{"id":"https://openalex.org/W4220810253","doi":"https://doi.org/10.1145/3503221.3508439","title":"Optimizing sparse computations jointly","display_name":"Optimizing sparse computations jointly","publication_year":2022,"publication_date":"2022-03-28","ids":{"openalex":"https://openalex.org/W4220810253","doi":"https://doi.org/10.1145/3503221.3508439"},"language":"en","primary_location":{"id":"doi:10.1145/3503221.3508439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503221.3508439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/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":true,"raw_author_name":"Kazem Cheshmi","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Mills Strout","raw_affiliation_strings":["University of Arizona"],"affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["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":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"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/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.6812,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64098269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"460"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983999729156494,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9973999857902527,"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":0.7966067790985107},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6909884810447693},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6885821223258972},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6704087257385254},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6191508769989014},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5743404626846313},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4910392761230469},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.49096181988716125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35994619131088257},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13277378678321838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966067790985107},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6909884810447693},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6885821223258972},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6704087257385254},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6191508769989014},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5743404626846313},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4910392761230469},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.49096181988716125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35994619131088257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13277378678321838},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503221.3508439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503221.3508439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7260959885","display_name":null,"funder_award_id":"CCF- 1657175,CCF-1814888, ACI-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1840953097","https://openalex.org/W2035080386","https://openalex.org/W2043701535","https://openalex.org/W2047937722","https://openalex.org/W2566719947","https://openalex.org/W2614185560","https://openalex.org/W2883867401","https://openalex.org/W2898106867","https://openalex.org/W2902699695","https://openalex.org/W2954219808","https://openalex.org/W2954427512","https://openalex.org/W3048458458"],"related_works":["https://openalex.org/W2186864281","https://openalex.org/W3093936885","https://openalex.org/W4255427455","https://openalex.org/W2994146737","https://openalex.org/W1966025497","https://openalex.org/W295308437","https://openalex.org/W2992046671","https://openalex.org/W233983175","https://openalex.org/W2355089277","https://openalex.org/W2312486021"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,110,171],"framework":[4],"called":[5,71],"FuSy":[6],"that":[7,99,115,156],"analyzes":[8,100],"the":[9,25,77,101,118,126,135,167,176],"data":[10],"dependence":[11],"graphs":[12],"(DAGs)":[13],"of":[14,76,103,113,128,173],"two":[15,104,119,140],"sparse":[16,61,66,84,105],"kernels":[17,26,30,58,85,106,120],"and":[18,37,42,65,92,107,144,163],"creates":[19,109],"an":[20,55,97],"efficient":[21],"schedule":[22],"to":[23,88],"execute":[24],"in":[27,34,38,48,73,122,150],"combination.":[28,49],"Sparse":[29],"are":[31,46,54,70,147],"frequently":[32],"used":[33,47,149],"scientific":[35],"codes":[36],"machine":[39],"learning":[40],"algorithms":[41],"very":[43],"often":[44],"they":[45],"Iterative":[50],"linear":[51],"system":[52],"solvers":[53],"example":[56],"where":[57],"such":[59],"as":[60],"triangular":[62],"solver":[63],"(SpTRSV)":[64],"matrix-vector":[67],"multiplication":[68],"(SpMV)":[69],"consecutively":[72],"each":[74],"iteration":[75],"solver.":[78],"Prior":[79],"approaches":[80],"typically":[81],"optimize":[82],"these":[83],"independently":[86],"leading":[87],"high":[89],"synchronization":[90],"overheads":[91],"low":[93],"locality.":[94],"We":[95],"propose":[96],"approach":[98,158],"DAGs":[102],"then":[108],"new":[111],"order":[112],"execution":[114],"enables":[116],"running":[117],"efficiently":[121],"parallel.":[123],"To":[124],"investigate":[125],"efficiency":[127],"our":[129,157],"approach,":[130],"we":[131],"compare":[132],"it":[133],"with":[134],"state-of-the-art":[136],"MKL":[137,168],"library":[138,169],"for":[139,170],"kernel":[141],"combinations,":[142],"SpTRSV-SpMV":[143],"SpMV-SpTRSV":[145],"which":[146],"commonly":[148],"iterative":[151],"solvers.":[152],"Experimental":[153],"results":[154],"show":[155],"is":[159],"on":[160],"average":[161],"2.6X":[162],"1.8X":[164],"faster":[165],"than":[166],"set":[172],"matrices":[174],"from":[175],"Suitesparse":[177],"matrix":[178],"repository.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}