{"id":"https://openalex.org/W4401408821","doi":"https://doi.org/10.1145/3673038.3673159","title":"DB-SpGEMM: A Massively Distributed Block-Sparse Matrix-Matrix Multiplication for Linear-Scaling DFT Calculations","display_name":"DB-SpGEMM: A Massively Distributed Block-Sparse Matrix-Matrix Multiplication for Linear-Scaling DFT Calculations","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408821","doi":"https://doi.org/10.1145/3673038.3673159"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673159","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673159","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 53rd 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/10.1145/3673038.3673159","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086075879","display_name":"Zhong Zheng","orcid":"https://orcid.org/0009-0001-7686-3561"},"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":"Zhong Zheng","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0001-7686-3561","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436158","display_name":"Junshi Chen","orcid":"https://orcid.org/0000-0002-6487-3658"},"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":"Junshi Chen","raw_affiliation_strings":["University of Science and Technology of China, China and Laoshan Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-6487-3658","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China and Laoshan Laboratory, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060336115","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0009-9644-8574"},"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":"Yang Zhao","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0009-9644-8574","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042365974","display_name":"L. S. Song","orcid":"https://orcid.org/0009-0003-8994-6280"},"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":"Longsheng Song","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0003-8994-6280","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070798308","display_name":"Xinming Qin","orcid":"https://orcid.org/0000-0001-6641-1003"},"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":"Xinming Qin","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-6641-1003","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085758579","display_name":"Hong An","orcid":"https://orcid.org/0000-0002-3900-3722"},"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":"Hong An","raw_affiliation_strings":["University of Science and Technology of China, China and Laoshan Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-3900-3722","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China and Laoshan Laboratory, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086075879"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6576,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66049939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1156","last_page":"1165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9775000214576721,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9743000268936157,"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/computer-science","display_name":"Computer science","score":0.6198441386222839},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6109107732772827},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6108468770980835},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5582597255706787},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5580158233642578},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5235181450843811},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5102858543395996},{"id":"https://openalex.org/keywords/linear-scale","display_name":"Linear scale","score":0.4837679862976074},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4595365524291992},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44475600123405457},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37342318892478943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24615570902824402},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1771986186504364},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1459396481513977},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0986127257347107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6198441386222839},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6109107732772827},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6108468770980835},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5582597255706787},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5580158233642578},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5235181450843811},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5102858543395996},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.4837679862976074},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4595365524291992},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44475600123405457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37342318892478943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24615570902824402},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1771986186504364},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1459396481513977},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0986127257347107},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673159","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673159","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673159","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673159","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 53rd 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":33,"referenced_works":["https://openalex.org/W1758621580","https://openalex.org/W1810694562","https://openalex.org/W1969233413","https://openalex.org/W1979394599","https://openalex.org/W2027353946","https://openalex.org/W2041281913","https://openalex.org/W2055578689","https://openalex.org/W2080353445","https://openalex.org/W2087609676","https://openalex.org/W2087772053","https://openalex.org/W2122948532","https://openalex.org/W2134048650","https://openalex.org/W2139316564","https://openalex.org/W2142501550","https://openalex.org/W2148424525","https://openalex.org/W2235832317","https://openalex.org/W2332437841","https://openalex.org/W2475126267","https://openalex.org/W2479443192","https://openalex.org/W2559782537","https://openalex.org/W2618525552","https://openalex.org/W2781204135","https://openalex.org/W2973084438","https://openalex.org/W3009472344","https://openalex.org/W3036005033","https://openalex.org/W3036899338","https://openalex.org/W3105654855","https://openalex.org/W3105937213","https://openalex.org/W4231154391","https://openalex.org/W4293731110","https://openalex.org/W4306796079","https://openalex.org/W4378652638","https://openalex.org/W4388697730"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Linear-scaling":[0],"<Formula":[1,40],"format=\"inline\"><TexMath><?TeX":[2,41],"$\\mathcal":[3,42],"{O}(N)$?></TexMath><AltText>Math":[4,43],"1</AltText><File":[5],"name=\"icpp24-121-inline1\"":[6],"type=\"svg\"/></Formula>":[7,46],"density":[8,134],"functional":[9,135],"theory":[10,136],"(DFT)":[11],"represents":[12],"a":[13,93,123,146],"significant":[14],"advancement":[15],"in":[16,39,107],"the":[17,56,62,72,131,139,153],"field":[18],"of":[19,26,65,76],"computational":[20,63,111],"materials":[21],"science,":[22],"especially":[23],"for":[24,100],"simulations":[25],"large":[27],"systems":[28],"where":[29],"traditional":[30],"cubic-scaling":[31],"methods":[32,47],"become":[33],"computationally":[34],"prohibitive.":[35],"The":[36],"core":[37],"operation":[38],"2</AltText><File":[44],"name=\"icpp24-121-inline2\"":[45],"is":[48,55,68],"sparse":[49,74],"general":[50],"matrix-matrix":[51,96],"multiplication":[52,97],"(SpGEMM),":[53],"which":[54],"major":[57],"performance":[58],"bottleneck.":[59],"To":[60],"enhance":[61],"efficiency":[64],"SpGEMM,":[66],"it":[67],"crucial":[69],"to":[70,152],"consider":[71],"inherent":[73],"pattern":[75],"these":[77],"matrices.":[78],"Targeting":[79],"block-sparse":[80,95],"matrices":[81],"with":[82],"moderate":[83],"block":[84,88],"sizes":[85],"and":[86,117,160],"regular":[87],"shapes,":[89],"we":[90,120],"have":[91,121],"developed":[92],"distributed":[94,108],"(DB-SpGEMM)":[98],"algorithm":[99,129],"large-scale":[101],"DFT":[102],"calculations.":[103],"Through":[104],"deep":[105],"optimizations":[106],"matrix":[109],"storage,":[110],"task":[112,115],"decomposition,":[113],"asynchronous":[114],"scheduling,":[116],"load":[118],"balancing,":[119],"implemented":[122],"linear-scaling":[124],"method":[125],"based":[126],"on":[127,156],"this":[128],"within":[130],"discontinuous":[132],"Galerkin":[133],"(DGDFT).":[137],"On":[138],"new":[140],"Sunway":[141],"supercomputer,":[142],"our":[143],"approach":[144],"achieves":[145],"8":[147],"\u223c":[148],"10x":[149],"speedup":[150],"compared":[151],"original":[154],"version":[155],"monolayer":[157],"phosphorene":[158],"systems,":[159],"demonstrates":[161],"superior":[162],"scalability.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
