{"id":"https://openalex.org/W7116424710","doi":"https://doi.org/10.1145/3754598.3754647","title":"A Fast Sparse Triangular Solve for Structured-grid Problems on Heterogeneous Processors","display_name":"A Fast Sparse Triangular Solve for Structured-grid Problems on Heterogeneous Processors","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116424710","doi":"https://doi.org/10.1145/3754598.3754647"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754647","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754647","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000331589","display_name":"Zhengding Hu","orcid":"https://orcid.org/0009-0005-8500-6173"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengding Hu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-8500-6173","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053505635","display_name":"Yi Zong","orcid":"https://orcid.org/0000-0001-7179-6593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7179-6593","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingwei Sun","orcid":"https://orcid.org/0000-0001-5098-1503"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5098-1503","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120897624","display_name":"Wei Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Tsinghua University, Beijing, China and Qinghai University and Intelligent Computing and Application Laboratory of Qinghai Province, Xining, China"],"raw_orcid":"https://orcid.org/0000-0001-9740-6581","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Qinghai University and Intelligent Computing and Application Laboratory of Qinghai Province, Xining, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120928586","display_name":"Guangzhong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhong Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0794-7681","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000331589"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6474036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8023999929428101,"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":0.8023999929428101,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.04529999941587448,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.043800000101327896,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bottleneck","display_name":"Bottleneck","score":0.6654999852180481},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5936999917030334},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5841000080108643},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4625999927520752},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361999988555908},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7511000037193298},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6654999852180481},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4300000071525574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.274399995803833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754647","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754647","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W993511226","https://openalex.org/W2003264742","https://openalex.org/W2003840611","https://openalex.org/W2009654791","https://openalex.org/W2011832776","https://openalex.org/W2035080386","https://openalex.org/W2048955810","https://openalex.org/W2062424467","https://openalex.org/W2106618443","https://openalex.org/W2135181239","https://openalex.org/W2154555766","https://openalex.org/W2469975815","https://openalex.org/W2473076915","https://openalex.org/W2617403939","https://openalex.org/W2751354592","https://openalex.org/W2789228469","https://openalex.org/W2794424798","https://openalex.org/W2805150752","https://openalex.org/W2887282140","https://openalex.org/W3002227887","https://openalex.org/W3048330007","https://openalex.org/W3132695675","https://openalex.org/W3137858876","https://openalex.org/W3210190478","https://openalex.org/W4247712932","https://openalex.org/W4247828381","https://openalex.org/W4293024985","https://openalex.org/W4380356442","https://openalex.org/W4390264496","https://openalex.org/W4391952019","https://openalex.org/W4400410919","https://openalex.org/W4401408715","https://openalex.org/W4405756444","https://openalex.org/W4408049822","https://openalex.org/W4413411899"],"related_works":[],"abstract_inverted_index":{"Structured-grid":[0],"problems":[1,24],"are":[2],"common":[3],"in":[4,8,21,87],"scientific":[5],"computing,":[6],"particularly":[7],"applications":[9],"like":[10],"fluid":[11],"dynamics":[12],"and":[13,42,55,92,122,165,191],"electromagnetic":[14],"simulation.":[15],"One":[16],"of":[17,52,59,69,147,160,183],"the":[18,50,56,66,173],"key":[19],"kernels":[20],"solving":[22],"these":[23,81],"is":[25],"Sparse":[26],"Triangular":[27],"Solve":[28],"(SpTRSV),":[29],"which":[30],"often":[31],"becomes":[32],"a":[33,100,114,127],"performance":[34],"bottleneck":[35],"due":[36,83],"to":[37,64,78,84,118,143,170],"its":[38],"low":[39],"computing":[40],"intensity":[41],"inherent":[43],"internal":[44],"data":[45,88,120],"dependencies.":[46],"In":[47,95],"structured-grid":[48],"SpTRSV,":[49],"regularity":[51],"non-zero":[53],"distributions":[54],"high":[57],"parallelism":[58,132,148],"sparse":[60],"matrices":[61],"present":[62],"opportunities":[63],"harness":[65],"architectural":[67],"strengths":[68],"modern":[70,108],"heterogeneous":[71,109,161],"processors.":[72,110],"However,":[73],"existing":[74],"SpTRSV":[75,102],"algorithms":[76],"fail":[77],"fully":[79],"exploit":[80],"advantages,":[82],"their":[85],"mismatches":[86],"dependencies,":[89],"computational":[90,134],"order,":[91],"memory":[93],"layouts.":[94],"this":[96],"paper,":[97],"we":[98,137],"introduce":[99],"novel":[101],"algorithm":[103,153],"tailored":[104],"for":[105],"structured-grids":[106],"on":[107,157],"Our":[111],"approach":[112],"introduces":[113],"two-level":[115],"blocking":[116],"strategy":[117],"enhance":[119],"locality":[121],"reduce":[123],"communication":[124],"overhead,":[125],"while":[126],"vertical":[128],"tiling-based":[129],"pipeline":[130],"balances":[131],"with":[133,167,196],"granularity.":[135],"Additionally,":[136],"design":[138],"hardware-specific":[139,168],"adaptive":[140],"scheduling":[141],"strategies":[142],"accommodate":[144],"varying":[145],"degrees":[146],"across":[149],"distinct":[150],"architectures.":[151],"The":[152],"has":[154],"been":[155],"implemented":[156],"two":[158],"types":[159],"processors,":[162],"NVIDIA":[163],"GPUs":[164],"SW26010-Pro,":[166],"optimizations":[169],"further":[171],"improve":[172],"performance.":[174],"Experimental":[175],"results":[176],"show":[177],"that":[178],"our":[179],"implementations":[180],"achieve":[181],"speedups":[182],"more":[184],"than":[185],"1.87":[186],"\u00d7":[187],"over":[188],"state-of-the-art":[189],"baselines":[190],"provide":[192],"efficient":[193],"end-to-end":[194],"solutions":[195],"lightweight":[197],"preprocessing.":[198]},"counts_by_year":[],"updated_date":"2025-12-21T02:06:08.432651","created_date":"2025-12-21T00:00:00"}