{"id":"https://openalex.org/W1992476323","doi":"https://doi.org/10.1109/padsw.2014.7097819","title":"Cache-aware sparse matrix formats for Kepler GPU","display_name":"Cache-aware sparse matrix formats for Kepler GPU","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1992476323","doi":"https://doi.org/10.1109/padsw.2014.7097819","mag":"1992476323"},"language":"en","primary_location":{"id":"doi:10.1109/padsw.2014.7097819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","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":"https://openalex.org/A5069048439","display_name":"Yusuke Nagasaka","orcid":"https://orcid.org/0009-0009-2204-2424"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Nagasaka","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo","Tokyo Institute of technology, Meguro, 152-8550, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of technology, Meguro, 152-8550, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006972521","display_name":"Akira Nukada","orcid":"https://orcid.org/0000-0001-7959-6975"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Nukada","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo","Tokyo Institute of technology, Meguro, 152-8550, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of technology, Meguro, 152-8550, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo","Tokyo Institute of technology, Meguro, 152-8550, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of technology, Meguro, 152-8550, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"281","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9977999925613403,"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":0.9973000288009644,"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":0.8253656625747681},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.802035927772522},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7031294107437134},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6711702942848206},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5937309861183167},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5838027000427246},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5445989370346069},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5374152660369873},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5203996896743774},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49284791946411133},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4545939266681671},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4510948359966278},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.3984667956829071},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3525328040122986},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10817769169807434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09036910533905029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253656625747681},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.802035927772522},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7031294107437134},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6711702942848206},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5937309861183167},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5838027000427246},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5445989370346069},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5374152660369873},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5203996896743774},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49284791946411133},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4545939266681671},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4510948359966278},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.3984667956829071},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3525328040122986},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10817769169807434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09036910533905029},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/padsw.2014.7097819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1555620806","https://openalex.org/W1588915715","https://openalex.org/W1776498962","https://openalex.org/W1987840949","https://openalex.org/W1995649289","https://openalex.org/W2035080386","https://openalex.org/W2040556424","https://openalex.org/W2043105874","https://openalex.org/W2071819510","https://openalex.org/W2083051666","https://openalex.org/W2086392083","https://openalex.org/W2103877122","https://openalex.org/W2120768584","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2141003547","https://openalex.org/W2162630236","https://openalex.org/W2164661813","https://openalex.org/W2183317050","https://openalex.org/W2262570173","https://openalex.org/W2518567779","https://openalex.org/W2610373075","https://openalex.org/W4231299715","https://openalex.org/W4237792308","https://openalex.org/W4285719527","https://openalex.org/W6638245406","https://openalex.org/W6686667855","https://openalex.org/W6693407638"],"related_works":["https://openalex.org/W1827355354","https://openalex.org/W2001324285","https://openalex.org/W4245668848","https://openalex.org/W2253769547","https://openalex.org/W2121191383","https://openalex.org/W2098406302","https://openalex.org/W2027255782","https://openalex.org/W2274935188","https://openalex.org/W2111709480","https://openalex.org/W2331506401"],"abstract_inverted_index":{"Scientific":[0],"simulations":[1],"often":[2],"require":[3],"solving":[4],"extremely":[5,41],"large":[6],"sparse":[7,14,66],"linear":[8],"equations,":[9],"whose":[10],"dominant":[11],"kernel":[12],"is":[13],"matrix":[15,67,84],"vector":[16],"multiplication.":[17],"On":[18],"modern":[19],"many-core":[20,70],"processors":[21,71],"such":[22,139],"as":[23,140],"GPU":[24],"or":[25],"MIC,":[26],"the":[27,59,74,83,86,89,92,97,103,126],"operation":[28],"has":[29],"been":[30,136],"known":[31],"to":[32,55,58,96,114,125],"pose":[33],"significant":[34],"bottleneck":[35],"and":[36,49,78,101,119,130],"thus":[37,79],"would":[38],"result":[39,104],"in":[40,117,121],"poor":[42],"efficiency,":[43],"because":[44],"of":[45,64],"limited":[46],"processor-to-memory":[47],"bandwidth":[48],"low":[50],"cache":[51,75,99],"hit":[52,76],"ratio":[53,77],"due":[54],"random":[56],"access":[57],"input":[60],"vector.":[61],"Our":[62],"family":[63],"new":[65,132],"formats":[68,133],"for":[69],"significantly":[72],"increases":[73],"performance":[80],"by":[81],"segmenting":[82],"along":[85],"columns,":[87],"dividing":[88],"work":[90],"among":[91],"many":[93],"core":[94],"up":[95,113],"internal":[98],"capacity,":[100],"aggregating":[102],"later":[105],"on.":[106],"Performance":[107],"studies":[108],"show":[109],"that":[110,134],"we":[111],"achieve":[112],"x3.0":[115],"speedup":[116],"SpMV":[118],"x1.68":[120],"multi-node":[122],"CG,":[123],"compared":[124],"best":[127],"vendor":[128],"libraries":[129],"competing":[131],"have":[135],"recently":[137],"proposed":[138],"SELL-C-\u03c3.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}