{"id":"https://openalex.org/W3121315393","doi":"https://doi.org/10.1109/cgo51591.2021.9370324","title":"C-for-Metal: High Performance Simd Programming on Intel GPUs","display_name":"C-for-Metal: High Performance Simd Programming on Intel GPUs","publication_year":2021,"publication_date":"2021-02-27","ids":{"openalex":"https://openalex.org/W3121315393","doi":"https://doi.org/10.1109/cgo51591.2021.9370324","mag":"3121315393"},"language":"en","primary_location":{"id":"doi:10.1109/cgo51591.2021.9370324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.11049","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090031333","display_name":"Guei-Yuan Lueh","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":true,"raw_author_name":"Guei-Yuan Lueh","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022122751","display_name":"Kaiyu Chen","orcid":"https://orcid.org/0000-0002-4464-0953"},"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":"Kaiyu Chen","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"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":"Gang Chen","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009779958","display_name":"Joel Fuentes","orcid":"https://orcid.org/0000-0003-0517-1231"},"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":"Joel Fuentes","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373298","display_name":"Wei-Yu Chen","orcid":"https://orcid.org/0000-0001-8922-3988"},"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":"Wei-Yu Chen","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100815128","display_name":"Fangwen Fu","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":"Fangwen Fu","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"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":"Hong Jiang","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695040","display_name":"Wanqing Li","orcid":"https://orcid.org/0000-0002-4427-2687"},"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":"Hongzheng Li","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel Corp., Santa Clara, CA, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corp., Santa Clara, CA, , USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026444349","display_name":"Daniel Rhee","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":"Daniel Rhee","raw_affiliation_strings":["Intel Corporation, Santa Clara, CA, USA","Intel,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel,,,,,","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5090031333"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0122643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"300"},"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":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8689413070678711},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8580974340438843},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.755588710308075},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6907471418380737},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6530832648277283},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.61448073387146},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.4336293935775757},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4296847879886627},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3206997513771057},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2180212438106537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689413070678711},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8580974340438843},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.755588710308075},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6907471418380737},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6530832648277283},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.61448073387146},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.4336293935775757},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4296847879886627},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3206997513771057},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2180212438106537}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cgo51591.2021.9370324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo51591.2021.9370324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.11049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.11049","pdf_url":"https://arxiv.org/pdf/2101.11049","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3121315393","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.11049.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.11049","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.11049","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.11049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.11049","pdf_url":"https://arxiv.org/pdf/2101.11049","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3121315393.pdf","grobid_xml":"https://content.openalex.org/works/W3121315393.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W110609005","https://openalex.org/W1561994953","https://openalex.org/W1790519466","https://openalex.org/W1954658694","https://openalex.org/W1994316441","https://openalex.org/W2028499920","https://openalex.org/W2081245617","https://openalex.org/W2087977509","https://openalex.org/W2107911628","https://openalex.org/W2122078011","https://openalex.org/W2151641736","https://openalex.org/W2153185479","https://openalex.org/W2161351786","https://openalex.org/W2162569557","https://openalex.org/W2167675119","https://openalex.org/W2293666837","https://openalex.org/W2333869848","https://openalex.org/W2399715892","https://openalex.org/W2412412865","https://openalex.org/W2794150393","https://openalex.org/W2798341898","https://openalex.org/W2920982347","https://openalex.org/W2966266849","https://openalex.org/W3007772124","https://openalex.org/W3011583392","https://openalex.org/W3021837324","https://openalex.org/W3105204543","https://openalex.org/W3138798301","https://openalex.org/W4246166885","https://openalex.org/W4249219201","https://openalex.org/W6682466346","https://openalex.org/W6703135172"],"related_works":["https://openalex.org/W2022915229","https://openalex.org/W1871378126","https://openalex.org/W160245670","https://openalex.org/W2180255888","https://openalex.org/W2920982347","https://openalex.org/W3175136721","https://openalex.org/W2059593116","https://openalex.org/W172681653","https://openalex.org/W38257615","https://openalex.org/W2228875006","https://openalex.org/W2484342675","https://openalex.org/W2016909619","https://openalex.org/W2377791546","https://openalex.org/W2885904495","https://openalex.org/W2157729530","https://openalex.org/W2093683727","https://openalex.org/W2767547855","https://openalex.org/W1599739018","https://openalex.org/W2169711291","https://openalex.org/W2553390857"],"abstract_inverted_index":{"The":[0,74],"SIMT":[1],"execution":[2],"model":[3],"is":[4,19,40],"commonly":[5],"used":[6],"for":[7],"general":[8],"GPU":[9],"development.":[10],"CUDA":[11],"and":[12,24,42,78,99],"OpenCL":[13,116],"developers":[14],"write":[15],"scalar":[16],"code":[17],"that":[18,106],"implicitly":[20],"parallelized":[21],"by":[22],"compiler":[23],"hardware.":[25],"On":[26],"Intel":[27,72,126],"GPUs,":[28],"however,":[29],"this":[30,52],"abstraction":[31],"has":[32],"profound":[33],"performance":[34,53,70],"implications":[35],"as":[36],"the":[37,88,113,124],"underlying":[38,89],"ISA":[39],"SIMD":[41,63,96],"important":[43],"hardware":[44,90],"capabilities":[45],"cannot":[46],"be":[47],"fully":[48],"utilized.":[49],"To":[50],"close":[51],"gap":[54],"we":[55],"introduce":[56],"C-":[57],"For-":[58],"Metal":[59],"(CM),":[60],"an":[61,83],"explicit":[62],"programming":[64,76],"framework":[65],"designed":[66],"to":[67,86,120],"deliver":[68],"close-to-the-metal":[69],"on":[71,123],"GPUs.":[73],"CM":[75,107],"language":[77],"its":[79],"vector/matrix":[80],"types":[81],"provide":[82],"intuitive":[84],"interface":[85],"exploit":[87],"features,":[91],"allowing":[92],"fine-grained":[93],"register":[94],"management,":[95],"size":[97],"control":[98],"cross-lane":[100],"data":[101],"sharing.":[102],"Experimental":[103],"results":[104],"show":[105],"applications":[108],"from":[109],"different":[110],"domains":[111],"outperform":[112],"best-known":[114],"SIMT-based":[115],"implementations,":[117],"achieving":[118],"up":[119],"2.7x":[121],"speedup":[122],"latest":[125],"GPU.":[127]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
