{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T16:38:12Z","timestamp":1786811892303,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2310422"],"award-info":[{"award-number":["CNS-2310422"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2152497"],"award-info":[{"award-number":["CNS-2152497"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2029014"],"award-info":[{"award-number":["CCF-2029014"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2008907"],"award-info":[{"award-number":["CCF-2008907"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFA0701500"],"award-info":[{"award-number":["2018YFA0701500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB44000000"],"award-info":[{"award-number":["XDB44000000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122076"],"award-info":[{"award-number":["62122076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025404"],"award-info":[{"award-number":["62025404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018527","name":"Key Research Program of Frontier Science, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["ZDBS-LY-JSC012"],"award-info":[{"award-number":["ZDBS-LY-JSC012"]}],"id":[{"id":"10.13039\/501100018527","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651381","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"71-85","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["ACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9481-7234","authenticated-orcid":false,"given":"Xiaoyang","family":"Lu","sequence":"first","affiliation":[{"name":"Illinois Institute of Technology, Chicago, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5774-6893","authenticated-orcid":false,"given":"Boyu","family":"Long","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1844","authenticated-orcid":false,"given":"Xiaoming","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0904-6681","authenticated-orcid":false,"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1093-0792","authenticated-orcid":false,"given":"Xian-He","family":"Sun","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"10778","volume-title":"Proceedings of the conference on Design, Automation and Test in Europe-Volume 1","author":"Agarwal Amit","unstructured":"Amit Agarwal, Kaushik Roy, and TN Vijaykumar. Exploring high bandwidth pipelined cache architecture for scaled technology. In Proceedings of the conference on Design, Automation and Test in Europe-Volume 1, page 10778. IEEE Computer Society, 2003."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293901"},{"key":"e_1_3_2_1_3_1","volume-title":"CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO), 14(2):1--25","author":"Balasubramonian Rajeev","year":"2017","unstructured":"Rajeev Balasubramonian, Andrew B Kahng, Naveen Muralimanohar, Ali Shafiee, and Vaishnav Srinivas. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO), 14(2):1--25, 2017."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.52.0078"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.93"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063471"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(96)00009-4"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250790.1250877"},{"key":"e_1_3_2_1_9_1","volume-title":"Cusp: Generic parallel algorithms for sparse matrix and graph computations","author":"Dalton Steven","year":"2014","unstructured":"Steven Dalton, Nathan Bell, Luke Olson, and Michael Garland. Cusp: Generic parallel algorithms for sparse matrix and graph computations, 2014."},{"key":"e_1_3_2_1_10_1","volume-title":"Optimizing sparse matrix---matrix multiplication for the gpu. ACM Transactions on Mathematical Software (TOMS), 41(4):1--20","author":"Dalton Steven","year":"2015","unstructured":"Steven Dalton, Luke Olson, and Nathan Bell. Optimizing sparse matrix---matrix multiplication for the gpu. ACM Transactions on Mathematical Software (TOMS), 41(4):1--20, 2015."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180403"},{"key":"e_1_3_2_1_12_1","volume-title":"The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS), 38(1):1--25","author":"Davis Timothy A","year":"2011","unstructured":"Timothy A Davis and Yifan Hu. The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS), 38(1):1--25, 2011."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00024"},{"key":"e_1_3_2_1_14_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571157"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"Josep Torrellas. SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM. In Proceedings of the 50th Annual International Symposium on Computer Architecture","author":"Gerogiannis Gerasimos","year":"2023","unstructured":"Gerasimos Gerogiannis, Serif Yesil, Damitha Lenadora, Dingyuan Cao, Charith Mendis, and Josep Torrellas. SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM. In Proceedings of the 50th Annual International Symposium on Computer Architecture, pages 1--15, 2023."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00069"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_1_20_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149, 2015."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392751"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"e_1_3_2_1_23_1","volume-title":"Computer Architecture: A Quantitative Approach","author":"Hennessy John L","year":"2019","unstructured":"John L Hennessy and David A Patterson. Computer Architecture: A Quantitative Approach. Elsevier, 2019."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995909"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00017"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/800052.801868"},{"key":"e_1_3_2_1_29_1","first-page":"195","volume-title":"Lockup-free instruction fetch\/prefetch cache organization. In 25 years of the international symposia on Computer architecture (selected papers)","author":"Kroft David","year":"1998","unstructured":"David Kroft. Lockup-free instruction fetch\/prefetch cache organization. In 25 years of the international symposia on Computer architecture (selected papers), pages 195--201, 1998."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304028"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575706"},{"key":"e_1_3_2_1_33_1","first-page":"806","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Liu Baoyuan","year":"2015","unstructured":"Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Pensky. Sparse convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 806--814, 2015."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.47"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00090"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00048"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00068"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071125"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582069"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC57314.2022.10015298"},{"key":"e_1_3_2_1_41_1","volume-title":"GPU Technology Conference","author":"Naumov Maxim","year":"2010","unstructured":"Maxim Naumov, L Chien, Philippe Vandermersch, and Ujval Kapasi. Cusparse library. In GPU Technology Conference, 2010."},{"key":"e_1_3_2_1_42_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson G Azzolini et al. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 2019."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1137\/130908737"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150019.1136501"},{"key":"e_1_3_2_1_47_1","volume-title":"On the all-pairs-shortest-path problem in unweighted undirected graphs. Journal of computer and system sciences, 51(3):400--403","author":"Seidel Raimund","year":"1995","unstructured":"Raimund Seidel. On the all-pairs-shortest-path problem in unweighted undirected graphs. Journal of computer and system sciences, 51(3):400--403, 1995."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2012.2193936"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-022-2911-1"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.227"},{"key":"e_1_3_2_1_53_1","volume-title":"An efficient algorithm for exploiting multiple arithmetic units. IBM Journal of research and Development, 11(1):25--33","author":"Tomasulo Robert M","year":"1967","unstructured":"Robert M Tomasulo. An efficient algorithm for exploiting multiple arithmetic units. IBM Journal of research and Development, 11(1):25--33, 1967."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/223982.224449"},{"key":"e_1_3_2_1_55_1","first-page":"2","article-title":"High-performance computing on the intel xeon phi","volume":"5","author":"Wang Endong","year":"2014","unstructured":"Endong Wang, Qing Zhang, Bo Shen, Guangyong Zhang, Xiaowei Lu, Qing Wu, and Yajuan Wang. High-performance computing on the intel xeon phi. Springer, 5:2, 2014.","journal-title":"Springer"},{"key":"e_1_3_2_1_56_1","volume-title":"Configurable multi-directional systolic array architecture for convolutional neural networks. ACM Transactions on Architecture and Code Optimization (TACO), 18(4):1--24","author":"Xu Rui","year":"2021","unstructured":"Rui Xu, Sheng Ma, Yaohua Wang, Xinhai Chen, and Yang Guo. Configurable multi-directional systolic array architecture for convolutional neural networks. ACM Transactions on Architecture and Code Optimization (TACO), 18(4):1--24, 2021."},{"key":"e_1_3_2_1_57_1","first-page":"421","volume-title":"International Conference on High Performance Computing for Computational Science","author":"Yamazaki Ichitaro","year":"2010","unstructured":"Ichitaro Yamazaki and Xiaoye S Li. On techniques to improve robustness and scalability of a parallel hybrid linear solver. In International Conference on High Performance Computing for Computational Science, pages 421--434. Springer, 2010."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED52811.2021.9502483"},{"key":"e_1_3_2_1_59_1","first-page":"254","volume-title":"SODA","volume":"4","author":"Yuster Raphael","year":"2004","unstructured":"Raphael Yuster and Uri Zwick. Detecting short directed cycles using rectangular matrix multiplication and dynamic programming. In SODA, volume 4, pages 254--260. Citeseer, 2004."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446702"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESSCIRC.2003.1257158"}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651381","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3620666.3651381","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:43Z","timestamp":1750291423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":63,"alternative-id":["10.1145\/3620666.3651381","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651381","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}