{"id":"https://openalex.org/W1996353004","doi":"https://doi.org/10.1145/2082156.2082158","title":"The challenges of writing portable, correct and high performance libraries for GPUs","display_name":"The challenges of writing portable, correct and high performance libraries for GPUs","publication_year":2011,"publication_date":"2011-12-19","ids":{"openalex":"https://openalex.org/W1996353004","doi":"https://doi.org/10.1145/2082156.2082158","mag":"1996353004","pmid":"https://pubmed.ncbi.nlm.nih.gov/23807820"},"language":"en","primary_location":{"id":"doi:10.1145/2082156.2082158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082158","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5083047329","display_name":"Miriam Leeser","orcid":"https://orcid.org/0000-0002-5624-056X"},"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":"Miriam Leeser","raw_affiliation_strings":["Northeastern University, Boston, MA","Northeastern University, Boston (MA)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Northeastern University, Boston (MA)#TAB#","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034903859","display_name":"Devon Yablonski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123572","display_name":"Mercury Systems (United States)","ror":"https://ror.org/02rd7bb97","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123572"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devon Yablonski","raw_affiliation_strings":["Mercury Computer Systems, Chelmsford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mercury Computer Systems, Chelmsford, MA","institution_ids":["https://openalex.org/I4210123572"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079980080","display_name":"Dana H. Brooks","orcid":"https://orcid.org/0000-0003-3231-6715"},"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":"Dana Brooks","raw_affiliation_strings":["Northeastern University, Boston, MA","Northeastern University, Boston (MA)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Northeastern University, Boston (MA)#TAB#","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027561302","display_name":"Laurie Smith King","orcid":null},"institutions":[{"id":"https://openalex.org/I107139065","display_name":"College of the Holy Cross","ror":"https://ror.org/05dwp6855","country_code":"US","type":"education","lineage":["https://openalex.org/I107139065"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurie Smith King","raw_affiliation_strings":["College of the Holy Cross, Worcester, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of the Holy Cross, Worcester, MA","institution_ids":["https://openalex.org/I107139065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3908,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85148689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"39","issue":"4","first_page":"2","last_page":"7"},"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":0.9984999895095825,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8504666090011597},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.8003221750259399},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7115955352783203},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5949022769927979},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5452438592910767},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5450373888015747},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5042699575424194},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4507472813129425},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4326857328414917},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4112621247768402},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28745460510253906},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.26524895429611206},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16739115118980408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504666090011597},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8003221750259399},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7115955352783203},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5949022769927979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5452438592910767},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5450373888015747},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5042699575424194},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4507472813129425},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4326857328414917},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4112621247768402},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28745460510253906},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26524895429611206},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16739115118980408},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2082156.2082158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2082156.2082158","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"},{"id":"pmid:23807820","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23807820","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer architecture news","raw_type":null},{"id":"pmh:oai:europepmc.org:2685981","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3691863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1260651376","display_name":null,"funder_award_id":"P41GM103545","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7628412913","display_name":null,"funder_award_id":"P41 RR012553","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"},{"id":"https://openalex.org/F4320338121","display_name":"Center of Innovation Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1779740778","https://openalex.org/W1985462363","https://openalex.org/W2035080386","https://openalex.org/W2095292158","https://openalex.org/W2106621552","https://openalex.org/W2260378502","https://openalex.org/W2399715892"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W1662038552","https://openalex.org/W3021568819","https://openalex.org/W1500978221","https://openalex.org/W2352639277"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,51,208],"widely":[5],"used":[6],"to":[7,36,44,54,58,85,106,148,155,160,210,240,253],"accelerate":[8],"scientific":[9],"applications.":[10],"Many":[11],"successes":[12],"have":[13],"been":[14],"reported":[15],"with":[16,40,203,217],"speedups":[17,33],"of":[18,23,28,110,120,133,151,165,174,185,194,198,220,235,246,257],"two":[19],"or":[20],"three":[21],"orders":[22],"magnitude":[24],"over":[25],"serial":[26],"implementations":[27,50],"the":[29,63,70,111,121,123,137,162,166,172,183,192,195,204,218,224,233,255,258,266,272],"same":[30,64],"algorithms.":[31],"These":[32],"typically":[34],"pertain":[35],"a":[37,45,80,92,117,130,141,149,177,186],"specific":[38,46],"implementation":[39],"fixed":[41],"parameters":[42,114,153],"mapped":[43],"hardware":[47,68,122],"implementation.":[48],"The":[49,103],"not":[52],"designed":[53],"be":[55,73,146],"easily":[56],"ported":[57],"other":[59],"GPUs,":[60],"even":[61],"from":[62,191],"manufacturer.":[65],"When":[66],"target":[67,167,271],"changes,":[69],"application":[71],"must":[72,145],"re-optimized.":[74],"In":[75],"this":[76,251],"paper":[77],"we":[78,270],"address":[79],"different":[81,101,131,152,244],"problem.":[82],"We":[83,213,249],"aim":[84],"deliver":[86,107],"working,":[87],"efficient":[88],"GPU":[89,187,221,259],"code":[90],"in":[91,265],"library":[93],"that":[94],"is":[95,105,171,188],"downloaded":[96],"and":[97,115,159,200,280],"run":[98],"by":[99,260],"many":[100,243],"users.":[102],"issue":[104,170],"efficiency":[108],"independent":[109],"individual":[112],"user":[113,124,206],"without":[116],"priori":[118],"knowledge":[119],"will":[125],"employ.":[126],"This":[127],"problem":[128],"requires":[129],"set":[132],"tradeoffs":[134],"than":[135],"finding":[136],"best":[138,163],"runtime":[139],"for":[140,283],"single":[142],"solution.":[143],"Solutions":[144],"adaptable":[147],"range":[150],"both":[154],"solve":[156],"users'":[157],"problems":[158],"make":[161],"use":[164,184,199,250],"hardware.":[168],"Another":[169],"integration":[173],"GPUs":[175],"into":[176,223],"Problem":[178],"Solving":[179],"Environment":[180],"(PSE)":[181],"where":[182],"almost":[189],"invisible":[190],"perspective":[193],"user.":[196],"Ease":[197],"smooth":[201],"interactions":[202],"existing":[205],"interface":[207],"important":[209],"our":[211,215],"approach.":[212],"illustrate":[214],"solution":[216],"incorporation":[219],"processing":[222],"Scientific":[225],"Computing":[226],"Institute":[227],"(SCI)Run":[228],"Biomedical":[229],"PSE":[230],"developed":[231],"at":[232],"University":[234],"Utah.":[236],"SCIRun":[237],"allows":[238],"scientists":[239],"interactively":[241],"construct":[242],"types":[245],"biomedical":[247],"simulations.":[248,268],"environment":[252],"demonstrate":[254],"effectiveness":[256],"accelerating":[261],"time":[262],"consuming":[263],"algorithms":[264],"scientist's":[267],"Specifically":[269],"linear":[273],"solver":[274],"module,":[275],"including":[276],"Conjugate":[277],"Gradient,":[278],"Jacobi":[279],"MinRes":[281],"solvers":[282],"sparse":[284],"matrices.":[285]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}