osama","sequence":"first","affiliation":[{"name":"University of California, Davis, Davis, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9199","authenticated-orcid":false,"given":"Serban D.","family":"Porumbescu","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6582-8237","authenticated-orcid":false,"given":"John D.","family":"Owens","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"e_1_3_2_1_2_1","unstructured":"Advanced Micro Devices Inc. 2022. HIP Programming Guide v5.2. (June 2022). https:\/\/docs.amd.com\/bundle\/HIP-Programming-Guide-v5.2\/page\/Introduction.html"},{"key":"e_1_3_2_1_3_1","unstructured":"Sean Baxter. 2013--2016. Moderngpu: Patterns and Behaviors for GPU Computing. (2013--2016). http:\/\/moderngpu.github.io\/moderngpu."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370321"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2330597"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2312\/EGGH\/EGGH08\/057-064"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545056"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.98"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.45"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3017994"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916333"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/chromium.googlesource.com\/chromium\/src\/+\/HEAD\/styleguide\/c++\/c++.md","author":"Chromium","year":"2023","unstructured":"Google. 2023. Chromium C++ style guide. (2023). https:\/\/chromium.googlesource.com\/chromium\/src\/+\/HEAD\/styleguide\/c++\/c++.md"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547581"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304621"},{"key":"e_1_3_2_1_18_1","volume-title":"Cooperative Groups: Flexible CUDA Thread Programming.","author":"Harris Mark","year":"2017","unstructured":"Mark Harris and Kyrylo Perelygin. 2017. Cooperative Groups: Flexible CUDA Thread Programming. (2017). https:\/\/developer.nvidia.com\/blog\/cooperative-groups\/"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.75"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145832"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00023"},{"key":"e_1_3_2_1_23_1","unstructured":"NVIDIA Corporation. 2007--2022. CUDA C++ Programming Guide. (Dec. 2007--2022). https:\/\/docs.nvidia.com\/cuda\/ PG-02829-001_v12.0."},{"key":"e_1_3_2_1_24_1","volume-title":"CUB: Cooperative primitives for CUDA C++.","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. 2023. CUB: Cooperative primitives for CUDA C++. (2023). https:\/\/nvlabs.github.io\/cub\/."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7465053"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079086"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.255"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.2312\/EGGH\/HPG10\/029-037"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3108140"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466795"},{"key":"e_1_3_2_1_32_1","volume-title":"Persistent Kernels for Iterative Memory-bound GPU Applications. CoRR (April","author":"Zhang Lingqi","year":"2022","unstructured":"Lingqi Zhang, Mohamed Wahib, Peng Chen, Jintao Meng, Xiao Wang, and Satoshi Matsuoka. 2022. Persistent Kernels for Iterative Memory-bound GPU Applications. CoRR (April 2022). arXiv:2204.02064"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.004"}],"event":{"name":"PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Montreal QC Canada","acronym":"PPoPP '23","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577434","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577434","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:08:09Z","timestamp":1750169289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":31,"alternative-id":["10.1145\/3572848.3577434","10.1145\/3572848"],"URL":"https:\/\/doi.org\/10.1145\/3572848.3577434","relation":{},"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"2023-02-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}