{"id":"https://openalex.org/W4388662112","doi":"https://doi.org/10.1145/3581784.3607097","title":"Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence","display_name":"Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence","publication_year":2023,"publication_date":"2023-11-11","ids":{"openalex":"https://openalex.org/W4388662112","doi":"https://doi.org/10.1145/3581784.3607097"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5011738547","display_name":"Kazem Cheshmi","orcid":"https://orcid.org/0000-0002-2968-5176"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Kazem Cheshmi","raw_affiliation_strings":["Electrical and Computer Engineering, McMaster University, Hamilton, Canada","McMaster University, Hamilton, Canada","Electrical and Computer Engineering, McMaster University, Hamilton, Canada McMaster University, Hamilton, Canada"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, McMaster University, Hamilton, Canada","institution_ids":["https://openalex.org/I98251732"]},{"raw_affiliation_string":"McMaster University, Hamilton, Canada","institution_ids":["https://openalex.org/I98251732"]},{"raw_affiliation_string":"Electrical and Computer Engineering, McMaster University, Hamilton, Canada McMaster University, Hamilton, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022191670","display_name":"Michelle Mills Strout","orcid":"https://orcid.org/0000-0001-7646-4766"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I4210122178","display_name":"Hewlett Packard Enterprise (United States)","ror":"https://ror.org/020x0c621","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122178"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Strout","raw_affiliation_strings":["Computer Science, University of Arizona, Tucson, United States of America","Hewlett Packard Enterprise (HPE), Tucson, United States of America","Computer Science, University of Arizona, Tucson, United States of America Hewlett Packard Enterprise (HPE), Tucson, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Arizona, Tucson, United States of America","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"Hewlett Packard Enterprise (HPE), Tucson, United States of America","institution_ids":["https://openalex.org/I4210122178"]},{"raw_affiliation_string":"Computer Science, University of Arizona, Tucson, United States of America Hewlett Packard Enterprise (HPE), Tucson, United States of America","institution_ids":["https://openalex.org/I4210122178","https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003682451","display_name":"Maryam Mehri Dehnavi","orcid":"https://orcid.org/0000-0002-2719-8788"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Maryam Mehri Dehnavi","raw_affiliation_strings":["Computer Science, University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011738547"],"corresponding_institution_ids":["https://openalex.org/I98251732"],"apc_list":null,"apc_paid":null,"fwci":2.7085,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90536422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.7793920040130615},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6174141764640808},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6162720918655396},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5714786648750305},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5541097521781921},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5257894992828369},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43919646739959717},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41805920004844666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1209234893321991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793920040130615},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6174141764640808},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6162720918655396},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5714786648750305},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5541097521781921},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5257894992828369},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43919646739959717},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41805920004844666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1209234893321991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1329667566","display_name":"Collaborative Research: SHF: Medium: Co-Optimizing Computation and Data Transformations for Sparse Tensors","funder_award_id":"2106621","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1597412403","display_name":null,"funder_award_id":"RGPIN-","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G400116904","display_name":null,"funder_award_id":"unknow","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G5536939483","display_name":null,"funder_award_id":"DGECR-","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G5784215521","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6221715925","display_name":null,"funder_award_id":"RGPIN","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G7136325465","display_name":null,"funder_award_id":"RGPIN-","funder_id":"https://openalex.org/F4320320994","funder_display_name":"Canada Research Chairs"},{"id":"https://openalex.org/G8105784103","display_name":null,"funder_award_id":"RGPIN-202","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8245661358","display_name":null,"funder_award_id":"04897","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8595721295","display_name":null,"funder_award_id":"NSERC","funder_id":"https://openalex.org/F4320320994","funder_display_name":"Canada Research Chairs"},{"id":"https://openalex.org/G919846122","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320320994","funder_display_name":"Canada Research Chairs"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1520511539","https://openalex.org/W1840953097","https://openalex.org/W1907157228","https://openalex.org/W1969468690","https://openalex.org/W1970009422","https://openalex.org/W1977444623","https://openalex.org/W2003117296","https://openalex.org/W2006962349","https://openalex.org/W2013424510","https://openalex.org/W2024149451","https://openalex.org/W2032032242","https://openalex.org/W2035080386","https://openalex.org/W2047937722","https://openalex.org/W2066166631","https://openalex.org/W2087507944","https://openalex.org/W2092990259","https://openalex.org/W2095258827","https://openalex.org/W2096714979","https://openalex.org/W2180959024","https://openalex.org/W2566719947","https://openalex.org/W2614185560","https://openalex.org/W2617628430","https://openalex.org/W2725179571","https://openalex.org/W2887885459","https://openalex.org/W2898106867","https://openalex.org/W2902699695","https://openalex.org/W2916568594","https://openalex.org/W2954219808","https://openalex.org/W2954427512","https://openalex.org/W2990714382","https://openalex.org/W2995704514","https://openalex.org/W3048458458","https://openalex.org/W4220810253","https://openalex.org/W4233973673","https://openalex.org/W4281550828","https://openalex.org/W4285503949","https://openalex.org/W4321500415","https://openalex.org/W4327911434","https://openalex.org/W4379518528"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W2056396287","https://openalex.org/W3202552726","https://openalex.org/W2279642117"],"abstract_inverted_index":{"Dependence":[0],"between":[1],"iterations":[2],"in":[3],"sparse":[4,17,31,48,68],"computations":[5],"causes":[6],"inefficient":[7,73],"use":[8],"of":[9,29,38,67,110,120,128,144],"memory":[10,80],"and":[11,58,90,102,115,122,139],"computation":[12],"resources.":[13],"This":[14],"paper":[15],"proposes":[16],"fusion,":[18],"a":[19,86],"technique":[20],"that":[21],"generates":[22],"efficient":[23],"parallel":[24,95],"code":[25,91,97],"for":[26,99,146],"the":[27,39,63,108,126],"combination":[28],"two":[30],"matrix":[32],"kernels,":[33,69],"where":[34],"at":[35],"least":[36],"one":[37],"kernels":[40,49],"has":[41],"loop-carried":[42],"dependencies.":[43],"Existing":[44],"implementations":[45,112,130],"optimize":[46],"individual":[47],"separately.":[50],"However,":[51],"this":[52],"approach":[53],"leads":[54],"to":[55,62,77,93],"synchronization":[56],"overheads":[57],"load":[59,103],"imbalance":[60],"due":[61,76],"irregular":[64,79],"dependence":[65],"patterns":[66],"as":[70,72,136],"well":[71],"cache":[74],"usage":[75],"their":[78],"access":[81],"patterns.":[82],"Sparse":[83,105],"fusion":[84,106],"uses":[85],"novel":[87],"inspection":[88],"strategy":[89],"transformation":[92],"generate":[94],"fused":[96,129],"optimized":[98],"data":[100],"locality":[101],"balance.":[104],"outperforms":[107],"best":[109,127],"unfused":[111],"using":[113,131],"ParSy":[114],"MKL":[116],"by":[117,141],"an":[118,142],"average":[119,143],"4.2\u00d7":[121],"is":[123],"faster":[124],"than":[125],"existing":[132],"scheduling":[133],"algorithms,":[134],"such":[135],"LBC,":[137],"DAGP,":[138],"wavefront":[140],"4\u00d7":[145],"various":[147],"kernel":[148],"combinations.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
