{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:32:06Z","timestamp":1790749926441,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,2,10]],"date-time":"2018-02-10T00:00:00Z","timestamp":1518220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2016YFA0602100, 2017YFA0604500"],"award-info":[{"award-number":["2016YFA0602100, 2017YFA0604500"]}]},{"name":"National Natural Science Foundation of China","award":["91530323, 41776010"],"award-info":[{"award-number":["91530323, 41776010"]}]},{"name":"European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie project","award":["752321"],"award-info":[{"award-number":["752321"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,2,10]]},"DOI":"10.1145\/3178487.3178513","type":"proceedings-article","created":{"date-parts":[[2018,2,6]],"date-time":"2018-02-06T13:12:23Z","timestamp":1517922743000},"page":"338-353","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["swSpTRSV"],"prefix":"10.1145","author":[{"given":"Xinliang","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,2,10]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2017. https:\/\/www.top500.org\/. (2017).  2017. https:\/\/www.top500.org\/. (2017)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129053389000056"},{"key":"e_1_3_2_2_3_1","volume-title":"26 PFLOPS Stencil Computations for Atmospheric Modeling on Sunway TaihuLight. In Parallel and Distributed Processing Symposium (IPDPS)","author":"Ao Yulong","year":"2017","unstructured":"Yulong Ao , Chao Yang , Xinliang Wang , Wei Xue , Haohuan Fu , Fang-fang Liu, Lin Gan , Ping Xu , and Wenjing Ma . 2017 . 26 PFLOPS Stencil Computations for Atmospheric Modeling on Sunway TaihuLight. In Parallel and Distributed Processing Symposium (IPDPS) , 2017 IEEE International. IEEE, 535--544. Yulong Ao, Chao Yang, Xinliang Wang, Wei Xue, Haohuan Fu, Fang-fang Liu, Lin Gan, Ping Xu, and Wenjing Ma. 2017. 26 PFLOPS Stencil Computations for Atmospheric Modeling on Sunway TaihuLight. In Parallel and Distributed Processing Symposium (IPDPS), 2017 IEEE International. IEEE, 535--544."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018747"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974690.ch2"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693488"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1104"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_2_9_1","volume-title":"Report on the sunway taihulight system. www.netlib.org. Retrieved June 20","author":"Dongarra Jack","year":"2016","unstructured":"Jack Dongarra . 2016. Report on the sunway taihulight system. www.netlib.org. Retrieved June 20 ( 2016 ). Jack Dongarra. 2016. Report on the sunway taihulight system. www.netlib.org. Retrieved June 20 (2016)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494999"},{"key":"e_1_3_2_2_11_1","volume-title":"Reid","author":"Duff Iain S.","year":"2017","unstructured":"Iain S. Duff , Albert M. Erisman , and John K . Reid . 2017 . Direct Methods for Sparse Matrices (2nd ed.). Oxford University Press , Inc. Iain S. Duff, Albert M. Erisman, and John K. Reid. 2017. Direct Methods for Sparse Matrices (2nd ed.). Oxford University Press, Inc."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.20"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-016-5588-7"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312035"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2006.88"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079105"},{"key":"e_1_3_2_2_17_1","volume-title":"Workshop on Profile and Feedback-Directed Compilation","volume":"139","author":"Im Eun-Jin","year":"1998","unstructured":"Eun-Jin Im and Katherine Yelick . 1998 . Model-based memory hierarchy optimizations for sparse matrices . In Workshop on Profile and Feedback-Directed Compilation , Vol. 139 . Eun-Jin Im and Katherine Yelick. 1998. Model-based memory hierarchy optimizations for sparse matrices. In Workshop on Profile and Feedback-Directed Compilation, Vol. 139."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.51"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807667"},{"key":"e_1_3_2_2_20_1","volume-title":"Synchronization Trade-Offs in GPU Implementations of Graph Algorithms. In 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 514--523","author":"Kaleem R.","unstructured":"R. Kaleem , A. Venkat , S. Pai , M. Hall , and K. Pingali . 2016 . Synchronization Trade-Offs in GPU Implementations of Graph Algorithms. In 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 514--523 . R. Kaleem, A. Venkat, S. Pai, M. Hall, and K. Pingali. 2016. Synchronization Trade-Offs in GPU Implementations of Graph Algorithms. In 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 514--523."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851164"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2611462.2611496"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126931"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462181"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-012-0825-3"},{"key":"e_1_3_2_2_26_1","volume-title":"Scalable Graph Traversal on Sunway TaihuLight with Ten Million Cores. In Parallel and Distributed Processing Symposium (IPDPS)","author":"Lin Heng","year":"2017","unstructured":"Heng Lin , Xiongchao Tang , Bowen Yu , Youwei Zhuo , Wenguang Chen , Jidong Zhai , Wanwang Yin , and Weimin Zheng . 2017 . Scalable Graph Traversal on Sunway TaihuLight with Ten Million Cores. In Parallel and Distributed Processing Symposium (IPDPS) , 2017 IEEE International. IEEE, 635--645. Heng Lin, Xiongchao Tang, Bowen Yu, Youwei Zhuo, Wenguang Chen, Jidong Zhai, Wanwang Yin, and Weimin Zheng. 2017. Scalable Graph Traversal on Sunway TaihuLight with Ten Million Cores. In Parallel and Distributed Processing Symposium (IPDPS), 2017 IEEE International. IEEE, 635--645."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.52"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_45"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4244"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2015.06.010"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.04.004"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3087556.3087582"},{"key":"e_1_3_2_2_35_1","volume-title":"GraphLab: A New Parallel Framework for Machine Learning. In Conference on Uncertainty in Artificial Intelligence (UAI).","author":"Low Yucheng","unstructured":"Yucheng Low , Joseph Gonzalez , Aapo Kyrola , Danny Bickson , Carlos Guestrin , and Joseph M. Hellerstein . 2010 . GraphLab: A New Parallel Framework for Machine Learning. In Conference on Uncertainty in Artificial Intelligence (UAI). Yucheng Low, Joseph Gonzalez, Aapo Kyrola, Danny Bickson, Carlos Guestrin, and Joseph M. Hellerstein. 2010. GraphLab: A New Parallel Framework for Machine Learning. In Conference on Uncertainty in Artificial Intelligence (UAI)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3040222"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-009-0066-3"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980987"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07518-1_8"},{"key":"e_1_3_2_2_41_1","volume-title":"Balancing Locality and Concurrency: Solving Sparse Triangular Systems on GPUs. In 2016 IEEE 23rd International Conference on High Performance Computing (HiPC). 183--192","author":"Picciau A.","unstructured":"A. Picciau , G. E. Inggs , J. Wickerson , E. C. Kerrigan , and G. A. Constantinides . 2016 . Balancing Locality and Concurrency: Solving Sparse Triangular Systems on GPUs. In 2016 IEEE 23rd International Conference on High Performance Computing (HiPC). 183--192 . A. Picciau, G. E. Inggs, J. Wickerson, E. C. Kerrigan, and G. A. Constantinides. 2016. Balancing Locality and Concurrency: Solving Sparse Triangular Systems on GPUs. In 2016 IEEE 23rd International Conference on High Performance Computing (HiPC). 183--192."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2453972"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494989"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Yousef Saad. 2003. Iterative methods for sparse linear systems. Siam.   Yousef Saad. 2003. Iterative methods for sparse linear systems. Siam.","DOI":"10.1137\/1.9780898718003"},{"key":"e_1_3_2_2_45_1","series-title":"SIAM journal on scientific and statistical computing 11, 1","volume-title":"Aggregation methods for solving sparse triangular systems on multiprocessors","author":"Saltz Joel H","year":"1990","unstructured":"Joel H Saltz . 1990. Aggregation methods for solving sparse triangular systems on multiprocessors . SIAM journal on scientific and statistical computing 11, 1 ( 1990 ), 123--144. Joel H Saltz. 1990. Aggregation methods for solving sparse triangular systems on multiprocessors. SIAM journal on scientific and statistical computing 11, 1 (1990), 123--144."},{"key":"e_1_3_2_2_46_1","volume-title":"Department of Computer Science","author":"Schreiber Robert","year":"1982","unstructured":"Robert Schreiber and Wei-Pei Tang . 1982. Vectorizing the conjugate gradient method. Unpublished manuscript , Department of Computer Science , Stanford University ( 1982 ). Robert Schreiber and Wei-Pei Tang. 1982. Vectorizing the conjugate gradient method. Unpublished manuscript, Department of Computer Science, Stanford University (1982)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781142"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/11596110_7"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041294"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2016.02.004"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2012.23"},{"key":"e_1_3_2_2_52_1","unstructured":"Guangming Tan Junhong Liu and Jiajia Li. 2018. Design and Implementation of Adaptive SpMV Library for Multicore and Manycore Architecture. ACM Trans. Math. Softw. (2018).  Guangming Tan Junhong Liu and Jiajia Li. 2018. Design and Implementation of Adaptive SpMV Library for Multicore and Manycore Architecture. ACM Trans. Math. Softw. (2018)."},{"key":"e_1_3_2_2_53_1","first-page":"1","article-title":"Trends in Data Locality Abstractions for HPC Systems","volume":"99","author":"Unat D.","year":"2017","unstructured":"D. Unat , A. Dubey , T. Hoefler , J. Shalf , M. Abraham , M. Bianco , B. L. Chamberlain , R. Cledat , H. C. Edwards , H. Finkel , K. Fuerlinger , F. Hannig , E. Jeannot , A. Kamil , J. Keasler , P. H. J. Kelly , V. Leung , H. Ltaief , N. Maruyama , C. J. Newburn , and M. Pericas . 2017 . Trends in Data Locality Abstractions for HPC Systems . IEEE Transactions on Parallel and Distributed Systems PP , 99 (2017), 1 -- 1 . D. Unat, A. Dubey, T. Hoefler, J. Shalf, M. Abraham, M. Bianco, B. L. Chamberlain, R. Cledat, H. C. Edwards, H. Finkel, K. Fuerlinger, F. Hannig, E. Jeannot, A. Kamil, J. Keasler, P. H. J. Kelly, V. Leung, H. Ltaief, N. Maruyama, C. J. Newburn, and M. Pericas. 2017. Trends in Data Locality Abstractions for HPC Systems. IEEE Transactions on Parallel and Distributed Systems PP, 99 (2017), 1--1.","journal-title":"IEEE Transactions on Parallel and Distributed Systems PP"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2738003"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3014904.3014959"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.5555\/1863086.1863099"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762822"},{"key":"e_1_3_2_2_59_1","volume-title":"Automatic Performance Tuning and Analysis of Sparse Triangular Solve. In ICS 2002: Workshop on Performance Optimization via High-Level Languages and Libraries.","author":"Vuduc Richard","year":"2002","unstructured":"Richard Vuduc , Shoaib Kamil , Jen Hsu , Rajesh Nishtala , James W Demmel , and Katherine A Yelick . 2002 . Automatic Performance Tuning and Analysis of Sparse Triangular Solve. In ICS 2002: Workshop on Performance Optimization via High-Level Languages and Libraries. Richard Vuduc, Shoaib Kamil, Jen Hsu, Rajesh Nishtala, James W Demmel, and Katherine A Yelick. 2002. Automatic Performance Tuning and Analysis of Sparse Triangular Solve. In ICS 2002: Workshop on Performance Optimization via High-Level Languages and Libraries."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926291"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018752"},{"key":"e_1_3_2_2_62_1","volume-title":"International Conference on High Performance Computing for Computational Science. Springer, 32--44","author":"Wolf Michael M","year":"2010","unstructured":"Michael M Wolf , Michael A Heroux , and Erik G Boman . 2010 . Factors impacting performance of multithreaded sparse triangular solve . In International Conference on High Performance Computing for Computational Science. Springer, 32--44 . Michael M Wolf, Michael A Heroux, and Erik G Boman. 2010. Factors impacting performance of multithreaded sparse triangular solve. In International Conference on High Performance Computing for Computational Science. Springer, 32--44."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.9"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555255"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442539"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.5555\/3014904.3014912"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950408"},{"key":"e_1_3_2_2_68_1","volume-title":"Scaling Concurrent Index Structures under Contention Using HTM","author":"Zhang Weihua","year":"2017","unstructured":"Weihua Zhang , Xin Wang , Shiyu Ji , Ziyun Wei , Zhaoguo Wang , and Haibo Chen . 2017. Scaling Concurrent Index Structures under Contention Using HTM . IEEE Transactions on Parallel and Distributed Systems ( 2017 ). Weihua Zhang, Xin Wang, Shiyu Ji, Ziyun Wei, Zhaoguo Wang, and Haibo Chen. 2017. Scaling Concurrent Index Structures under Contention Using HTM. IEEE Transactions on Parallel and Distributed Systems (2017)."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.20"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178495"}],"event":{"name":"PPoPP '18: 23nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","location":"Vienna Austria","acronym":"PPoPP '18","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 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178487.3178513","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3178487.3178513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:39:08Z","timestamp":1750196348000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178487.3178513"}},"subtitle":["a fast sparse triangular solve with sparse level tile layout on sunway architectures"],"short-title":[],"issued":{"date-parts":[[2018,2,10]]},"references-count":67,"alternative-id":["10.1145\/3178487.3178513","10.1145\/3178487"],"URL":"https:\/\/doi.org\/10.1145\/3178487.3178513","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3200691.3178513","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2018,2,10]]},"assertion":[{"value":"2018-02-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}