{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:00:10Z","timestamp":1784905210628,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Suzhou Science and Technology Development Planning Programme","award":["No. ZXL2023176"],"award-info":[{"award-number":["No. ZXL2023176"]}]},{"name":"Key Technology R&D Program of Ningbo","award":["No. 2022Z149"],"award-info":[{"award-number":["No. 2022Z149"]}]},{"name":"Jiangsu Province Engineering Research Centre of Data Science and Cognitive Computation at XJTLU and SIP AI innovation platform","award":["No. YZCXPT2022103"],"award-info":[{"award-number":["No. YZCXPT2022103"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673069","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"179-188","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SyncMalloc: A Synchronized Host-Device Co-Management System for GPU Dynamic Memory Allocation across All Scales"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-9411","authenticated-orcid":false,"given":"Jiajian","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China and The University of Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9618-8965","authenticated-orcid":false,"given":"Fangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2855-7259","authenticated-orcid":false,"given":"Hai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Bejing University of Posts and Telecommunications, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8686-9513","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Liverpool, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6964-8143","authenticated-orcid":false,"given":"Genlang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer and Data Engineering, NingboTech University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0918-4606","authenticated-orcid":false,"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"GPU Technology Conference, Vol.\u00a0152","author":"Adinetz V","year":"2014","unstructured":"Andrew\u00a0V Adinetz and Dirk Pleiter. 2014. Halloc: a high-throughput dynamic memory allocator for GPGPU architectures. In GPU Technology Conference, Vol.\u00a0152."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/356989.357000"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03460-2"},{"key":"e_1_3_2_1_4_1","volume-title":"Efficient and Scalable Graph Pattern Mining on GPUs. In USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 857\u2013877","author":"Chen Xuhao","year":"2022","unstructured":"Xuhao Chen and Arvind. 2022. Efficient and Scalable Graph Pattern Mining on GPUs. In USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 857\u2013877."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3218508"},{"key":"e_1_3_2_1_6_1","volume-title":"US-Byte: An Efficient Communication Framework for Scheduling Unequal-Sized Tensor Blocks in Distributed Deep Learning","author":"Gao Yunqi","year":"2023","unstructured":"Yunqi Gao, Bing Hu, Mahdi\u00a0Boloursaz Mashhadi, A-Long Jin, Pei Xiao, and Chunming Wu. 2023. US-Byte: An Efficient Communication Framework for Scheduling Unequal-Sized Tensor Blocks in Distributed Deep Learning. IEEE Transactions on Parallel and Distributed Systems (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295727"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2010.206"},{"key":"e_1_3_2_1_9_1","volume-title":"Occamy: Memory-efficient GPU Compiler for DNN Inference. In ACM\/IEEE Design Automation Conference. IEEE, 1\u20136.","author":"Lee Jaeho","year":"2023","unstructured":"Jaeho Lee, Shinnung Jeong, Seungbin Song, Kunwoo Kim, Heelim Choi, Youngsok Kim, and Hanjun Kim. 2023. Occamy: Memory-efficient GPU Compiler for DNN Inference. In ACM\/IEEE Design Automation Conference. IEEE, 1\u20136."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605632"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3060393"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622837"},{"key":"e_1_3_2_1_13_1","volume-title":"Gallatin: A General-Purpose GPU Memory Manager. In ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming. 364\u2013376","author":"Mccoy Hunter","year":"2024","unstructured":"Hunter Mccoy and Prashant Pandey. 2024. Gallatin: A General-Purpose GPU Memory Manager. In ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming. 364\u2013376."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607059"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532387"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593703"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588768.2576781"},{"key":"e_1_3_2_1_18_1","volume-title":"DynaSOAr: A Parallel Memory Allocator for Object-Oriented Programming on GPUs with Efficient Memory Access. In European Conference on Object-Oriented Programming, Vol.\u00a0134","author":"Springer Matthias","year":"2019","unstructured":"Matthias Springer and Hidehiko Masuhara. 2019. DynaSOAr: A Parallel Memory Allocator for Object-Oriented Programming on GPUs with Efficient Memory Access. In European Conference on Object-Oriented Programming, Vol.\u00a0134. 17:1\u201317:37."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315573.3329979"},{"key":"e_1_3_2_1_20_1","volume-title":"Innovative Parallel Computing","author":"Steinberger Markus","unstructured":"Markus Steinberger, Michael Kenzel, Bernhard Kainz, and Dieter Schmalstieg. 2012. ScatterAlloc: Massively parallel dynamic memory allocation for the GPU. In Innovative Parallel Computing. IEEE, 1\u201310."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Marek Vinkler and Vlastimil Havran. 2015. Register efficient dynamic memory allocator for GPUs. In Computer Graphics Forum Vol.\u00a034. 143\u2013154.","DOI":"10.1111\/cgf.12666"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3221821"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458535"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392742"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00063"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 219\u2013233","author":"Winter Martin","year":"2021","unstructured":"Martin Winter, Mathias Parger, Daniel Mlakar, and Markus Steinberger. 2021. Are dynamic memory managers on gpus slow? a survey and benchmarks. In Proceedings of ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 219\u2013233."},{"key":"e_1_3_2_1_27_1","volume-title":"LightTraffic: On Optimizing CPU-GPU Data Traffic for Efficient Large-scale Random Walks. In International Conference on Data Engineering. IEEE, 882\u2013895","author":"Xing Yipeng","year":"2023","unstructured":"Yipeng Xing, Yongkun Li, Zhiqiang Wang, Yinlong Xu, and John\u00a0CS Lui. 2023. LightTraffic: On Optimizing CPU-GPU Data Traffic for Efficient Large-scale Random Walks. In International Conference on Data Engineering. IEEE, 882\u2013895."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3199998"},{"key":"e_1_3_2_1_29_1","volume-title":"Characterizing Massively Parallel Polymorphism. In IEEE International Symposium on Performance Analysis of Systems and Software. IEEE, 205\u2013216","author":"Zhang Mengchi","year":"2021","unstructured":"Mengchi Zhang, Ahmad Alawneh, and Timothy\u00a0G Rogers. 2021. Characterizing Massively Parallel Polymorphism. In IEEE International Symposium on Performance Analysis of Systems and Software. IEEE, 205\u2013216."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605585"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673069","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:31:58Z","timestamp":1758648718000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":30,"alternative-id":["10.1145\/3673038.3673069","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673069","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}