{"id":"https://openalex.org/W7162415649","doi":"https://doi.org/10.1109/ispass69572.2026.00069","title":"VCSR-MM: A Bandwidth-Optimized SpMM Design for Modern GPUs","display_name":"VCSR-MM: A Bandwidth-Optimized SpMM Design for Modern GPUs","publication_year":2026,"publication_date":"2026-04-26","ids":{"openalex":"https://openalex.org/W7162415649","doi":"https://doi.org/10.1109/ispass69572.2026.00069"},"language":null,"primary_location":{"id":"doi:10.1109/ispass69572.2026.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5116861045","display_name":"Mouad Tiahi","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mouad Tiahi","raw_affiliation_strings":["Northeastern University Boston,Khoury College of Computer Science,MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Boston,Khoury College of Computer Science,MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137035149","display_name":"Elmira Karimi","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elmira Karimi","raw_affiliation_strings":["Northeastern University Boston,Dept. of Electrical and Computer Engineering,MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Boston,Dept. of Electrical and Computer Engineering,MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133574686","display_name":"David Kaeli","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University Boston,Dept. of Electrical and Computer Engineering,MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Boston,Dept. of Electrical and Computer Engineering,MA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73595175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6656000018119812,"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":0.6656000018119812,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.07519999891519547,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.02889999933540821,"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/computation","display_name":"Computation","score":0.2851000130176544},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2354000061750412},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.23510000109672546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.23149999976158142},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.23019999265670776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208999752998352},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2354000061750412},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.23510000109672546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23149999976158142},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.23019999265670776},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.22990000247955322},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2224999964237213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass69572.2026.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass69572.2026.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8231176137924194,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2128853364","https://openalex.org/W2914631005","https://openalex.org/W2964337156","https://openalex.org/W3132695675","https://openalex.org/W3158112431","https://openalex.org/W3161200675","https://openalex.org/W4285104934","https://openalex.org/W4395106472","https://openalex.org/W4402917213","https://openalex.org/W4412038588"],"related_works":[],"abstract_inverted_index":{"Sparse":[0,40],"matrix-matrix":[1],"multiplication":[2],"(SpMM)":[3],"involves":[4],"multiplying":[5],"a":[6,11,69,114],"sparse":[7,72],"matrix":[8,13],"A":[9],"by":[10],"dense":[12,34],"B.":[14,36,62],"SpMM":[15],"can":[16],"suffer":[17],"from":[18],"low":[19],"GPU":[20,75],"utilization":[21],"due":[22],"to":[23,49,61],"non-coalesced":[24,110],"memory":[25],"transactions":[26],"and":[27,74,81,93,108,135,145,152],"poor":[28],"temporal":[29,82],"locality":[30,83],"when":[31],"accessing":[32],"the":[33,51,117],"operand":[35],"The":[37],"Vertical":[38],"Condensed":[39],"Row":[41],"(VCSR)":[42],"format":[43,73],"groups":[44],"nonzeros":[45],"into":[46,90],"contiguous":[47],"blocks":[48],"improve":[50],"structure":[52],"of":[53,71,97,116,126],"A,":[54],"but":[55],"still":[56],"generates":[57],"non-contiguous":[58],"gather":[59],"operations":[60],"We":[63],"introduce":[64],"VCSR-MM":[65,102,122],"with":[66],"Stream":[67],"Tiling,":[68],"co-design":[70],"kernel":[76],"that":[77],"targets":[78],"B-side":[79],"spatial":[80],"in":[84,99],"SpMM.":[85],"By":[86],"partitioning":[87],"column":[88],"indices":[89],"compact":[91],"segments":[92],"staging":[94],"bounded":[95],"tiles":[96],"B":[98],"shared":[100],"memory,":[101],"eliminates":[103],"redundant":[104],"L2":[105],"cache":[106],"misses":[107],"reduces":[109],"global-memory":[111],"transactions.":[112],"Across":[113],"sample":[115],"SuiteSparse":[118],"collection":[119],"[1],":[120],"Segmented":[121],"delivers":[123],"geometric-mean":[124],"speedups":[125],"$\\mathbf{1.":[127,131,136],"2":[128],"2}":[129,133],"\\times$,":[130,134],"6":[132],"7":[137],"5}":[138],"\\times$":[139],"over":[140],"cuSPARSE":[141],"[2],":[142],"ASpT":[143],"[3],":[144],"FastSPMM":[146],"[4]":[147],"on":[148],"NVIDIA":[149],"A100,":[150],"H100,":[151],"H200":[153],"GPUs.":[154]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-05-27T00:00:00"}
