{"id":"https://openalex.org/W2026849037","doi":"https://doi.org/10.1145/1375657.1375679","title":"Optimizing scientific application loops on stream processors","display_name":"Optimizing scientific application loops on stream processors","publication_year":2008,"publication_date":"2008-06-12","ids":{"openalex":"https://openalex.org/W2026849037","doi":"https://doi.org/10.1145/1375657.1375679","mag":"2026849037"},"language":"en","primary_location":{"id":"doi:10.1145/1375657.1375679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375657.1375679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGPLAN-SIGBED conference on Languages, compilers, and tools for embedded systems","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/A5100335993","display_name":"Li Wang","orcid":"https://orcid.org/0000-0002-2946-3194"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["NUDT, ChangSha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUDT, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061870286","display_name":"Xuejun Yang","orcid":"https://orcid.org/0000-0002-8595-545X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejun Yang","raw_affiliation_strings":["NUDT, ChangSha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUDT, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024664385","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["UNSW, Sydney, Australia","UNSW, Sydney Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"UNSW, Sydney Australia#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025178580","display_name":"Yu Deng","orcid":"https://orcid.org/0000-0002-7048-9855"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Deng","raw_affiliation_strings":["NDUT, ChangSha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NDUT, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100807669","display_name":"Xiaobo Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Yan","raw_affiliation_strings":["NUDT, ChangSha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUDT, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084996912","display_name":"Tao Tang","orcid":"https://orcid.org/0000-0002-9071-137X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Tang","raw_affiliation_strings":["NUDT, ChangSha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUDT, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101634258","display_name":"Quan Nguyen","orcid":"https://orcid.org/0000-0003-4776-9557"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Hoang Nguyen","raw_affiliation_strings":["UNSW, Sydney, Australia","UNSW, Sydney Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"UNSW, Sydney Australia#TAB#","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1079,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91810833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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":0.998199999332428,"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":0.8975064158439636},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7965922355651855},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7855823040008545},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6825272440910339},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.6438101530075073},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.5295743942260742},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5171515345573425},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.5043388605117798},{"id":"https://openalex.org/keywords/graph-coloring","display_name":"Graph coloring","score":0.4454437792301178},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4430297017097473},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.438950777053833},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.43793994188308716},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28660741448402405},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2559645175933838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8975064158439636},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7965922355651855},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7855823040008545},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6825272440910339},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.6438101530075073},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.5295743942260742},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5171515345573425},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.5043388605117798},{"id":"https://openalex.org/C76946457","wikidata":"https://www.wikidata.org/wiki/Q504843","display_name":"Graph coloring","level":3,"score":0.4454437792301178},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4430297017097473},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.438950777053833},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.43793994188308716},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28660741448402405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2559645175933838},{"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":2,"locations":[{"id":"doi:10.1145/1375657.1375679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375657.1375679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGPLAN-SIGBED conference on Languages, compilers, and tools for embedded systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4814","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unsw.edu.au/~jingling/papers/lctes08.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":35,"referenced_works":["https://openalex.org/W1503700136","https://openalex.org/W1530011161","https://openalex.org/W1583386943","https://openalex.org/W1587952852","https://openalex.org/W1968518918","https://openalex.org/W2003672926","https://openalex.org/W2004766113","https://openalex.org/W2015752867","https://openalex.org/W2023200270","https://openalex.org/W2044636417","https://openalex.org/W2069086083","https://openalex.org/W2080285119","https://openalex.org/W2092958336","https://openalex.org/W2101182628","https://openalex.org/W2103817093","https://openalex.org/W2118866757","https://openalex.org/W2126952393","https://openalex.org/W2127218913","https://openalex.org/W2127384214","https://openalex.org/W2130007585","https://openalex.org/W2135866892","https://openalex.org/W2142550124","https://openalex.org/W2151406013","https://openalex.org/W2165100134","https://openalex.org/W2165125411","https://openalex.org/W2169725869","https://openalex.org/W2171281059","https://openalex.org/W2172212694","https://openalex.org/W2296445158","https://openalex.org/W3148529197","https://openalex.org/W4231121606","https://openalex.org/W4238326245","https://openalex.org/W4285719527","https://openalex.org/W4297924243","https://openalex.org/W6634784020"],"related_works":["https://openalex.org/W1572875092","https://openalex.org/W1522013263","https://openalex.org/W2278840053","https://openalex.org/W2901114907","https://openalex.org/W2741603978","https://openalex.org/W2083056254","https://openalex.org/W2883898247","https://openalex.org/W4240874773","https://openalex.org/W2118219998","https://openalex.org/W2083264194"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,58],"graph":[4,62],"coloring":[5],"compiler":[6,84,104],"framework":[7,23,85],"to":[8,34,113],"allocate":[9],"on-chip":[10],"SRF(Stream":[11],"Register":[12],"File)":[13],"storage":[14],"for":[15,40],"optimizing":[16],"scientific":[17,91],"applications":[18],"on":[19,94,127],"stream":[20,36,72,97],"processors.":[21],"Our":[22,99],"consists":[24],"of":[25,82,110,133],"first":[26],"applying":[27],"enabling":[28],"optimizations":[29],"such":[30],"as":[31],"loop":[32],"unrolling":[33],"expose":[35],"reuse":[37],"and":[38,47,74],"opportunities":[39],"maximizing":[41,76],"parallelism,":[42],"i.e.,":[43],"overlapping":[44],"kernel":[45],"execution":[46],"memory":[48],"transfers.Then":[49],"the":[50,68,80,119],"three":[51],"SRF":[52],"management":[53,105],"tasks":[54],"are":[55],"solved":[56],"in":[57,67],"unified":[59],"manner":[60],"via":[61],"coloring:":[63],"(1)":[64],"placing":[65],"streams":[66],"SRF,":[69],"(2)":[70],"exploiting":[71],"use,":[73],"(3)":[75],"parallelism.":[77],"We":[78],"evaluate":[79],"performance":[81,120],"our":[83,95],"by":[86],"actually":[87],"running":[88,124],"nine":[89],"representative":[90],"computing":[92],"kernels":[93],"FT64":[96],"processor.":[98],"preliminary":[100],"results":[101,121],"show":[102],"that":[103],"achieves":[106],"an":[107,130],"average":[108,131],"speedup":[109,132],"2.3x":[111],"compared":[112],"First-Fit":[114],"allocation.":[115],"In":[116],"comparison":[117],"with":[118],"obtained":[122],"from":[123],"these":[125],"benchmarks":[126],"Itanium":[128],"2,":[129],"2.1x":[134],"is":[135],"observed.":[136]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
