{"id":"https://openalex.org/W4220818654","doi":"https://doi.org/10.1109/cgo53902.2022.9741270","title":"Automatic Horizontal Fusion for GPU Kernels","display_name":"Automatic Horizontal Fusion for GPU Kernels","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4220818654","doi":"https://doi.org/10.1109/cgo53902.2022.9741270"},"language":"en","primary_location":{"id":"doi:10.1109/cgo53902.2022.9741270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5100359729","display_name":"Ao Li","orcid":"https://orcid.org/0000-0001-9910-8967"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ao Li","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053912518","display_name":"Bojian Zheng","orcid":"https://orcid.org/0000-0002-1999-2359"},"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":"Bojian Zheng","raw_affiliation_strings":["University of Toronto,Canada","University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007585346","display_name":"Gennady Pekhimenko","orcid":"https://orcid.org/0000-0002-3839-0919"},"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":"Gennady Pekhimenko","raw_affiliation_strings":["University of Toronto,Canada","University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087318419","display_name":"Fan Long","orcid":null},"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":"Fan Long","raw_affiliation_strings":["University of Toronto,Canada","University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100359729"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":8.1593,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98171615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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":0.9955999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7921576499938965},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.7192386388778687},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6972469091415405},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6857075691223145},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6619089841842651},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6196439266204834},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.47132638096809387},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3457331657409668},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1557357907295227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07105246186256409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921576499938965},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.7192386388778687},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6972469091415405},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6857075691223145},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6619089841842651},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6196439266204834},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.47132638096809387},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3457331657409668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1557357907295227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07105246186256409},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo53902.2022.9741270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322015","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087"},{"id":"https://openalex.org/F4320324245","display_name":"Connaught Fund","ror":"https://ror.org/03dbr7087"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463","https://openalex.org/W1977763331","https://openalex.org/W4318483369","https://openalex.org/W2076165488"],"abstract_inverted_index":{"We":[0,46],"present":[1,48],"automatic":[2,59],"horizontal":[3,33,60,68,84],"fusion,":[4,22],"a":[5,50,102,106],"novel":[6],"optimization":[7],"technique":[8,35],"that":[9,57,66,82,94],"complements":[10],"the":[11,20,39,67,73,83],"standard":[12,21],"kernel":[13,104],"fusion":[14,34,69,85],"techniques":[15],"for":[16,89],"GPU":[17,99],"programs.":[18],"Unlike":[19],"whose":[23],"goal":[24],"is":[25,86],"to":[26,37,42,53],"eliminate":[27],"intermediate":[28],"data":[29],"round":[30],"trips,":[31],"our":[32],"aims":[36],"increase":[38],"thread-level":[40],"parallelism":[41],"hide":[43],"instruction":[44],"latencies.":[45],"also":[47],"HFUSE,":[49],"new":[51],"source":[52,54],"CUDA":[55],"compiler":[56],"implements":[58],"fusion.":[61],"Our":[62,79],"experimental":[63],"results":[64,80],"show":[65],"can":[70],"speed":[71],"up":[72],"running":[74],"time":[75],"by":[76],"2.5%":[77],"60.8%.":[78],"reveal":[81],"especially":[87],"beneficial":[88],"fusing":[90],"kernels":[91],"with":[92],"instructions":[93],"require":[95],"different":[96],"kinds":[97],"of":[98],"resources":[100],"(e.g.,":[101],"memory-intensive":[103],"and":[105],"compute-intensive":[107],"kernel).":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}