{"id":"https://openalex.org/W2143746374","doi":"https://doi.org/10.1145/2503210.2503295","title":"Load-balanced pipeline parallelism","display_name":"Load-balanced pipeline parallelism","publication_year":2013,"publication_date":"2013-10-30","ids":{"openalex":"https://openalex.org/W2143746374","doi":"https://doi.org/10.1145/2503210.2503295","mag":"2143746374"},"language":"en","primary_location":{"id":"doi:10.1145/2503210.2503295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023211716","display_name":"Md Kamruzzaman","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Kamruzzaman","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005764203","display_name":"Steven Swanson","orcid":"https://orcid.org/0000-0002-5896-1037"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Swanson","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065583627","display_name":"Dean M. Tullsen","orcid":"https://orcid.org/0000-0003-3174-9316"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dean M. Tullsen","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.538,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.61676045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9991999864578247,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.8927319049835205},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8122612237930298},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7393956184387207},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7254283428192139},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6680936217308044},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5838622450828552},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5711161494255066},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5040959119796753},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.48944559693336487},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.47086966037750244},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.45163071155548096},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.448906809091568},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.41655397415161133},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.41495072841644287},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.33699044585227966},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32302922010421753},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1624421775341034},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07497519254684448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8927319049835205},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8122612237930298},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7393956184387207},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7254283428192139},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6680936217308044},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5838622450828552},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5711161494255066},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5040959119796753},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.48944559693336487},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.47086966037750244},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.45163071155548096},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.448906809091568},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.41655397415161133},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.41495072841644287},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.33699044585227966},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32302922010421753},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1624421775341034},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07497519254684448},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2503210.2503295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.8952","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.8952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cseweb.ucsd.edu/%7Etullsen/sc13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1971113345","display_name":null,"funder_award_id":"CCF-1018356, CCF-0643880","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6988700210","display_name":null,"funder_award_id":"2086.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W79448102","https://openalex.org/W1541631323","https://openalex.org/W1576974478","https://openalex.org/W1582788465","https://openalex.org/W1976397984","https://openalex.org/W1976623675","https://openalex.org/W1982812416","https://openalex.org/W1999625132","https://openalex.org/W2016559894","https://openalex.org/W2034209740","https://openalex.org/W2086779607","https://openalex.org/W2090408221","https://openalex.org/W2094693699","https://openalex.org/W2111905231","https://openalex.org/W2118518065","https://openalex.org/W2121253564","https://openalex.org/W2125623590","https://openalex.org/W2128294826","https://openalex.org/W2137299962","https://openalex.org/W2143592587","https://openalex.org/W2145406052","https://openalex.org/W2147536281","https://openalex.org/W2150547581","https://openalex.org/W2155312437","https://openalex.org/W2171546589","https://openalex.org/W2296006986","https://openalex.org/W2532845325"],"related_works":["https://openalex.org/W4240606930","https://openalex.org/W2526302199","https://openalex.org/W2003935582","https://openalex.org/W4236721623","https://openalex.org/W2042008201","https://openalex.org/W2105992728","https://openalex.org/W2169040626","https://openalex.org/W2020784655","https://openalex.org/W2082701182","https://openalex.org/W2126220043"],"abstract_inverted_index":{"Accelerating":[0],"a":[1,9,84],"single":[2,40],"thread":[3,41],"in":[4,83],"current":[5],"parallel":[6,86],"systems":[7],"remains":[8],"challenging":[10,47],"problem,":[11],"because":[12],"sequential":[13,94],"threads":[14],"do":[15],"not":[16],"naturally":[17,64],"take":[18],"advantage":[19],"of":[20,30],"the":[21,66,77],"additional":[22],"cores.":[23],"Recent":[24],"work":[25,55],"shows":[26,56],"that":[27,63],"automatic":[28],"extraction":[29],"pipeline":[31,61,78,110],"parallelism":[32,62,111],"is":[33],"an":[34],"effective":[35],"way":[36],"to":[37,59,92,108],"speed":[38],"up":[39],"execution.":[42],"However,":[43],"two":[44],"problems":[45],"remain":[46],"--":[48],"load":[49,67],"balancing":[50,68],"and":[51,69,80,104],"inter-thread":[52],"communication.":[53],"This":[54,72,96],"new":[57],"mechanism":[58],"exploit":[60,109],"solves":[65],"communication":[70],"problems.":[71],"compiler-based":[73],"technique":[74,97],"automatically":[75],"extracts":[76],"stages":[79],"executes":[81],"them":[82],"data":[85],"fashion,":[87],"using":[88],"token-based":[89],"chunked":[90],"synchronization":[91],"handle":[93],"stages.":[95],"provides":[98],"linear":[99],"speedup":[100],"for":[101],"several":[102],"applications,":[103],"outperforms":[105],"prior":[106],"techniques":[107],"by":[112],"as":[113,115],"much":[114],"50%.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}