{"id":"https://openalex.org/W2127384214","doi":"https://doi.org/10.1145/1152154.1152164","title":"Compiling for stream processing","display_name":"Compiling for stream processing","publication_year":2006,"publication_date":"2006-09-16","ids":{"openalex":"https://openalex.org/W2127384214","doi":"https://doi.org/10.1145/1152154.1152164","mag":"2127384214"},"language":"en","primary_location":{"id":"doi:10.1145/1152154.1152164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","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/A5066986611","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0003-1088-2601"},"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":"Abhishek Das","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084342236","display_name":"William J. Dally","orcid":"https://orcid.org/0000-0003-4632-2876"},"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":"William J. Dally","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053488528","display_name":"Peter Mattson","orcid":"https://orcid.org/0000-0002-5984-238X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Mattson","raw_affiliation_strings":["Stream Processors, Inc"],"affiliations":[{"raw_affiliation_string":"Stream Processors, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066986611"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":12.7714,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.99237262,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and 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":0.9980999827384949,"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":0.8794164657592773},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6886606216430664},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6552427411079407},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5558294057846069},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5278511047363281},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.46518534421920776},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.44134002923965454},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.4221588969230652},{"id":"https://openalex.org/keywords/linux-kernel","display_name":"Linux kernel","score":0.4165892004966736},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4146576523780823},{"id":"https://openalex.org/keywords/registered-memory","display_name":"Registered memory","score":0.41460880637168884},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.41097649931907654},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.40427958965301514},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3773042559623718},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3286702036857605},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.2922533452510834},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.13392561674118042},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07485869526863098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8794164657592773},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6886606216430664},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6552427411079407},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5558294057846069},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5278511047363281},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.46518534421920776},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.44134002923965454},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.4221588969230652},{"id":"https://openalex.org/C553261973","wikidata":"https://www.wikidata.org/wiki/Q14579","display_name":"Linux kernel","level":2,"score":0.4165892004966736},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4146576523780823},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.41460880637168884},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.41097649931907654},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.40427958965301514},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3773042559623718},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3286702036857605},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.2922533452510834},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.13392561674118042},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07485869526863098}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1152154.1152164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.553.2408","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.553.2408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.virginia.edu/~pact2006/program/pact2006/pact129-das3.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W174513348","https://openalex.org/W1575732703","https://openalex.org/W1587952852","https://openalex.org/W1801279003","https://openalex.org/W1977590451","https://openalex.org/W2015752867","https://openalex.org/W2034147186","https://openalex.org/W2057108708","https://openalex.org/W2063249715","https://openalex.org/W2069086083","https://openalex.org/W2071467620","https://openalex.org/W2080285119","https://openalex.org/W2114295495","https://openalex.org/W2133361919","https://openalex.org/W2157758640","https://openalex.org/W2162569595","https://openalex.org/W2296445158","https://openalex.org/W2752885492","https://openalex.org/W3145128584","https://openalex.org/W4230771139","https://openalex.org/W4232919122","https://openalex.org/W4253240009","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2354036839","https://openalex.org/W2041174925","https://openalex.org/W2155373950","https://openalex.org/W2782503170","https://openalex.org/W4321458411","https://openalex.org/W3021597805","https://openalex.org/W4233816696","https://openalex.org/W2587873888","https://openalex.org/W2044064773","https://openalex.org/W3048967625"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,89],"compiler":[4,22,61,87,100,170],"for":[5],"stream":[6,14,78,134],"programs":[7],"that":[8,99,132,182],"efficiently":[9],"schedules":[10],"computational":[11,194],"kernels":[12,76],"and":[13,17,29,33,47,69,77,93,113,164,177],"memory":[15,34,43,58,79,107,175],"operations,":[16],"allocates":[18],"on-chip":[19,53,103,143],"storage.":[20,129],"Our":[21,60,96],"uses":[23],"information":[24],"about":[25],"the":[26,73,83,127,155,160],"program":[27,187],"structure":[28],"estimates":[30],"of":[31,51,75,85,91,102,126,157,186],"kernel":[32,40],"operation":[35],"execution":[36,41,115,188],"times":[37],"to":[38,48,111,119,122,139,150,159,165,173,184],"overlap":[39,174],"with":[42],"transfers,":[44],"maximizing":[45],"performance,":[46],"optimize":[49],"use":[50],"scarce":[52],"memory,":[54],"significantly":[55],"reducing":[56,145],"external":[57,106,146],"bandwidth.":[59],"applies":[62],"optimizations":[63],"such":[64],"as":[65],"strip-mining,":[66],"loop":[67],"unrolling,":[68],"software":[70],"pipelining,":[71],"at":[72],"level":[74],"operations.":[80],"We":[81,130,152],"evaluate":[82,154],"performance":[84,158],"our":[86,169],"on":[88],"suite":[90],"media":[92],"scientific":[94],"benchmarks.":[95],"results":[97],"show":[98,131],"management":[101,125],"storage":[104,144,180],"reduces":[105,114],"bandwidth":[108,147],"by":[109,117,148],"35%":[110],"93%":[112],"time":[116,189],"23%":[118],"72%":[120],"compared":[121],"cachelike":[123],"LRU":[124],"same":[128],"strip-mining":[133],"applications":[135],"enables":[136],"producer-consumer":[137],"locality":[138],"be":[140],"captured":[141],"in":[142,192],"50%":[149],"80%.":[151],"also":[153],"sensitivity":[156],"scheduling":[161],"methods":[162],"used":[163],"critical":[166],"resources.":[167],"Overall,":[168],"is":[171,190],"able":[172],"operations":[176],"manage":[178],"local":[179],"so":[181],"78%":[183],"96%":[185],"spent":[191],"running":[193],"kernels.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}