{"id":"https://openalex.org/W4362675398","doi":"https://doi.org/10.1145/3585341.3585364","title":"Machine Learning for Vectorization Decision in OpenCL/SYCL Kernel","display_name":"Machine Learning for Vectorization Decision in OpenCL/SYCL Kernel","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362675398","doi":"https://doi.org/10.1145/3585341.3585364"},"language":"en","primary_location":{"id":"doi:10.1145/3585341.3585364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585341.3585364","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/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":3,"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":0.12676056,"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":0.996999979019165,"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":0.996999979019165,"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":0.9879999756813049,"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":0.9580000042915344,"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":0.8683574199676514},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7291946411132812},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7065412998199463},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.680446207523346},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6567072868347168},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4952649176120758},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.46418991684913635},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.43504226207733154},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.43316033482551575},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2777545154094696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23512759804725647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05766940116882324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8683574199676514},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7291946411132812},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7065412998199463},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.680446207523346},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6567072868347168},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4952649176120758},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.46418991684913635},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43504226207733154},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.43316033482551575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2777545154094696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23512759804725647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05766940116882324},{"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:10.1145/3585341.3585364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3585341.3585364","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3209449653","https://openalex.org/W4206284583","https://openalex.org/W4292907573","https://openalex.org/W6600788304"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W1908180445","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W2035419609","https://openalex.org/W2056079253","https://openalex.org/W2912502764","https://openalex.org/W1766386015","https://openalex.org/W2895895456","https://openalex.org/W2929736795"],"abstract_inverted_index":{"Vectorization":[0],"of":[1],"OpenCL/SYCL":[2],"kernel":[3],"on":[4,77],"CPU":[5,52,82],"device":[6,53],"could":[7,41],"improve":[8],"performance":[9],"significantly.":[10],"It":[11],"utilizes":[12],"single":[13],"instruction":[14,18],"multiple":[15,21],"data":[16],"(SIMD)":[17],"to":[19,32,45,57,60,71],"process":[20],"work-items":[22],"concurrently.":[23],"However,":[24],"some":[25],"applications":[26],"don't":[27],"benefit":[28],"from":[29,43],"vectorization.":[30],"Whether":[31],"do":[33],"vectorization":[34],"is":[35,87],"a":[36,67],"challenging":[37],"problem,":[38],"since":[39],"it":[40],"vary":[42],"case":[44],"case.":[46],"For":[47],"OpenCL":[48],"kernels,":[49],"Intel":[50,78],"SYCL":[51],"currently":[54],"uses":[55],"heuristic":[56,91],"decide":[58],"whether":[59],"discard":[61],"vectorized":[62],"kernel.":[63],"This":[64],"paper":[65],"presents":[66],"machine":[68],"learning":[69],"approach":[70,86],"tackle":[72],"this":[73],"problem.":[74],"Experimental":[75],"result":[76],"Xeon":[79],"Cascade":[80],"Lake":[81],"demonstrates":[83],"the":[84,90],"new":[85],"better":[88],"than":[89],"approach.":[92]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}