{"id":"https://openalex.org/W4411471719","doi":"https://doi.org/10.1145/3695053.3731078","title":"Telos: A Dataflow Accelerator for Sparse Triangular Solver of Partial Differential Equations","display_name":"Telos: A Dataflow Accelerator for Sparse Triangular Solver of Partial Differential Equations","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411471719","doi":"https://doi.org/10.1145/3695053.3731078"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731078","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731078","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072764450","display_name":"X. Q. Hao","orcid":"https://orcid.org/0009-0004-2127-6011"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Hao","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2127-6011","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103423687","display_name":"Hao Luo","orcid":"https://orcid.org/0009-0008-1038-944X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Luo","raw_affiliation_strings":["School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-1038-944X","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chu Wang","orcid":"https://orcid.org/0009-0002-3088-8349"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Wang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3088-8349","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7426-6248","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9076-7998","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10172859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1792","last_page":"1805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11416","display_name":"Numerical methods for differential equations","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8853333592414856},{"id":"https://openalex.org/keywords/telos","display_name":"Telos","score":0.6334246397018433},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6289229989051819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6205593943595886},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.606937825679779},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5074207186698914},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4094889760017395},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32054686546325684},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24605432152748108},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16079631447792053},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.13863956928253174}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8853333592414856},{"id":"https://openalex.org/C2777885928","wikidata":"https://www.wikidata.org/wiki/Q3243630","display_name":"Telos","level":2,"score":0.6334246397018433},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6289229989051819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205593943595886},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.606937825679779},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5074207186698914},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4094889760017395},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32054686546325684},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24605432152748108},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16079631447792053},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.13863956928253174},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731078","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731078","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1004804915","display_name":null,"funder_award_id":"T2325001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411471719.pdf","grobid_xml":"https://content.openalex.org/works/W4411471719.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W993511226","https://openalex.org/W1635779336","https://openalex.org/W1645731123","https://openalex.org/W1977631509","https://openalex.org/W2048968833","https://openalex.org/W2071696716","https://openalex.org/W2134427337","https://openalex.org/W2469975815","https://openalex.org/W2562913534","https://openalex.org/W2626476365","https://openalex.org/W2725159389","https://openalex.org/W2796303555","https://openalex.org/W2883084140","https://openalex.org/W2887282140","https://openalex.org/W2899691047","https://openalex.org/W2949619037","https://openalex.org/W3006586535","https://openalex.org/W3016904661","https://openalex.org/W3190092209","https://openalex.org/W3199181189","https://openalex.org/W3206453033","https://openalex.org/W3206847052","https://openalex.org/W3210190478","https://openalex.org/W3212403328","https://openalex.org/W4282961330","https://openalex.org/W4308985205","https://openalex.org/W4313447739","https://openalex.org/W4327911471","https://openalex.org/W4377864779","https://openalex.org/W4380875466","https://openalex.org/W4380875568","https://openalex.org/W4380881167","https://openalex.org/W4381328365","https://openalex.org/W4383335342","https://openalex.org/W4387674212","https://openalex.org/W4388095748","https://openalex.org/W4389476354","https://openalex.org/W4389500474","https://openalex.org/W4393407064","https://openalex.org/W4393576100","https://openalex.org/W4395106460","https://openalex.org/W4401212175","https://openalex.org/W4401212179","https://openalex.org/W4404954854","https://openalex.org/W4404955127","https://openalex.org/W4404955396","https://openalex.org/W4409282868"],"related_works":["https://openalex.org/W3011358647","https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W1549048322","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2011940952","https://openalex.org/W2144429051"],"abstract_inverted_index":{"Partial":[0],"Differential":[1],"Equations":[2],"(PDEs)":[3],"serve":[4],"as":[5],"the":[6,46,54,117],"backbone":[7],"of":[8,26,119,158,163,174],"numerous":[9],"scientific":[10],"problems.Their":[11],"solutions":[12],"often":[13],"rely":[14],"on":[15],"numerical":[16,42],"methods,":[17,33],"which":[18],"transform":[19],"these":[20],"equations":[21],"into":[22,150],"large,":[23],"sparse":[24,47],"systems":[25],"linear":[27],"equations.These":[28],"systems,":[29],"solved":[30],"with":[31,113,165],"iterative":[32],"exhibit":[34],"structured":[35,94],"sparsity":[36,95],"patterns":[37,96],"when":[38],"derived":[39],"from":[40,66],"stencil-based":[41],"schemes.In":[43],"preconditioned":[44],"solvers,":[45],"triangular":[48],"solve":[49],"procedure,":[50],"SpTRSV,":[51],"usually":[52],"dominates":[53],"entire":[55],"execution":[56,101],"due":[57],"to":[58,73,82,109,146],"its":[59],"loop-carried":[60],"dependencies.Optimizing":[61],"SpTRSV":[62,91],"requires":[63],"extracting":[64],"parallelism":[65,77,108],"dependent":[67,159],"computations.However,":[68],"prior":[69],"works":[70],"have":[71],"struggled":[72],"achieve":[74],"both":[75],"high":[76],"and":[78,161,177],"data":[79,111,121,138,148],"locality,":[80],"leading":[81],"suboptimal":[83],"performance.We":[84],"propose":[85],"Telos,":[86],"a":[87,125,151],"dataflow":[88,100],"accelerator":[89,154],"for":[90],"that":[92,129,169],"exploits":[93],"in":[97],"PDE":[98],"solving.The":[99],"leverages":[102],"stencil":[103],"patterns,":[104],"efficiently":[105],"utilizing":[106],"pipeline":[107],"resolve":[110],"dependencies":[112,122],"minimal":[114],"overhead.We":[115],"tackle":[116],"challenge":[118],"complex":[120],"by":[123],"proposing":[124],"plane-parallel":[126],"pipelining":[127,157],"technique":[128,143],"maps":[130],"computations":[131,160,164],"onto":[132],"processing":[133],"elements":[134],"(PEs)":[135],"while":[136],"preserving":[137],"locality.A":[139],"cross-plane":[140],"communication":[141],"aggregation":[142],"is":[144],"developed":[145],"streamline":[147],"transfers":[149],"systolic":[152],"manner.Our":[153],"features":[155],"effective":[156],"overlapping":[162],"memory":[166],"accesses.Experiments":[167],"demonstrate":[168],"Telos":[170],"delivers":[171],"average":[172],"speedups":[173],"61,":[175],"8,":[176],"11":[178],"over":[179],"CPUs,":[180],"GPUs,":[181],"state-of-the-art":[182],"accelerator,":[183],"respectively.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}