{"id":"https://openalex.org/W4399154859","doi":"https://doi.org/10.1007/s11227-024-06234-2","title":"Optimizing sparse general matrix\u2013matrix multiplication for DCUs","display_name":"Optimizing sparse general matrix\u2013matrix multiplication for DCUs","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399154859","doi":"https://doi.org/10.1007/s11227-024-06234-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-024-06234-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06234-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06234-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06234-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056815618","display_name":"Hengliang Guo","orcid":"https://orcid.org/0000-0001-5796-233X"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hengliang Guo","raw_affiliation_strings":["National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023982995","display_name":"Haolei Wang","orcid":"https://orcid.org/0000-0002-4626-2853"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolei Wang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069344375","display_name":"Wanting Chen","orcid":"https://orcid.org/0009-0001-8487-4068"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanting Chen","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034633626","display_name":"Congxiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congxiang Zhang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109031593","display_name":"Yubo Han","orcid":"https://orcid.org/0009-0004-4656-2532"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubo Han","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101062877","display_name":"Shengguang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengguang Zhu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078983894","display_name":"Dujuan Zhang","orcid":"https://orcid.org/0000-0001-7720-4800"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dujuan Zhang","raw_affiliation_strings":["National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103253055","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0002-0179-6712"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guo","raw_affiliation_strings":["National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022800604","display_name":"Jiandong Shang","orcid":"https://orcid.org/0009-0001-7673-2641"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiandong Shang","raw_affiliation_strings":["National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112111930","display_name":"Tao Wan","orcid":"https://orcid.org/0009-0004-4784-1250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Wan","raw_affiliation_strings":["Geophysical Research Institute of Zhongyuan Oilfield Company, Puyang, 457000, China"],"affiliations":[{"raw_affiliation_string":"Geophysical Research Institute of Zhongyuan Oilfield Company, Puyang, 457000, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107249448","display_name":"Qingyang Li","orcid":"https://orcid.org/0009-0004-5666-2158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Li","raw_affiliation_strings":["Geophysical Research Institute of Zhongyuan Oilfield Company, Puyang, 457000, China"],"affiliations":[{"raw_affiliation_string":"Geophysical Research Institute of Zhongyuan Oilfield Company, Puyang, 457000, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108916466","display_name":"Gang Wu","orcid":"https://orcid.org/0009-0007-6537-2285"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wu","raw_affiliation_strings":["National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, 450001, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5056815618"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.0396,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73458445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"80","issue":"14","first_page":"20176","last_page":"20200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7919999361038208},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7142311334609985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6909052133560181},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6430539488792419},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6089009046554565},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5620515942573547},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5221812725067139},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5004069805145264},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45833781361579895},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4446123540401459},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11671727895736694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919999361038208},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7142311334609985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6909052133560181},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6430539488792419},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6089009046554565},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5620515942573547},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5221812725067139},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5004069805145264},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45833781361579895},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4446123540401459},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11671727895736694},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-024-06234-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06234-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06234-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-024-06234-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06234-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06234-2.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399154859.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1543862374","https://openalex.org/W1589103334","https://openalex.org/W1665157575","https://openalex.org/W1965996575","https://openalex.org/W1973918431","https://openalex.org/W1980282429","https://openalex.org/W1985263109","https://openalex.org/W2010370862","https://openalex.org/W2035080386","https://openalex.org/W2045491525","https://openalex.org/W2089437293","https://openalex.org/W2141380216","https://openalex.org/W2154111453","https://openalex.org/W2168931017","https://openalex.org/W2394534308","https://openalex.org/W2410432900","https://openalex.org/W2410461480","https://openalex.org/W2751658790","https://openalex.org/W2786790754","https://openalex.org/W2903237845","https://openalex.org/W2908198074","https://openalex.org/W2914086833","https://openalex.org/W2962729196","https://openalex.org/W3000305333","https://openalex.org/W4220912491","https://openalex.org/W4283033672","https://openalex.org/W4360995394","https://openalex.org/W4377693098","https://openalex.org/W4378220964","https://openalex.org/W4385496093","https://openalex.org/W4385698913","https://openalex.org/W4392855244"],"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":{"Abstract":[0],"Sparse":[1],"general":[2],"matrix\u2013matrix":[3],"multiplication":[4],"(SpGEMM)":[5],"is":[6,28],"a":[7,65],"crucial":[8],"and":[9,123,137,146,164,189],"complex":[10],"computational":[11],"task":[12],"in":[13,45,64],"many":[14],"practical":[15],"applications.":[16],"Improving":[17],"the":[18,32,81,97,101],"performance":[19,47,131],"of":[20,35,69,80,100,114,121,172],"SpGEMM":[21,130,158],"on":[22,75,84,195],"SIMT":[23],"processors":[24],"like":[25],"modern":[26],"GPUs":[27],"challenging":[29],"due":[30],"to":[31,57,95,155,175,179,183,187,192],"unpredictable":[33],"sparsity":[34],"sparse":[36,197,201],"matrices.":[37],"Although":[38],"existing":[39],"GPU":[40],"solutions":[41],"have":[42],"made":[43],"progress":[44],"improving":[46,128],"through":[48,143],"advanced":[49],"algorithm":[50,83],"design,":[51],"they":[52],"ignore":[53],"some":[54],"optimizations":[55,90],"related":[56],"specific":[58],"processor":[59],"architectures.":[60],"This":[61,72],"can":[62],"result":[63],"partially":[66],"inefficient":[67,78],"implementation":[68],"their":[70],"algorithms.":[71],"paper":[73],"focuses":[74],"optimizing":[76],"four":[77],"parts":[79],"NSparse":[82],"DCU":[85],"(a":[86],"GPU-like":[87],"accelerator).":[88],"The":[89],"include:":[91],"1)":[92],"setting":[93],"parameters":[94],"improve":[96],"load":[98,141],"balance":[99,142],"second":[102],"matrix":[103],"by":[104,117,132],"extracting":[105],"maximum":[106],"row":[107],"information":[108],"at":[109],"runtime;":[110],"2)":[111],"reducing":[112],"overhead":[113],"binning":[115],"operations":[116],"making":[118],"full":[119],"use":[120],"registers":[122],"shared":[124],"memory":[125],"effectively;":[126],"3)":[127],"numerical":[129],"adjusting":[133],"its":[134],"calculation":[135],"mode;":[136],"4)":[138],"enhancing":[139],"global":[140],"finer-grained":[144],"grouping":[145],"kernel":[147],"configurations.":[148],"Experiment":[149],"results":[150],"demonstrate":[151],"that":[152],"when":[153],"compared":[154],"five":[156],"state-of-the-art":[157],"algorithms":[159],"(bhSparse,":[160],"KokkosKernels,":[161],"NSparse,":[162],"rocSparse,":[163],"spECK),":[165],"our":[166],"optimized":[167],"method":[168],"achieves":[169],"an":[170],"average":[171],"7.99x":[173],"(up":[174,178,182,186,191],"18.2x),":[176],"8.01x":[177],"20.83x),":[180],"2.37x":[181],"6.16x),":[184],"1.82x":[185],"4.20x),":[188],"1.63x":[190],"5.01x)":[193],"speedups":[194],"29":[196],"matrices":[198],"with":[199],"different":[200],"structures,":[202],"respectively.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
