{"id":"https://openalex.org/W2771946537","doi":"https://doi.org/10.1109/iiswc.2017.8167754","title":"AutoMatch: An automated framework for relative performance estimation and workload distribution on heterogeneous HPC systems","display_name":"AutoMatch: An automated framework for relative performance estimation and workload distribution on heterogeneous HPC systems","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771946537","doi":"https://doi.org/10.1109/iiswc.2017.8167754","mag":"2771946537"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2017.8167754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2017.8167754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","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/A5090060327","display_name":"Ahmed E. Helal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107680","display_name":"\u00c9cole Nationale des Greffes","ror":"https://ror.org/01pcs0h38","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210107680"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ahmed E. Helal","raw_affiliation_strings":["Electrical and Computer Eng"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Eng","institution_ids":["https://openalex.org/I4210107680"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I4210107680","display_name":"\u00c9cole Nationale des Greffes","ror":"https://ror.org/01pcs0h38","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210107680"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Electrical and Computer Eng","Virginia Tech, Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Eng","institution_ids":["https://openalex.org/I4210107680"]},{"raw_affiliation_string":"Virginia Tech, Computer Science","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102903612","display_name":"Changhee Jung","orcid":"https://orcid.org/0000-0002-6422-6549"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhee Jung","raw_affiliation_strings":["Virginia Tech, Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Computer Science","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058341329","display_name":"Yasser Y. Hanafy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107680","display_name":"\u00c9cole Nationale des Greffes","ror":"https://ror.org/01pcs0h38","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210107680"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yasser Y. Hanafy","raw_affiliation_strings":["Electrical and Computer Eng"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Eng","institution_ids":["https://openalex.org/I4210107680"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0808,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89014279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"127","issue":null,"first_page":"32","last_page":"42"},"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":0.9998000264167786,"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":0.9994999766349792,"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/workload","display_name":"Workload","score":0.8212175369262695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281542420387268},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5035890936851501},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.373957097530365},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2087501585483551},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09398534893989563},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09153050184249878}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8212175369262695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281542420387268},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5035890936851501},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.373957097530365},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2087501585483551},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09398534893989563},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09153050184249878}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iiswc.2017.8167754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2017.8167754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W41300326","https://openalex.org/W842872497","https://openalex.org/W1489767088","https://openalex.org/W1850405760","https://openalex.org/W1974872983","https://openalex.org/W1979582240","https://openalex.org/W1982008063","https://openalex.org/W1992558790","https://openalex.org/W2006785118","https://openalex.org/W2009215380","https://openalex.org/W2035080386","https://openalex.org/W2038142281","https://openalex.org/W2050487400","https://openalex.org/W2055084740","https://openalex.org/W2078794610","https://openalex.org/W2080592089","https://openalex.org/W2084660366","https://openalex.org/W2089064856","https://openalex.org/W2105321788","https://openalex.org/W2110195531","https://openalex.org/W2111127986","https://openalex.org/W2117689653","https://openalex.org/W2124333827","https://openalex.org/W2131645097","https://openalex.org/W2147801215","https://openalex.org/W2150329270","https://openalex.org/W2153185479","https://openalex.org/W2154713585","https://openalex.org/W2159481344","https://openalex.org/W2164705534","https://openalex.org/W2167334577","https://openalex.org/W2239144794","https://openalex.org/W2273440736","https://openalex.org/W2275977038","https://openalex.org/W2342906597","https://openalex.org/W2436525433","https://openalex.org/W2506485539","https://openalex.org/W2508088496","https://openalex.org/W2745803261","https://openalex.org/W3000120212","https://openalex.org/W4242339253","https://openalex.org/W4249904046","https://openalex.org/W4285719527","https://openalex.org/W6623314183","https://openalex.org/W6675903601","https://openalex.org/W6676579300","https://openalex.org/W6694302311","https://openalex.org/W6694513646","https://openalex.org/W6743379173"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W950578619"],"abstract_inverted_index":{"Porting":[0],"sequential":[1,138,160,228],"applications":[2,64,212,229],"to":[3,13,19,56,117,128,148,219,237],"heterogeneous":[4,118,163],"HPC":[5,119,164,188,211,245],"systems":[6],"requires":[7],"extensive":[8],"software":[9],"and":[10,18,86,125,174,230],"hardware":[11,185],"expertise":[12],"estimate":[14],"the":[15,22,45,57,75,83,94,130,154,159,172,178,183,200,224,233,238,256],"potential":[16],"speedup":[17,77,84,225],"efficiently":[20],"use":[21],"available":[23,201],"compute":[24,115],"resources":[25],"in":[26,203],"such":[27,167],"systems.":[28],"To":[29],"streamline":[30],"this":[31],"daunting":[32],"process,":[33],"researchers":[34],"have":[35],"proposed":[36],"several":[37],"\u201cblack-box\u201d":[38],"performance":[39,46,241,257],"prediction":[40],"approaches":[41,80],"that":[42,196],"rely":[43],"on":[44,162],"of":[47,51,59,63,114,135,153,158,209,227,255,258],"a":[48,60,136,146,150,168,207,259],"training":[49],"set":[50,62,208],"parallel":[52,69,96,133,156,234,240],"applications.":[53],"However,":[54],"due":[55],"lack":[58],"diverse":[61],"along":[65],"with":[66,213],"their":[67],"optimized":[68,155],"implementations":[70,97],"for":[71,101,112],"each":[72],"architecture":[73],"type,":[74],"predicted":[76],"by":[78],"these":[79],"is":[81,236],"not":[82,99],"upper-bound,":[85],"even":[87],"worse":[88],"it":[89],"can":[90],"be":[91,220],"misleading,":[92],"if":[93],"reference":[95],"are":[98],"equally-optimized":[100],"every":[102],"target":[103],"architecture.":[104],"This":[105],"paper":[106],"presents":[107],"AutoMatch,":[108],"an":[109],"automated":[110],"framework":[111],"matching":[113],"kernels":[116],"architectures.":[120,246],"AutoMatch":[121,190,216],"uses":[122],"hybrid":[123],"(static":[124],"dynamic)":[126],"analysis":[127],"find":[129],"best":[131,239],"dependency-preserving":[132],"schedule":[134,143],"given":[137],"code.":[139],"The":[140],"resulting":[141],"operations":[142],"serves":[144],"as":[145],"basis":[147],"construct":[149],"cost":[151,169,181],"function":[152,170],"execution":[157,180],"code":[161],"nodes.":[165],"Since":[166],"informs":[171],"user":[173],"runtime":[175,193],"system":[176],"about":[177],"relative":[179],"across":[182,242],"different":[184,214,244],"devices":[186,202],"within":[187],"nodes,":[189],"enables":[191],"efficient":[192],"workload":[194,249],"distribution":[195,250],"simultaneously":[197],"utilizes":[198],"all":[199],"performance-proportional":[204],"way.":[205],"For":[206],"open-source":[210],"characteristics,":[215],"turns":[217],"out":[218],"very":[221],"effective,":[222],"identifying":[223],"upper-bound":[226],"how":[231],"close":[232],"implementation":[235],"five":[243],"Furthermore,":[247],"AutoMatch's":[248],"scheme":[251],"achieves":[252],"approximately":[253],"90%":[254],"profiling-driven":[260],"oracle.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}