{"id":"https://openalex.org/W7125915276","doi":"https://doi.org/10.1145/3774934.3786442","title":"Trojan Horse: Aggregate-and-Batch for Scaling Up Sparse Direct Solvers on GPU Clusters","display_name":"Trojan Horse: Aggregate-and-Batch for Scaling Up Sparse Direct Solvers on GPU Clusters","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125915276","doi":"https://doi.org/10.1145/3774934.3786442"},"language":null,"primary_location":{"id":"doi:10.1145/3774934.3786442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yida Li","orcid":"https://orcid.org/0000-0003-0527-5209"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Li","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0527-5209","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124132740","display_name":"Siwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Zhang","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3869-5453","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124104459","display_name":"Yiduo Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiduo Niu","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6203-5361","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124081867","display_name":"Yang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Du","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2799-2201","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060999547","display_name":"Qingxiao Sun","orcid":"https://orcid.org/0000-0003-2927-362X"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiao Sun","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2927-362X","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048293143","display_name":"Zhou Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Jin","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0632-9494","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":null,"display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2150-5759","affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.39399999380111694,"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":0.39399999380111694,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.09969999641180038,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.08139999955892563,"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/leverage","display_name":"Leverage (statistics)","score":0.61080002784729},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.48249998688697815},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4544999897480011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4350999891757965},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.33500000834465027},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.31929999589920044},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.3165999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347000241279602},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5180000066757202},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5077999830245972},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774934.3786442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1518783595","https://openalex.org/W1607053641","https://openalex.org/W1904624772","https://openalex.org/W1970009422","https://openalex.org/W1984048334","https://openalex.org/W1987322414","https://openalex.org/W2013424510","https://openalex.org/W2013433526","https://openalex.org/W2035080386","https://openalex.org/W2038205735","https://openalex.org/W2041999884","https://openalex.org/W2051917325","https://openalex.org/W2053999255","https://openalex.org/W2055094346","https://openalex.org/W2057569957","https://openalex.org/W2063298393","https://openalex.org/W2063675347","https://openalex.org/W2070299075","https://openalex.org/W2070571481","https://openalex.org/W2071362730","https://openalex.org/W2074093855","https://openalex.org/W2084848530","https://openalex.org/W2089024363","https://openalex.org/W2118076222","https://openalex.org/W2121079503","https://openalex.org/W2132895243","https://openalex.org/W2141331848","https://openalex.org/W2141944997","https://openalex.org/W2226936188","https://openalex.org/W2410272182","https://openalex.org/W2508784218","https://openalex.org/W2601355684","https://openalex.org/W2775348209","https://openalex.org/W2811328680","https://openalex.org/W2903504144","https://openalex.org/W2970278615","https://openalex.org/W3047681903","https://openalex.org/W3165254043","https://openalex.org/W3167826856","https://openalex.org/W3173589482","https://openalex.org/W3187688612","https://openalex.org/W4220912491","https://openalex.org/W4232836277","https://openalex.org/W4252234101","https://openalex.org/W4285609454","https://openalex.org/W4312491464","https://openalex.org/W4313408245","https://openalex.org/W4321446091","https://openalex.org/W4321446115","https://openalex.org/W4367171414","https://openalex.org/W4380356442","https://openalex.org/W4386709563","https://openalex.org/W4388101094","https://openalex.org/W4388102819","https://openalex.org/W4388662066","https://openalex.org/W4388664805","https://openalex.org/W4388798965","https://openalex.org/W4393168968","https://openalex.org/W4399145742","https://openalex.org/W4402995590","https://openalex.org/W4416004554","https://openalex.org/W7106700490"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"direct":[1,19],"solvers":[2,20],"are":[3,40],"critical":[4],"building":[5],"blocks":[6],"in":[7,71],"a":[8,46,61,65,75],"range":[9],"of":[10,34,45,60,68],"scientific":[11],"applications":[12],"on":[13,74],"heterogeneous":[14],"supercomputers.":[15],"However,":[16],"existing":[17],"sparse":[18],"have":[21],"not":[22],"been":[23],"able":[24],"to":[25,52],"well":[26],"leverage":[27],"the":[28,43,54,58],"high":[29],"bandwidth":[30],"and":[31,56],"floating-point":[32],"performance":[33],"modern":[35],"GPUs.":[36],"The":[37],"primary":[38],"challenges":[39],"twofold:":[41],"(1)":[42],"absence":[44],"mechanism":[47,62],"for":[48,63],"aggregating":[49],"small":[50,69],"tasks":[51,70],"saturate":[53],"GPU,":[55],"(2)":[57],"lack":[59],"executing":[64],"diverse":[66],"set":[67],"batch":[72],"mode":[73],"single":[76],"GPU.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}