{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:12:56Z","timestamp":1780708376006,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong RGC Research Impact Fund","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872310"],"award-info":[{"award-number":["61872310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JSPS KAKENHI","award":["21H03424"],"award-info":[{"award-number":["21H03424"]}]},{"name":"General Research Fund","award":["152221\/19E, 152203\/20E, and 152244\/21E"],"award-info":[{"award-number":["152221\/19E, 152203\/20E, and 152244\/21E"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2021B0101400003"],"award-info":[{"award-number":["2021B0101400003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"DOI":"10.1145\/3502181.3531462","type":"proceedings-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T22:14:30Z","timestamp":1656022470000},"page":"253-264","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Hare"],"prefix":"10.1145","author":[{"given":"Fahao","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Aizu, Aizu-wakamatsu, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Aizu, Aizu-wakamatsu, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celimuge","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electro-Communications, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University & The Hong Kong Polytechnic University Shenzhen Research Institute, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,6,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2016. Wmt16 dataset. http:\/\/www.statmt.org\/wmt16\/  2016. Wmt16 dataset. http:\/\/www.statmt.org\/wmt16\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2019. CUDA MakeUppercaseMulti-MakeUppercaseProcess MakeUppercaseService. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA_Multi_Process_Service_Overview.pdf  2019. CUDA MakeUppercaseMulti-MakeUppercaseProcess MakeUppercaseService. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA_Multi_Process_Service_Overview.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"2019. Google Cluster Traces. http:\/\/github.com\/google\/cluster-data  2019. Google Cluster Traces. http:\/\/github.com\/google\/cluster-data"},{"key":"e_1_3_2_1_4_1","unstructured":"2020. Common voice dataset. https:\/\/voice.mozilla.org\/  2020. Common voice dataset. https:\/\/voice.mozilla.org\/"},{"key":"e_1_3_2_1_5_1","unstructured":"2020. gRPC. https:\/\/grpc.io  2020. gRPC. https:\/\/grpc.io"},{"key":"e_1_3_2_1_6_1","unstructured":"2021. Apache Hadoop. http:\/\/hadoop.apache.org\/.  2021. Apache Hadoop. http:\/\/hadoop.apache.org\/."},{"key":"e_1_3_2_1_7_1","unstructured":"2021. Technical Report. https:\/\/www.dropbox.com\/s\/vkdip7xbhh5ca06\/Technical_report.pdf?dl=0  2021. Technical Report. https:\/\/www.dropbox.com\/s\/vkdip7xbhh5ca06\/Technical_report.pdf?dl=0"},{"key":"e_1_3_2_1_8_1","volume-title":"PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Bai Zhihao","year":"2020","unstructured":"Zhihao Bai , Zhen Zhang , Yibo Zhu , and Xin Jin . 2020 . PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20) . 499--514. Zhihao Bai, Zhen Zhang, Yibo Zhu, and Xin Jin. 2020. PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 499--514."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3125565"},{"key":"e_1_3_2_1_11_1","volume-title":"6th International Conference on Learning Representations, ICLR Conference Track Proceedings. https:\/\/openreview.net\/forum?id=rytstxWAW","author":"Chen Jie","year":"2018","unstructured":"Jie Chen , Tengfei Ma , and Cao Xiao . 2018 . FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling . In 6th International Conference on Learning Representations, ICLR Conference Track Proceedings. https:\/\/openreview.net\/forum?id=rytstxWAW Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. In 6th International Conference on Learning Representations, ICLR Conference Track Proceedings. https:\/\/openreview.net\/forum?id=rytstxWAW"},{"key":"e_1_3_2_1_12_1","volume-title":"NIPS Workshop on Machine Learning Systems (LearningSys)","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen , Mu Li , Yutian Li , Min Lin , Naiyan Wang , Minjie Wang , Tianjun Xiao , Bing Xu , Chiyuan Zhang , and Zheng Zhang . 2016 . Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems . NIPS Workshop on Machine Learning Systems (LearningSys) (2016). Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2016. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. NIPS Workshop on Machine Learning Systems (LearningSys) (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Chilimbi Trishul","year":"2014","unstructured":"Trishul Chilimbi , Yutaka Suzue , Johnson Apacible , and Karthik Kalyanaraman . 2014 . Project adam: Building an efficient and scalable deep learning training system . In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14) . 571--582. Trishul Chilimbi, Yutaka Suzue, Johnson Apacible, and Karthik Kalyanaraman. 2014. Project adam: Building an efficient and scalable deep learning training system. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). 571--582."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9195"},{"key":"e_1_3_2_1_15_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3318027"},{"key":"e_1_3_2_1_17_1","unstructured":"Michael R Garey and David S Johnson. 1979. Computers and intractability: A Guide to the theory of np-completeness. (1979).  Michael R Garey and David S Johnson. 1979. Computers and intractability: A Guide to the theory of np-completeness. (1979)."},{"key":"e_1_3_2_1_18_1","unstructured":"Andrew Gibiansky. 2017. Bringing HPC techniques to deep learning. https:\/\/andrew.gibiansky.com\/blog\/machine-learning\/baidu-allreduce\/  Andrew Gibiansky. 2017. Bringing HPC techniques to deep learning. https:\/\/andrew.gibiansky.com\/blog\/machine-learning\/baidu-allreduce\/"},{"key":"e_1_3_2_1_19_1","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu , Mosharaf Chowdhury , Kang G Shin , Yibo Zhu , Myeongjae Jeon , Junjie Qian , Hongqiang Liu , and Chuanxiong Guo . 2019 . Tiresias: A GPU cluster manager for distributed deep learning . In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19) . 485--500. Juncheng Gu, Mosharaf Chowdhury, Kang G Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU cluster manager for distributed deep learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19) . 485--500."},{"key":"e_1_3_2_1_20_1","unstructured":"William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Neural Information Processing Systems (NIPS). 1024--1034.  William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Neural Information Processing Systems (NIPS). 1024--1034."},{"key":"e_1_3_2_1_21_1","volume-title":"et almbox","author":"Hannun Awni","year":"2014","unstructured":"Awni Hannun , Carl Case , Jared Casper , Bryan Catanzaro , Greg Diamos , Erich Elsen , Ryan Prenger , Sanjeev Satheesh , Shubho Sengupta , Adam Coates , et almbox . 2014 . Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, et almbox. 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","unstructured":"Alex Krizhevsky Geoffrey Hinton etal 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387547"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_1_26_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan , Arjun Balasubramanian , Arjun Singhvi , Shivaram Venkataraman , Aditya Akella , Amar Phanishayee , and Shuchi Chawla . 2020 . Themis: Fair and efficient GPU cluster scheduling . In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20) . 289--304. Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and efficient GPU cluster scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 289--304."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_29_1","volume-title":"Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Narayanan Deepak","year":"2020","unstructured":"Deepak Narayanan , Keshav Santhanam , Fiodar Kazhamiaka , Amar Phanishayee , and Matei Zaharia . 2020 . Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20) . 481--498. Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka, Amar Phanishayee, and Matei Zaharia. 2020. Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 481--498."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_32_1","volume-title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Qiao Aurick","year":"2021","unstructured":"Aurick Qiao , Sang Keun Choe , Suhas Jayaram Subramanya , Willie Neiswanger , Qirong Ho , Hao Zhang , Gregory R Ganger , and Eric P Xing . 2021 . Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21) . Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing. 2021. Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581271"},{"key":"e_1_3_2_1_34_1","unstructured":"Pranav Rajpurkar Jian Zhang Konstantin Lopyrev and Percy Liang. 2016. SQuAD: 100 000  Pranav Rajpurkar Jian Zhang Konstantin Lopyrev and Percy Liang. 2016. SQuAD: 100 000"},{"key":"e_1_3_2_1_35_1","volume-title":"Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383--2392","author":"Questions","unstructured":"Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383--2392 . https:\/\/www.aclweb.org\/anthology\/D16--1264 Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383--2392. https:\/\/www.aclweb.org\/anthology\/D16--1264"},{"key":"e_1_3_2_1_36_1","volume-title":"Collective classification in network data. AI magazine","author":"Sen Prithviraj","year":"2008","unstructured":"Prithviraj Sen , Galileo Namata , Mustafa Bilgic , Lise Getoor , Brian Galligher , and Tina Eliassi-Rad . 2008. Collective classification in network data. AI magazine , Vol. 29 , 3 ( 2008 ), 93--93. Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine, Vol. 29, 3 (2008), 93--93."},{"key":"e_1_3_2_1_37_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso . 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 ( 2018 ). Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_1_38_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman . 2015 . Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409 .1556 Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_40_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"e_1_3_2_1_42_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao , Romil Bhardwaj , Ramachandran Ramjee , Muthian Sivathanu , Nipun Kwatra , Zhenhua Han , Pratyush Patel , Xuan Peng , Hanyu Zhao , Quanlu Zhang , 2018 . Gandiva: Introspective cluster scheduling for deep learning . In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) . 595--610. Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. 2018. Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 595--610."},{"key":"e_1_3_2_1_43_1","volume-title":"AntMan: Dynamic Scaling on GPU Clusters for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao , Shiru Ren , Yong Li , Yang Zhang , Pengyang Hou , Zhi Li , Yihui Feng , Wei Lin , and Yangqing Jia . 2020 . AntMan: Dynamic Scaling on GPU Clusters for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20) . 533--548. Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. AntMan: Dynamic Scaling on GPU Clusters for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 533--548."},{"key":"e_1_3_2_1_44_1","volume-title":"Jinliang Wei, Seunghak Lee, Xun Zheng, Pengtao Xie, Abhimanu Kumar, and Yaoliang Yu.","author":"Xing Eric P","year":"2015","unstructured":"Eric P Xing , Qirong Ho , Wei Dai , Jin Kyu Kim , Jinliang Wei, Seunghak Lee, Xun Zheng, Pengtao Xie, Abhimanu Kumar, and Yaoliang Yu. 2015 . Petuum : A new platform for distributed machine learning on big data. IEEE transactions on Big Data , Vol. 1 , 2 (2015), 49--67. Eric P Xing, Qirong Ho, Wei Dai, Jin Kyu Kim, Jinliang Wei, Seunghak Lee, Xun Zheng, Pengtao Xie, Abhimanu Kumar, and Yaoliang Yu. 2015. Petuum: A new platform for distributed machine learning on big data. IEEE transactions on Big Data, Vol. 1, 2 (2015), 49--67."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586244"},{"key":"e_1_3_2_1_46_1","volume-title":"Salus: Fine-grained gpu sharing primitives for deep learning applications. arXiv preprint arXiv:1902.04610","author":"Yu Peifeng","year":"2019","unstructured":"Peifeng Yu and Mosharaf Chowdhury . 2019 . Salus: Fine-grained gpu sharing primitives for deep learning applications. arXiv preprint arXiv:1902.04610 (2019). Peifeng Yu and Mosharaf Chowdhury. 2019. Salus: Fine-grained gpu sharing primitives for deep learning applications. arXiv preprint arXiv:1902.04610 (2019)."},{"key":"e_1_3_2_1_47_1","first-page":"10","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J Franklin , Scott Shenker , Ion Stoica , 2010 . Spark: Cluster computing with working sets . USENIX HotCloud , Vol. 10 , 10 -- 10 (2010), 95. Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, Ion Stoica, et al. 2010. Spark: Cluster computing with working sets. USENIX HotCloud, Vol. 10, 10--10 (2010), 95.","journal-title":"USENIX HotCloud"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3409128"}],"event":{"name":"HPDC '22: The 31st International Symposium on High-Performance Parallel and Distributed Computing","location":"Minneapolis MN USA","acronym":"HPDC '22","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 31st International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502181.3531462","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3502181.3531462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:49Z","timestamp":1750183789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502181.3531462"}},"subtitle":["Exploiting Inter-job and Intra-job Parallelism of Distributed Machine Learning on Heterogeneous GPUs"],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":48,"alternative-id":["10.1145\/3502181.3531462","10.1145\/3502181"],"URL":"https:\/\/doi.org\/10.1145\/3502181.3531462","relation":{},"subject":[],"published":{"date-parts":[[2022,6,27]]},"assertion":[{"value":"2022-06-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}