{"id":"https://openalex.org/W4362675250","doi":"https://doi.org/10.1145/3585341.3585359","title":"Profile Guided Optimization Transfer-Learning for OpenCL/SYCL Kernel Compilation and Runtime","display_name":"Profile Guided Optimization Transfer-Learning for OpenCL/SYCL Kernel Compilation and Runtime","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362675250","doi":"https://doi.org/10.1145/3585341.3585359"},"language":"en","primary_location":{"id":"doi:10.1145/3585341.3585359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585341.3585359","pdf_url":null,"source":{"id":"https://openalex.org/S4306420323","display_name":"International Workshop on OpenCL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","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/A5068829304","display_name":"Wenju He","orcid":"https://orcid.org/0009-0003-1012-8921"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenju He","raw_affiliation_strings":["Intel, China"],"raw_orcid":"https://orcid.org/0009-0003-1012-8921","affiliations":[{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068395016","display_name":"Maosu Zhao","orcid":"https://orcid.org/0009-0007-0747-4099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosu Zhao","raw_affiliation_strings":["Intel, China"],"raw_orcid":"https://orcid.org/0009-0007-0747-4099","affiliations":[{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102995881","display_name":"Yuxin Zou","orcid":"https://orcid.org/0000-0003-4347-2051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxin Zou","raw_affiliation_strings":["Intel, China"],"raw_orcid":"https://orcid.org/0000-0003-4347-2051","affiliations":[{"raw_affiliation_string":"Intel, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033484023","display_name":"Feng Zou","orcid":"https://orcid.org/0009-0006-9892-3613"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Zou","raw_affiliation_strings":["Intel, China"],"raw_orcid":"https://orcid.org/0009-0006-9892-3613","affiliations":[{"raw_affiliation_string":"Intel, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068829304"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09859155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8649487495422363},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7377051115036011},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7039462924003601},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.649197518825531},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5882700085639954},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5781083703041077},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4915812909603119},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38745084404945374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8649487495422363},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7377051115036011},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7039462924003601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.649197518825531},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5882700085639954},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5781083703041077},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4915812909603119},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38745084404945374},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3585341.3585359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585341.3585359","pdf_url":null,"source":{"id":"https://openalex.org/S4306420323","display_name":"International Workshop on OpenCL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on OpenCL","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2080592089","https://openalex.org/W3094876077","https://openalex.org/W3209449653"],"related_works":["https://openalex.org/W2479014312","https://openalex.org/W1583465708","https://openalex.org/W2348361596","https://openalex.org/W1601646354","https://openalex.org/W4235959758","https://openalex.org/W4245265375","https://openalex.org/W2078700326","https://openalex.org/W1853049011","https://openalex.org/W1508811940","https://openalex.org/W2348711589"],"abstract_inverted_index":{"Reducing":[0],"SYCL":[1,36],"kernel":[2,37,58],"compilation":[3,38,59],"time":[4],"and":[5,39],"overhead":[6,85],"of":[7],"runtime":[8,84],"are":[9],"important":[10],"topics":[11],"for":[12],"heterogeneous":[13],"computing":[14],"performance.":[15],"Profile-Guided":[16],"Optimization":[17],"(PGO)":[18],"is":[19],"an":[20],"optimization":[21],"technique":[22],"widely":[23],"used":[24,79],"in":[25,86],"compiler":[26],"to":[27,34,80],"better":[28],"optimize":[29],"code.":[30],"We":[31],"apply":[32],"PGO":[33],"both":[35],"backend":[40,83],"runtime.":[41],"The":[42,63],"first":[43],"experiment":[44,65],"demonstrates":[45,67],"transfer-learning":[46,68],"that":[47,69],"profiling":[48,70],"data":[49,71],"collected":[50,72],"from":[51,73],"SPEC":[52],"CPU\u00ae":[53],"2006":[54],"benchmark":[55],"can":[56],"benefit":[57],"on":[60],"OpenCL/SYCL":[61,75],"benchmarks.":[62,88],"second":[64],"also":[66],"some":[74],"benchmarks":[76],"could":[77],"be":[78],"reduce":[81],"CPU":[82],"unseen":[87]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}