{"id":"https://openalex.org/W2554260456","doi":"https://doi.org/10.1109/iccd.2016.7753288","title":"Hardware thread reordering to boost OpenCL throughput on FPGAs","display_name":"Hardware thread reordering to boost OpenCL throughput on FPGAs","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2554260456","doi":"https://doi.org/10.1109/iccd.2016.7753288","mag":"2554260456"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2016.7753288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","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/A5052322934","display_name":"Amir Momeni","orcid":"https://orcid.org/0000-0002-6941-8179"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Momeni","raw_affiliation_strings":["ECE Department, Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063615699","display_name":"Hamed Tabkhi","orcid":"https://orcid.org/0000-0001-5420-1121"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Hamed Tabkhi","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026700236","display_name":"Gunar Schirner","orcid":"https://orcid.org/0000-0002-5408-8496"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gunar Schirner","raw_affiliation_strings":["ECE Department, Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["ECE Department, Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9614,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75359418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"264"},"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/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/T10829","display_name":"Interconnection Networks and Systems","score":0.9972000122070312,"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":0.8928279876708984},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7632580995559692},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7558239698410034},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6289041042327881},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.596657395362854},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.47038522362709045},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4317498505115509},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.42443621158599854},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.41449955105781555},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29924118518829346},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14036238193511963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8928279876708984},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7632580995559692},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7558239698410034},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6289041042327881},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.596657395362854},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.47038522362709045},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4317498505115509},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.42443621158599854},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.41449955105781555},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29924118518829346},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14036238193511963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd.2016.7753288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2016.7753288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1988163097","https://openalex.org/W2000921084","https://openalex.org/W2014469493","https://openalex.org/W2018055497","https://openalex.org/W2038190779","https://openalex.org/W2042766074","https://openalex.org/W2043735637","https://openalex.org/W2060569848","https://openalex.org/W2085884196","https://openalex.org/W2125951114","https://openalex.org/W2264337508","https://openalex.org/W2343480761","https://openalex.org/W4233908922","https://openalex.org/W4241148135","https://openalex.org/W4247312607","https://openalex.org/W4253128333","https://openalex.org/W6661452130","https://openalex.org/W6665723138","https://openalex.org/W6704274203"],"related_works":["https://openalex.org/W3095167194","https://openalex.org/W2095925360","https://openalex.org/W1549956274","https://openalex.org/W4246377515","https://openalex.org/W2052160877","https://openalex.org/W2040778456","https://openalex.org/W2119238100","https://openalex.org/W2148473336","https://openalex.org/W4254236578","https://openalex.org/W2144344516"],"abstract_inverted_index":{"Availability":[0],"of":[1,12,29,70,92,107,151,158],"OpenCL":[2,31,75,111],"for":[3,45,52,63],"FPGAs":[4,71,94],"has":[5],"raised":[6],"new":[7,64],"questions":[8],"about":[9],"the":[10,90,93,148,156,168,172,177],"efficiency":[11,49,69,157],"massive":[13],"thread-level":[14],"parallelism":[15],"on":[16,162],"FPGAs.":[17],"The":[18,104,123,133],"general":[19],"trend":[20],"is":[21,109,126],"toward":[22],"creating":[23],"deep":[24],"pipelining":[25],"and":[26,143],"in-order":[27],"execution":[28,68,113],"many":[30],"threads":[32],"across":[33],"a":[34,41,80,115,129,201],"shared":[35,116],"data-path.":[36,183],"While":[37],"this":[38],"can":[39],"be":[40],"very":[42,202],"effective":[43],"approach":[44],"regular":[46],"kernels,":[47],"its":[48],"significantly":[50,120],"diminishes":[51],"irregular":[53,74,97,165],"kernels":[54,98,198],"with":[55,138,181],"runtime-dependent":[56],"control":[57,102,141],"flow.":[58,103],"We":[59,154],"need":[60],"to":[61,66,88,118,146,175,194],"look":[62],"approaches":[65],"improve":[67],"when":[72,95],"targeting":[73],"kernels.":[76,166],"This":[77],"paper":[78],"proposes":[79],"novel":[81],"solution,":[82],"called":[83],"Hardware":[84],"Thread":[85],"Reordering":[86],"(HTR),":[87],"boost":[89],"throughput":[91,199],"executing":[96],"possessing":[99],"non-deterministic":[100],"runtime":[101],"key":[105],"insight":[106],"HRT":[108],"out-of-order":[110],"thread":[112,124],"over":[114],"data-path":[117,180,191],"achieve":[119],"higher":[121],"throughput.":[122],"reordering":[125],"performed":[127],"at":[128,200],"basic-block":[130],"level":[131],"granularity.":[132],"synthesized":[134],"basic-blocks":[135],"are":[136],"extended":[137],"independent":[139],"pipeline":[140],"signals":[142],"context":[144],"registers":[145],"bypass":[147],"live":[149],"values":[150],"reordered":[152],"threads.":[153],"demonstrate":[155,188],"our":[159],"proposed":[160],"solution":[161],"three":[163],"parallel":[164],"For":[167],"experiments,":[169],"we":[170],"utilize":[171],"LegUp":[173],"tool":[174],"compare":[176],"baseline":[178],"(in-order)":[179],"HTR-enhanced":[182,190],"Our":[184],"RTL":[185],"simulation":[186],"results":[187],"that":[189],"achieves":[192],"up":[193],"11\u00d7":[195],"increase":[196,208],"in":[197,209],"low":[203],"overhead":[204],"(less":[205],"than":[206],"2\u00d7":[207],"FPGA":[210],"resources).":[211]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
