{"id":"https://openalex.org/W2171399035","doi":"https://doi.org/10.1145/2555243.2555258","title":"Singe","display_name":"Singe","publication_year":2014,"publication_date":"2014-02-06","ids":{"openalex":"https://openalex.org/W2171399035","doi":"https://doi.org/10.1145/2555243.2555258","mag":"2171399035"},"language":"en","primary_location":{"id":"doi:10.1145/2555243.2555258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGPLAN symposium on Principles and practice of parallel programming","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/A5101680564","display_name":"Michael Bauer","orcid":"https://orcid.org/0009-0000-5475-7293"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Bauer","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005774998","display_name":"Sean Treichler","orcid":"https://orcid.org/0000-0003-2189-4026"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Treichler","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087402475","display_name":"Alex Aiken","orcid":"https://orcid.org/0000-0002-3723-9555"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Aiken","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101680564"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":5.3639,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96139262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"130"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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":0.9991000294685364,"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":0.8457227945327759},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8272775411605835},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8146315813064575},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6913968324661255},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5446829199790955},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5143061876296997},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4374547600746155},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4360818564891815},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42438894510269165},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36082154512405396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457227945327759},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8272775411605835},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8146315813064575},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6913968324661255},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5446829199790955},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5143061876296997},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4374547600746155},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4360818564891815},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42438894510269165},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36082154512405396},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2555243.2555258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1529622848","https://openalex.org/W1981812667","https://openalex.org/W1989988531","https://openalex.org/W1997677898","https://openalex.org/W2046100676","https://openalex.org/W2049875313","https://openalex.org/W2109473404","https://openalex.org/W2128329055","https://openalex.org/W2151972839","https://openalex.org/W2154968583","https://openalex.org/W2164106630","https://openalex.org/W2399715892","https://openalex.org/W4246297106"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W4225271228","https://openalex.org/W1484403103","https://openalex.org/W2521947294"],"abstract_inverted_index":{"We":[0,121],"present":[1],"Singe,":[2],"a":[3,54,118],"Domain":[4],"Specific":[5],"Language":[6],"(DSL)":[7],"compiler":[8],"for":[9,21,116],"combustion":[10],"chemistry":[11],"that":[12,31,123],"leverages":[13],"warp":[14,35,73],"specialization":[15,36,74],"to":[16,41,50,77,97,132],"produce":[17],"high":[18],"performance":[19],"code":[20,126],"GPUs.":[22],"Instead":[23],"of":[24,93],"relying":[25],"on":[26],"traditional":[27],"GPU":[28,139],"programming":[29],"models":[30],"emphasize":[32],"data-parallel":[33,138],"computations,":[34],"allows":[37,75,95],"compilers":[38],"like":[39],"Singe":[40,76,96,129],"partition":[42],"computations":[43,71,94],"into":[44,103],"sub-computations":[45],"which":[46],"are":[47],"then":[48],"assigned":[49],"different":[51],"warps":[52,60],"within":[53],"thread":[55],"block.":[56],"Fine-grain":[57],"synchronization":[58],"between":[59],"is":[61,130],"performed":[62],"efficiently":[63,79],"in":[64,83],"hardware":[65],"using":[66,72],"producer-consumer":[67],"named":[68],"barriers.":[69],"Partitioning":[70],"deal":[78],"with":[80],"the":[81,109,124],"irregularity":[82],"both":[84],"data":[85],"access":[86],"patterns":[87],"and":[88,111],"computation.":[89],"Furthermore,":[90],"warp-specialized":[91,125],"partitioning":[92],"fit":[98],"extremely":[99],"large":[100],"working":[101],"sets":[102],"on-chip":[104],"memories.":[105],"Finally,":[106],"we":[107],"describe":[108],"architecture":[110],"general":[112],"compilation":[113],"techniques":[114],"necessary":[115],"constructing":[117],"warp-specializing":[119],"compiler.":[120],"show":[122],"emitted":[127],"by":[128],"up":[131],"3.75X":[133],"faster":[134],"than":[135],"previously":[136],"optimized":[137],"kernels.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2016-06-24T00:00:00"}