{"id":"https://openalex.org/W1994089185","doi":"https://doi.org/10.1109/fpt.2013.6718409","title":"Efficient methods for out-of-order load/store execution for high-performance soft processors","display_name":"Efficient methods for out-of-order load/store execution for high-performance soft processors","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1994089185","doi":"https://doi.org/10.1109/fpt.2013.6718409","mag":"1994089185"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2013.6718409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2013.6718409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on Field-Programmable Technology (FPT)","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/A5000808423","display_name":"Henry Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Henry Wong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto","Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030184404","display_name":"Vaughn Betz","orcid":"https://orcid.org/0000-0003-0528-6493"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vaughn Betz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto","Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090184149","display_name":"Jonathan Rose","orcid":"https://orcid.org/0000-0002-3551-2175"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Rose","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto","Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000808423"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.3171,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.58746017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"442","last_page":"445"},"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/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":0.9983000159263611,"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":0.8698944449424744},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.7652892470359802},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.6857996582984924},{"id":"https://openalex.org/keywords/message-queue","display_name":"Message queue","score":0.5505750179290771},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5098687410354614},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4819624125957489},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4674314856529236},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.45655858516693115},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39530879259109497},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28864526748657227},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1994631588459015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698944449424744},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.7652892470359802},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.6857996582984924},{"id":"https://openalex.org/C26324664","wikidata":"https://www.wikidata.org/wiki/Q1065525","display_name":"Message queue","level":2,"score":0.5505750179290771},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5098687410354614},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4819624125957489},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4674314856529236},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.45655858516693115},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39530879259109497},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28864526748657227},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1994631588459015}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fpt.2013.6718409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2013.6718409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on Field-Programmable Technology (FPT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.641.3654","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.641.3654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecg.utoronto.ca/~vaughn/papers/fpt2013_memory_speculation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.6532","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.6532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecg.toronto.edu/%7Ejayar/pubs/wong/wongfpt13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W312691478","https://openalex.org/W1516817683","https://openalex.org/W1562605315","https://openalex.org/W1968630848","https://openalex.org/W2016889342","https://openalex.org/W2024080903","https://openalex.org/W2095906375","https://openalex.org/W2102325484","https://openalex.org/W2105552602","https://openalex.org/W2111683449","https://openalex.org/W2119786518","https://openalex.org/W2145483435","https://openalex.org/W2160313031","https://openalex.org/W4248310923","https://openalex.org/W4256083753","https://openalex.org/W6611015109","https://openalex.org/W6633563652","https://openalex.org/W6657509424","https://openalex.org/W6674169808","https://openalex.org/W6675986312","https://openalex.org/W6681372123"],"related_works":["https://openalex.org/W2187189666","https://openalex.org/W2949084706","https://openalex.org/W631639522","https://openalex.org/W2754841804","https://openalex.org/W2818116514","https://openalex.org/W2540664775","https://openalex.org/W2053048395","https://openalex.org/W1480183640","https://openalex.org/W2039545941","https://openalex.org/W1994089185"],"abstract_inverted_index":{"As":[0],"FPGAs":[1],"continue":[2],"to":[3,13,36,55,103],"increase":[4],"in":[5,81],"size,":[6,147],"it":[7],"becomes":[8],"increasingly":[9],"feasible":[10],"and":[11,40,62,85,100,110,128,132,140,150,164,169,178,184],"desirable":[12],"build":[14],"higher":[15,186],"performance":[16],"soft":[17],"processors.":[18],"Preserving":[19],"the":[20,58,82,130],"familiar":[21],"single-threaded":[22],"programming":[23],"model":[24],"can":[25],"be":[26],"done":[27,78],"with":[28,79,106,144,155],"an":[29],"out":[30,42],"of":[31,43,72],"order":[32,44,73],"processor.":[33],"The":[34],"ability":[35],"execute":[37],"memory":[38,74,116],"loads":[39,63],"stores":[41,61],"has":[45],"a":[46,124],"large":[47,89],"impact":[48],"on":[49,93,123],"performance,":[50],"but":[51,88,158],"this":[52],"is":[53,76],"difficult":[54],"do":[56],"because":[57],"dependencies":[59],"between":[60],"are":[64,69,91],"not":[65],"known":[66],"until":[67],"addresses":[68],"computed.":[70],"Out":[71],"disambiguation":[75,117],"traditionally":[77],"CAMs":[80,90,105,175],"load":[83,111],"queue":[84,146,156,181],"store":[86],"queue,":[87],"inefficient":[92],"FPGAs.":[94],"Store":[95],"Queue":[96],"Index":[97],"Prediction":[98],"(SQIP)":[99],"NoSQ":[101,151,170],"propose":[102],"replace":[104],"store-load":[107],"forwarding":[108],"prediction":[109,163],"re-execution.":[112],"We":[113,135],"implement":[114],"four":[115],"schemes":[118],"(in-order,":[119],"CAM,":[120],"SQIP,":[121],"NoSQ)":[122],"Stratix":[125],"IV":[126],"FPGA":[127],"evaluate":[129],"area":[131,139,160,173],"delay":[133,141],"trade-offs.":[134],"find":[136],"that":[137],"CAM":[138],"degrade":[142],"quickly":[143],"load/store":[145,180],"while":[148],"SQIP":[149,168],"have":[152,159,185],"little":[153],"degradation":[154],"size":[157],"overhead":[161],"for":[162],"predictor":[165],"training":[166],"hardware.":[167],"use":[171],"less":[172],"than":[174],"beyond":[176,189],"32":[177],"16":[179],"entries,":[182],"respectively,":[183],"maximum":[187],"frequency":[188],"4":[190],"entries.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}