{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T21:10:02Z","timestamp":1755983402035,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"European Research Council","doi-asserted-by":"publisher","award":["949587"],"award-info":[{"award-number":["949587"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3642961.3643799","type":"proceedings-article","created":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T12:03:32Z","timestamp":1712232212000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GPU-Initiated Resource Allocation for Irregular Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0384-6330","authenticated-orcid":false,"given":"Ilyas","family":"Turimbetov","sequence":"first","affiliation":[{"name":"Ko\u00e7 University, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6166-4252","authenticated-orcid":false,"given":"Muhammad Aditya","family":"Sasongko","sequence":"additional","affiliation":[{"name":"Ko\u00e7 University, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2351-0770","authenticated-orcid":false,"given":"Didem","family":"Unat","sequence":"additional","affiliation":[{"name":"Ko\u00e7 University, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,4]]},"reference":[{"volume-title":"ComScribe: Identifying Intra-node GPU Communication","author":"Akhtar Palwisha","key":"e_1_3_2_1_1_1","unstructured":"Palwisha Akhtar, Erhan Tezcan, Fareed\u00a0Mohammad Qararyah, and Didem Unat. 2021. ComScribe: Identifying Intra-node GPU Communication. In Benchmarking, Measuring, and Optimizing, Felix Wolf and Wanling Gao (Eds.). Springer International Publishing, Cham, 157\u2013174."},{"key":"e_1_3_2_1_2_1","unstructured":"AMD. 2020. \"AMD Instinct MI100\" Instruction Set Architecture Reference Guide. AMD."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573485"},{"volume-title":"Proceedings of the Workshop on Secure and Dependable Middleware for Cloud Monitoring and Management (Montreal","author":"Beernaert Leander","key":"e_1_3_2_1_4_1","unstructured":"Leander Beernaert, Miguel Matos, Ricardo Vila\u00e7a, and Rui Oliveira. [n. d.]. Automatic Elasticity in OpenStack. In Proceedings of the Workshop on Secure and Dependable Middleware for Cloud Monitoring and Management (Montreal, Quebec, Canada) (SDMCMM \u201912). ACM, New York, NY, USA, Article 2, 6\u00a0pages."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018756"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3155284.3018756"},{"key":"e_1_3_2_1_7_1","volume-title":"SPIN: Seamless Operating System Integration of Peer-to-Peer DMA Between SSDs and GPUs. In 2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Bergman Shai","year":"2017","unstructured":"Shai Bergman, Tanya Brokhman, Tzachi Cohen, and Mark Silberstein. 2017. SPIN: Seamless Operating System Integration of Peer-to-Peer DMA Between SSDs and GPUs. In 2017 USENIX Annual Technical Conference (USENIX ATC 17). 167\u2013179."},{"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\/SC41404.2022.00055"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.37"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Taylor Groves Ben Brock Yuxin Chen Khaled\u00a0Z. Ibrahim Lenny Oliker Nicholas\u00a0J. Wright Samuel Williams and Katherine Yelick. [n. d.]. Performance Trade-offs in GPU Communication: A Study of Host and Device-initiated Approaches. In 2020 IEEE\/ACM Performance Modeling Benchmarking and Simulation of High Performance Computer Systems. 126\u2013137.","DOI":"10.1109\/PMBS51919.2020.00016"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Kshitij Gupta Jeff\u00a0A. Stuart and John\u00a0D. Owens. 2012. A study of Persistent Threads style GPU programming for GPGPU workloads. In 2012 Innovative Parallel Computing (InPar). 1\u201314. https:\/\/doi.org\/10.1109\/InPar.2012.6339596","DOI":"10.1109\/InPar.2012.6339596"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593713"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437715"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037707"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2553081"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2963098"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661250"},{"key":"e_1_3_2_1_20_1","volume-title":"GPU-to-CPU Callbacks. In Proceedings of the 2010 Conference on Parallel Processing","author":"Stuart A.","year":"2010","unstructured":"Jeff\u00a0A. Stuart, Michael Cox, and John\u00a0D. Owens. 2010. GPU-to-CPU Callbacks. In Proceedings of the 2010 Conference on Parallel Processing (Ischia, Italy) (Euro-Par 2010). Springer-Verlag, Berlin, Heidelberg, 365\u2013372."},{"key":"e_1_3_2_1_21_1","volume-title":"Evaluating Performance Tradeoffs on the Radeon Open Compute Platform. In 2018 IEEE Int\u2019l Symposium on Performance Analysis of Systems and Software (ISPASS). 209\u2013218","author":"Sun Yifan","year":"2018","unstructured":"Yifan Sun, Saoni Mukherjee, Trinayan Baruah, Shi Dong, Julian Gutierrez, Prannoy Mohan, and David Kaeli. 2018. Evaluating Performance Tradeoffs on the Radeon Open Compute Platform. In 2018 IEEE Int\u2019l Symposium on Performance Analysis of Systems and Software (ISPASS). 209\u2013218."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2907912"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1921479.1921485"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337801.3337819"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00075"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3016078.2851145"},{"key":"e_1_3_2_1_27_1","volume-title":"CERES: Container-Based Elastic Resource Management System for Mixed Workloads. In 50th International Conference on Parallel Processing","author":"Yu Jinyu","year":"2021","unstructured":"Jinyu Yu, Dan Feng, Wei Tong, Pengze Lv, and Yufei Xiong. 2021. CERES: Container-Based Elastic Resource Management System for Mixed Workloads. In 50th International Conference on Parallel Processing (Lemont, IL, USA) (ICPP 2021). ACM, New York, NY, USA, Article 13, 10\u00a0pages."},{"key":"e_1_3_2_1_28_1","unstructured":"Lingqi Zhang Mohamed Wahib Peng Chen Jintao Meng Xiao Wang and Satoshi Matsuoka. 2022. Persistent Kernels for Iterative Memory-bound GPU Applications. https:\/\/arxiv.org\/abs\/2204.02064"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00057"}],"event":{"name":"PPoPP '24: The 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Edinburgh United Kingdom","acronym":"PPoPP '24"},"container-title":["Proceedings of the 3rd International Workshop on Extreme Heterogeneity Solutions"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642961.3643799","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3642961.3643799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T20:36:10Z","timestamp":1755981370000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642961.3643799"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":29,"alternative-id":["10.1145\/3642961.3643799","10.1145\/3642961"],"URL":"https:\/\/doi.org\/10.1145\/3642961.3643799","relation":{},"subject":[],"published":{"date-parts":[[2024,3,2]]},"assertion":[{"value":"2024-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}