{"id":"https://openalex.org/W7124179387","doi":"https://doi.org/10.1145/3767295.3769378","title":"Matrix\u2011PIC: Harnessing Matrix Outer-product for High\u2011Performance Particle\u2011in\u2011Cell Simulations","display_name":"Matrix\u2011PIC: Harnessing Matrix Outer-product for High\u2011Performance Particle\u2011in\u2011Cell Simulations","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7124179387","doi":"https://doi.org/10.1145/3767295.3769378"},"language":null,"primary_location":{"id":"doi:10.1145/3767295.3769378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769378","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123033031","display_name":"Yizhuo Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yizhuo Rao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0000-3572-6969","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123024376","display_name":"Xingjian Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian Cui","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0000-1442-5526","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123047476","display_name":"Jiabin Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabin Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-0770-3086","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123015569","display_name":"Shangzhi Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangzhi Pang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0008-5488-9235","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123022370","display_name":"Guangnan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangnan Feng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-1382-280X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123006931","display_name":"Jinhui Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Wei","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-9850-8384","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108648345","display_name":"Zhiguang Chen","orcid":"https://orcid.org/0000-0002-5427-1266"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguang Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-5715","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107264798","display_name":"Yutong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5315-3375","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5123033031"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0565534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2073","last_page":"2092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.09790000319480896,"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":0.09790000319480896,"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/T11471","display_name":"Block Copolymer Self-Assembly","score":0.05350000038743019,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.05139999836683273,"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/speedup","display_name":"Speedup","score":0.6636999845504761},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6384999752044678},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6251999735832214},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5788999795913696},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5544000267982483},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5486000180244446},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5372999906539917},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5167999863624573},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6951000094413757},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6384999752044678},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5455999970436096},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C64297162","wikidata":"https://www.wikidata.org/wiki/Q1987070","display_name":"Deposition (geology)","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2777032711","wikidata":"https://www.wikidata.org/wiki/Q5318993","display_name":"Dynamic mode decomposition","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767295.3769378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769378","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.08277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.08277","pdf_url":"https://arxiv.org/pdf/2601.08277","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769378","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42576873302459717,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320338094","display_name":"Institute of Plasma Physics, Chinese Academy of Sciences","ror":"https://ror.org/033cbzv42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Particle-in-Cell":[0],"(PIC)":[1],"simulations":[2,70],"devote":[3],"most":[4],"cycles":[5],"to":[6,49,71],"particle-grid":[7],"interactions,":[8],"and":[9,46],"their":[10],"fine-grained":[11],"atomic":[12],"updates":[13],"become":[14],"a":[15,43],"severe":[16],"bottleneck":[17],"on":[18,54,61],"traditional":[19],"many-core":[20],"CPUs.":[21],"The":[22],"evolution":[23],"of":[24,30],"CPU":[25],"architectures,":[26],"particularly":[27],"the":[28,63],"integration":[29],"specialized":[31],"Matrix":[32],"Processing":[33],"Units":[34],"(MPUs)":[35],"designed":[36],"for":[37],"efficient":[38],"matrix":[39],"outer-product":[40],"operations,":[41],"presents":[42],"paradigm":[44],"shift":[45],"an":[47],"opportunity":[48],"alleviate":[50],"these":[51],"bottlenecks.":[52],"Capitalizing":[53],"this":[55,58,72],"architectural":[56],"advancement,":[57],"work":[59],"focuses":[60],"adapting":[62],"critical":[64],"current":[65],"deposition":[66],"step":[67],"in":[68],"PIC":[69],"new":[73],"matrix-centric":[74],"computational":[75],"model.":[76]},"counts_by_year":[],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2026-01-15T00:00:00"}
