{"id":"https://openalex.org/W7131100494","doi":"https://doi.org/10.1109/cgo68049.2026.11395237","title":"PASTA: A Modular Program Analysis Tool Framework for Accelerators","display_name":"PASTA: A Modular Program Analysis Tool Framework for Accelerators","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7131100494","doi":"https://doi.org/10.1109/cgo68049.2026.11395237"},"language":null,"primary_location":{"id":"doi:10.1109/cgo68049.2026.11395237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5126632763","display_name":"Mao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mao Lin","raw_affiliation_strings":["University of California,Merced,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Merced,USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081531196","display_name":"Hyeran Jeon","orcid":"https://orcid.org/0000-0002-1767-8198"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyeran Jeon","raw_affiliation_strings":["University of California,Merced,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Merced,USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063326523","display_name":"Keren Zhou","orcid":"https://orcid.org/0000-0002-7977-3182"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keren Zhou","raw_affiliation_strings":["George Mason University,USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126632763"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88345558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"520","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1120000034570694,"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":0.1120000034570694,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.07069999724626541,"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/T10559","display_name":"Particle Accelerators and Free-Electron Lasers","score":0.05810000002384186,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7419000267982483},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6496999859809875},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5181000232696533},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5149000287055969},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/program-analysis","display_name":"Program analysis","score":0.4918999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906000018119812},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6496999859809875},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4650999903678894},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.435699999332428},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo68049.2026.11395237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W118742224","https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2789572737","https://openalex.org/W2949486320","https://openalex.org/W2979340153","https://openalex.org/W2983717258","https://openalex.org/W3012479151","https://openalex.org/W3042369493","https://openalex.org/W3132094421","https://openalex.org/W3174529902","https://openalex.org/W3181838507","https://openalex.org/W3204998121","https://openalex.org/W3209568355","https://openalex.org/W4214707742","https://openalex.org/W4293213271","https://openalex.org/W4327911463","https://openalex.org/W4381894554","https://openalex.org/W4404954461","https://openalex.org/W4404954692","https://openalex.org/W4405755849","https://openalex.org/W4405756380","https://openalex.org/W4407217670","https://openalex.org/W4408847715","https://openalex.org/W4409060008","https://openalex.org/W4411486597","https://openalex.org/W4412610672","https://openalex.org/W4414976983","https://openalex.org/W4416203860"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"and":[3,23,37,49,61,89,103,109,156],"diversity":[4],"of":[5,75],"hardware":[6],"accelerators":[7],"in":[8],"modern":[9,162],"computing":[10,164],"systems":[11],"demand":[12],"flexible,":[13],"low-overhead":[14,22],"program":[15],"analysis":[16,80,141],"tools.":[17],"We":[18,71],"present":[19],"PASTA,":[20],"a":[21,44,150],"modular":[24],"Program":[25],"AnalysiS":[26],"Tool":[27],"Framework":[28],"for":[29,84,161],"Accelerators.":[30],"PASTA":[31,76,124,148],"abstracts":[32],"over":[33],"low-level":[34],"profiling":[35],"APIs":[36],"diverse":[38],"deep":[39,85,97],"learning":[40,86,98],"frameworks,":[41],"offering":[42],"users":[43],"unified":[45],"interface":[46],"to":[47,63,134,144],"capture":[48],"analyze":[50],"runtime":[51],"events":[52],"at":[53],"multiple":[54],"levels.":[55],"Its":[56],"extensible":[57],"design":[58],"enables":[59],"researchers":[60],"practitioners":[62],"rapidly":[64],"prototype":[65],"custom":[66],"tools":[67,83],"with":[68,129],"minimal":[69],"overhead.":[70],"demonstrate":[72,113],"the":[73],"utility":[74],"by":[77],"developing":[78],"several":[79],"tools,":[81,142],"including":[82],"workload":[87],"characterization":[88],"UVM":[90],"optimization.":[91],"Through":[92],"extensive":[93],"evaluations":[94],"on":[95,101],"mainstream":[96],"workloads":[99],"tested":[100],"NVIDIA":[102,118],"AMD":[104],"GPUs":[105],"under":[106],"both":[107],"single-":[108],"multi-GPU":[110],"scenarios,":[111],"we":[112,120],"PASTA\u2019s":[114],"broad":[115],"applicability.":[116],"On":[117],"GPUs,":[119],"further":[121],"show":[122],"that":[123],"provides":[125],"detailed":[126],"performance":[127],"insights":[128],"significantly":[130],"lower":[131],"overhead":[132],"(up":[133],"1.3\u00d710<sup":[135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</sup>":[137],"faster)":[138],"than":[139],"conventional":[140],"thanks":[143],"its":[145],"GPU-accelerated":[146],"backend.":[147],"strikes":[149],"practical":[151],"balance":[152],"between":[153],"usability,":[154],"extensibility,":[155],"efficiency,":[157],"making":[158],"it":[159],"well-suited":[160],"accelerator-based":[163],"environments.":[165]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}