{"id":"https://openalex.org/W3139203108","doi":"https://doi.org/10.1109/pact.2013.6618823","title":"Breaking SIMD shackles with an exposed flexible microarchitecture and the access execute PDG","display_name":"Breaking SIMD shackles with an exposed flexible microarchitecture and the access execute PDG","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W3139203108","doi":"https://doi.org/10.1109/pact.2013.6618823","mag":"3139203108"},"language":"en","primary_location":{"id":"doi:10.1109/pact.2013.6618823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2013.6618823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd 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/A5100999753","display_name":"Feng Ji","orcid":"https://orcid.org/0000-0002-2051-5453"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Feng Ji","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066494596","display_name":"Heshan Lin","orcid":"https://orcid.org/0000-0001-9286-9421"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heshan Lin","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083800790","display_name":"Xiaosong Ma","orcid":"https://orcid.org/0000-0003-1261-2496"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaosong Ma","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, US"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, US","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100999753"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.9456,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78269797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"45","issue":null,"first_page":"341","last_page":"352"},"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8861347436904907},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6038079261779785},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.5959507822990417},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5347594022750854},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5342451930046082},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.488135427236557},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4423588812351227},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.44099369645118713},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42594751715660095},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.41714394092559814},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3713766038417816},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33171820640563965},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3089361786842346},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.08723661303520203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8861347436904907},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6038079261779785},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.5959507822990417},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5347594022750854},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5342451930046082},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.488135427236557},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4423588812351227},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.44099369645118713},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42594751715660095},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.41714394092559814},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3713766038417816},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33171820640563965},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3089361786842346},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.08723661303520203},{"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":1,"locations":[{"id":"doi:10.1109/pact.2013.6618823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2013.6618823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310013","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1651324627","https://openalex.org/W1966124831","https://openalex.org/W1983540755","https://openalex.org/W2022941486","https://openalex.org/W2044902313","https://openalex.org/W2053376261","https://openalex.org/W2085118703","https://openalex.org/W2088943630","https://openalex.org/W2095668076","https://openalex.org/W2106579652","https://openalex.org/W2109426995","https://openalex.org/W2109473404","https://openalex.org/W2112340065","https://openalex.org/W2126503506","https://openalex.org/W2127510911","https://openalex.org/W2144643978","https://openalex.org/W2149234156","https://openalex.org/W2150476673","https://openalex.org/W2153375074","https://openalex.org/W2159792012","https://openalex.org/W2725179571","https://openalex.org/W3145506805","https://openalex.org/W4235762625","https://openalex.org/W4241790656","https://openalex.org/W4247913514","https://openalex.org/W6633127185","https://openalex.org/W6636916521","https://openalex.org/W6793351010"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"While":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPU)":[4],"have":[5],"gained":[6],"much":[7],"success":[8],"in":[9,13,43,62,108],"general":[10],"purpose":[11],"computing":[12],"recent":[14,34],"years,":[15],"their":[16],"programming":[17],"is":[18,53],"still":[19,54,213],"difficult,":[20],"due":[21,68],"to,":[22],"particularly,":[23],"explicitly":[24],"managed":[25],"GPU":[26,38,49,64,107,118,131,141,147,177,191,226],"memory":[27,50,83,101,119,148,168,200],"and":[28,106,111,121,143,162],"manual":[29],"CPU-GPU":[30,82],"data":[31,123,134,217],"transfer.":[32],"Despite":[33],"calls":[35],"for":[36,80,170,208,229],"managing":[37],"resources":[39],"as":[40],"first-class":[41],"citizens":[42],"the":[44,60,90,137,140,151,160,198,205],"operating":[45],"system,":[46],"a":[47,77,98,109,184],"mature":[48],"management":[51,120],"mechanism":[52,79],"missing,":[55],"which":[56],"leads":[57],"to":[58,69,116,193],"reinventing":[59],"wheels":[61],"various":[63],"system":[65,231],"software.":[66],"Meanwhile,":[67],"ever":[70],"enlarging":[71],"problem":[72,195,210],"sizes,":[73,211],"we":[74,88],"urgently":[75],"need":[76],"system-level":[78],"unified":[81,166],"management.":[84],"In":[85,114],"this":[86],"work,":[87],"present":[89],"design":[91],"of":[92,164],"Region-based":[93],"Software":[94],"Virtual":[95],"Memory":[96],"(RSVM),":[97],"software":[99,232],"virtual":[100,167],"running":[102],"on":[103,159,175,216],"both":[104],"CPU":[105],"distributed":[110],"cooperative":[112],"way.":[113],"addition":[115],"automatic":[117],"GPU-CPU":[122],"transfer,":[124],"RSVM":[125,187],"offers":[126],"two":[127],"novel":[128],"features:":[129],"1)":[130],"kernel-issued":[132],"on-demand":[133],"fetching":[135],"from":[136],"host":[138],"into":[139,150],"memory,":[142],"2)":[144],"intra-kernel":[145],"transparent":[146],"swapping":[149],"main":[152],"memory.":[153],"Our":[154,221],"study":[155],"reveals":[156],"important":[157],"insights":[158],"challenges":[161],"opportunities":[163],"building":[165],"systems":[169],"heterogeneous":[171],"computing.":[172],"Experimental":[173],"results":[174],"real":[176],"benchmarks":[178],"demonstrate":[179],"that,":[180],"though":[181],"it":[182],"incurs":[183],"small":[185],"overhead,":[186],"can":[188,214],"transparently":[189],"scale":[190],"kernels":[192],"large":[194],"sizes":[196],"exceeding":[197],"device":[199],"size":[201],"limit;":[202],"developers":[203],"write":[204],"same":[206],"code":[207],"different":[209],"but":[212],"optimize":[215],"layout":[218],"definition":[219],"accordingly.":[220],"evaluation":[222],"also":[223],"identifies":[224],"missing":[225],"architecture":[227],"features":[228],"better":[230],"efficiency.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
