{"id":"https://openalex.org/W4409131817","doi":"https://doi.org/10.1109/hpec62836.2024.10938441","title":"MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks","display_name":"MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409131817","doi":"https://doi.org/10.1109/hpec62836.2024.10938441"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5092010614","display_name":"Tal Kadosh","orcid":"https://orcid.org/0009-0000-8332-9079"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tal Kadosh","raw_affiliation_strings":["Ben-Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071259938","display_name":"Niranjan Hasabnis","orcid":"https://orcid.org/0009-0004-4010-7213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niranjan Hasabnis","raw_affiliation_strings":["Code Metal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Code Metal","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018108126","display_name":"Vy A. Vo","orcid":"https://orcid.org/0000-0001-9601-1297"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vy A. Vo","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083904464","display_name":"Nadav Schneider","orcid":"https://orcid.org/0000-0002-3838-5482"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nadav Schneider","raw_affiliation_strings":["Ben-Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092671710","display_name":"Neva Krien","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Neva Krien","raw_affiliation_strings":["Ben-Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047526567","display_name":"Mihai Capot\u0103","orcid":"https://orcid.org/0000-0002-7323-2393"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihai Capot\u0103","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059201002","display_name":"Abdul Wasay","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdul Wasay","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060359945","display_name":"Guy Tamir","orcid":"https://orcid.org/0009-0002-6160-0678"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy Tamir","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055703000","display_name":"Ted Willke","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Willke","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059294839","display_name":"Nesreen K. Ahmed","orcid":"https://orcid.org/0000-0002-7913-4962"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nesreen Ahmed","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008477284","display_name":"Yuval Pinter","orcid":"https://orcid.org/0000-0003-3174-1621"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Pinter","raw_affiliation_strings":["Ben-Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048097160","display_name":"Timothy G. Mattson","orcid":"https://orcid.org/0000-0002-6106-8717"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Timothy Mattson","raw_affiliation_strings":["Ben-Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben-Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030616543","display_name":"Gal Oren","orcid":"https://orcid.org/0000-0002-8831-5423"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gal Oren","raw_affiliation_strings":["Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9835000038146973,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9835000038146973,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7946922779083252},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6686408519744873},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.6135201454162598},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5291683673858643},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48378679156303406},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46134263277053833},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3937128186225891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.326571524143219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946922779083252},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6686408519744873},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.6135201454162598},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5291683673858643},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48378679156303406},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46134263277053833},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3937128186225891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.326571524143219},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320323051","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982"},{"id":"https://openalex.org/F4320325704","display_name":"PAZY Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2762767331","https://openalex.org/W2912530233","https://openalex.org/W2969133273","https://openalex.org/W3081844928","https://openalex.org/W3095319910","https://openalex.org/W3212766292","https://openalex.org/W4317602012","https://openalex.org/W4320480737","https://openalex.org/W4321446116","https://openalex.org/W4386268988","https://openalex.org/W4388581326","https://openalex.org/W4388581500","https://openalex.org/W4396790347","https://openalex.org/W4402047561"],"related_works":["https://openalex.org/W2056396287","https://openalex.org/W2057033141","https://openalex.org/W4252103056","https://openalex.org/W2917823318","https://openalex.org/W2917572814","https://openalex.org/W4242858628","https://openalex.org/W2979406678","https://openalex.org/W2915857720","https://openalex.org/W2916715723","https://openalex.org/W3006129753"],"abstract_inverted_index":{"With":[0],"easier":[1],"access":[2],"to":[3,17,23,33,93,105,203],"powerful":[4],"compute":[5,48],"resources,":[6],"there":[7],"is":[8,53,142,234],"a":[9,25,133],"growing":[10],"trend":[11],"in":[12,43],"AI":[13],"for":[14,50,57,95,118,212],"software":[15],"development":[16],"develop":[18],"large":[19],"language":[20,115],"models":[21,116],"(LLMs)":[22],"address":[24],"variety":[26],"of":[27,101,144,168,180],"programming":[28,71,90],"tasks.":[29],"Even":[30],"LLMs":[31,56,65,84,111,197],"applied":[32],"tasks":[34,59],"from":[35,174],"the":[36,178],"high-performance":[37,213],"computing":[38],"(HPC)":[39],"domain":[40,134],"are":[41,60],"huge":[42],"size":[44],"and":[45,89,135,156,170,214],"demand":[46],"expensive":[47],"resources":[49],"training.":[51],"This":[52],"partly":[54],"because":[55],"HPC":[58,94,131,157,225],"obtained":[61],"by":[62,109,112],"finetuning":[63],"existing":[64,110,148,193],"that":[66,188,223],"support":[67],"several":[68],"natural":[69,87],"and/or":[70],"languages.":[72],"We":[73,176],"found":[74],"this":[75,99],"design":[76],"choice":[77],"confusing":[78],"-":[79,121],"why":[80],"do":[81],"we":[82,103,122,128,160],"need":[83],"trained":[85],"on":[86,154,198],"languages":[88,91],"unrelated":[92],"HPC-specific":[96,138,164],"tasks?":[97],"In":[98,218],"line":[100],"work,":[102],"aim":[104],"question":[106],"choices":[107],"made":[108],"developing":[113],"smaller":[114,146,191],"(LMs)":[117],"specific":[119],"domains":[120],"call":[123],"them":[124],"domain-specific":[125],"LMs.":[126],"Specifically,":[127,159],"start":[129],"with":[130],"as":[132],"build":[136],"an":[137,163],"LM,":[139],"named":[140],"MonoCoder,which":[141],"orders":[143],"magnitude":[145],"than":[147,192,228],"LMs":[149],"but":[150],"delivers":[151],"better":[152,227],"performance":[153,179],"non-HPC":[155],"codes.":[158],"pretrained":[161],"MonoCoderon":[162],"dataset":[165],"(named":[166],"HPCORPUS)":[167],"C":[169],"C++":[171],"programs":[172],"mined":[173],"GitHub.":[175],"evaluated":[177],"MonoCoder":[181],"against":[182],"state-of-the-art":[183,229],"multi-lingual":[184],"LLMs.":[185,230],"Results":[186],"demonstrate":[187],"MonoCoder,although":[189],"much":[190],"LMs,":[194],"outperforms":[195],"other":[196,219],"normalized-perplexity":[199],"tests":[200],"(in":[201],"relation":[202],"model":[204],"size)":[205],"while":[206],"also":[207],"delivering":[208],"competing":[209],"CodeBLEU":[210],"scores":[211],"parallel":[215],"code":[216,226,233],"generations.":[217],"words,":[220],"results":[221],"suggest":[222],"MonoCoderunderstands":[224],"Mono":[231],"Codersource":[232],"available":[235],"at":[236],"our":[237],"GitHub":[238],"repository.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}