{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:40:08Z","timestamp":1750506008755,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731078","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"1792-1805","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Telos: A Dataflow Accelerator for Sparse Triangular Solver of Partial Differential Equations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2127-6011","authenticated-orcid":false,"given":"Xiaochen","family":"Hao","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1038-944X","authenticated-orcid":false,"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3088-8349","authenticated-orcid":false,"given":"Chu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7426-6248","authenticated-orcid":false,"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-7998","authenticated-orcid":false,"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00029"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00034"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00117"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Rajeev Balasubramonian Andrew\u00a0B Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Huanqi Cao Shizhi Tang Qianchao Zhu Bowen Yu and Wenguang Chen. 2023. Mat2Stencil: A Modular Matrix-Based DSL for Explicit and Implicit Matrix-Free PDE Solvers on Structured Grid. Proceedings of the ACM on Programming Languages 7 OOPSLA2 (2023) 686\u2013715.","DOI":"10.1145\/3622822"},{"key":"e_1_3_3_2_7_2","unstructured":"Long Chen. 2022. Finite difference methods for poisson equation."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Edmond Chow and Yousef Saad. 1997. Experimental study of ILU preconditioners for indefinite matrices. Journal of computational and applied mathematics 86 2 (1997) 387\u2013414.","DOI":"10.1016\/S0377-0427(97)00171-4"},{"key":"e_1_3_3_2_10_2","unstructured":"Jack Dongarra Piotr Luszczek and M Heroux. 2013. HPCG technical specification. Sandia National Laboratories Sandia Report SAND2013-8752 (2013)."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Toby Driscoll. 2022. Fundamentals of Numerical Computation - 8.8 Preconditioning. https:\/\/tobydriscoll.net\/fnc-julia\/krylov\/precond.html.","DOI":"10.1137\/1.9781611977011"},{"key":"e_1_3_3_2_12_2","volume-title":"Partial differential equations for scientists and engineers","author":"Farlow Stanley\u00a0J","year":"1993","unstructured":"Stanley\u00a0J Farlow. 1993. Partial differential equations for scientists and engineers. Courier Corporation."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00039"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00054"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623783"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00081"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589054"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532373"},{"key":"e_1_3_3_2_20_2","unstructured":"Xiaochen Hao Mingzhe Zhang Ce Sun Zhuofu Tao Hongbo Rong Yu Zhang Lei He Eric Petit Wenguang Chen and Yun Liang. 2025. Productively Generating a High-Performance Linear Algebra Library on FPGAs. ACM Transactions on Reconfigurable Technology and Systems (2025)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637568"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582051"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571891"},{"key":"e_1_3_3_2_24_2","unstructured":"Zhengding Hu Jingwei Sun Zhongyang Li and Guangzhong Sun. 2024. AG-SpTRSV: An Automatic Framework to Optimize Sparse Triangular Solve on GPUs. ACM Transactions on Architecture and Code Optimization (2024)."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586329"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Sun-Yuan Kung Bhaskar Rao et\u00a0al. 1982. Wavefront array processor: Language architecture and applications. IEEE Trans. Comput. 100 11 (1982) 1054\u20131066.","DOI":"10.1109\/TC.1982.1675922"},{"key":"e_1_3_3_2_27_2","unstructured":"Jiajun Li and Yue Deng. 2024. SPADIX: A Highly Efficient Accelerator for Solving 3D Partial Differential Equations. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589083"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Shang Li Zhiyuan Yang Dhiraj Reddy Ankur Srivastava and Bruce Jacob. 2020. DRAMsim3: A Cycle-Accurate Thermal-Capable DRAM Simulator. IEEE Computer Architecture Letters 19 2 (2020) 106\u2013109.","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676735"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_45"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00013"},{"key":"e_1_3_3_2_35_2","volume-title":"International Conference on Supercomputing (ICS)","author":"Luo Hao","year":"2025","unstructured":"Hao Luo, Qianchao Zhu, Xiaochen Hao, Chunxi Lei, Chengdi Ma, Chenchen Zhang, Yun Liang, and Chao Yang. 2025. StructILU: Dependency-Preserving Incomplete LU with Hierarchical Parallelism for Structured Grid PDEs on GPUs. In International Conference on Supercomputing (ICS)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0Tran Mills Mark\u00a0F. Adams Satish Balay Jed Brown and Alp Dener. 2021. Toward performance-portable PETSc for GPU-based exascale systems. Parallel Comput. 108 (2021) 102831.","DOI":"10.1016\/j.parco.2021.102831"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511812248"},{"key":"e_1_3_3_2_38_2","unstructured":"Maxim Naumov. 2011. Parallel solution of sparse triangular linear systems in the preconditioned iterative methods on the GPU. NVIDIA Corp. Tech. Rep. 1 (2011)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.70"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07518-1_8"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-3286-8_127"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433778"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Patrick Sanan Dave\u00a0A May Richard\u00a0T Mills et\u00a0al. 2022. DMStag: staggered structured grids for PETSc. Journal of Open Source Software 7 79 (2022) 4531.","DOI":"10.21105\/joss.04531"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476220"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593719"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614284"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607077"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543622.3573182"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589108"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00115"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062185"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225071"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623786"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.5555\/3014904.3014912"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00072"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651336"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476158"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Tokyo Japan","acronym":"SIGARCH '25"},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:09:43Z","timestamp":1750504183000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":57,"alternative-id":["10.1145\/3695053.3731078","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731078","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}