{"id":"https://openalex.org/W4251064080","doi":"https://doi.org/10.1109/isca.2014.6853234","title":"Single-graph multiple flows: Energy efficient design alternative for GPGPUs","display_name":"Single-graph multiple flows: Energy efficient design alternative for GPGPUs","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W4251064080","doi":"https://doi.org/10.1109/isca.2014.6853234"},"language":"en","primary_location":{"id":"doi:10.1109/isca.2014.6853234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2014.6853234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA)","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/A5079954440","display_name":"Dani Voitsechov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Dani Voitsechov","raw_affiliation_strings":["Electrical Enqineering, Technion - Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Electrical Enqineering, Technion - Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014183046","display_name":"Yoav Etsion","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoav Etsion","raw_affiliation_strings":["Computer Science, Technion - Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Computer Science, Technion - Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079954440"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":1.8389,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86562001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"216"},"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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":0.8799649477005005},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8237934708595276},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7242463827133179},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6411871910095215},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6350387930870056},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5001184940338135},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49989748001098633},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.441386342048645},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.4171859323978424},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.41600775718688965},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3627132177352905},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.35717397928237915},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27039384841918945},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21946150064468384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799649477005005},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8237934708595276},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7242463827133179},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6411871910095215},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6350387930870056},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5001184940338135},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49989748001098633},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.441386342048645},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.4171859323978424},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.41600775718688965},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3627132177352905},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.35717397928237915},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27039384841918945},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21946150064468384},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isca.2014.6853234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2014.6853234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1568192366","https://openalex.org/W1964471912","https://openalex.org/W1975489482","https://openalex.org/W1979527452","https://openalex.org/W1982205631","https://openalex.org/W1990087033","https://openalex.org/W2000335122","https://openalex.org/W2008165887","https://openalex.org/W2018885404","https://openalex.org/W2024122052","https://openalex.org/W2033597569","https://openalex.org/W2034147186","https://openalex.org/W2059593728","https://openalex.org/W2080592089","https://openalex.org/W2090068045","https://openalex.org/W2093043622","https://openalex.org/W2120120110","https://openalex.org/W2130408605","https://openalex.org/W2131867938","https://openalex.org/W2134715867","https://openalex.org/W2140375692","https://openalex.org/W2144481293","https://openalex.org/W2146451305","https://openalex.org/W2155503253","https://openalex.org/W2157373341","https://openalex.org/W2169339215","https://openalex.org/W2171532807","https://openalex.org/W2172212694","https://openalex.org/W2295946175","https://openalex.org/W2912425543","https://openalex.org/W3138798301","https://openalex.org/W3142147837","https://openalex.org/W4236272793","https://openalex.org/W4239997146","https://openalex.org/W4242368470","https://openalex.org/W4244593655","https://openalex.org/W4246166885","https://openalex.org/W4249868603","https://openalex.org/W6679984923"],"related_works":["https://openalex.org/W2070865675","https://openalex.org/W2170268965","https://openalex.org/W2907215606","https://openalex.org/W4236883517","https://openalex.org/W1664545926","https://openalex.org/W2161462353","https://openalex.org/W4291395144","https://openalex.org/W2159378609","https://openalex.org/W2135947393","https://openalex.org/W2161825883"],"abstract_inverted_index":{"We":[0,123],"present":[1],"the":[2,64,80,92,107,126],"single-graph":[3],"multiple-flows":[4],"(SGMF)":[5],"architecture":[6,23,35,128],"that":[7,125,133],"combines":[8],"coarse-grain":[9,47],"reconfigurable":[10,48],"computing":[11],"with":[12],"dynamic":[13],"dataflow":[14,43],"to":[15,132],"deliver":[16],"massive":[17],"thread-level":[18],"parallelism.":[19],"The":[20,34,73,94],"CUDA-compatible":[21],"SGMF":[22,89,127],"is":[24],"positioned":[25],"as":[26,41],"an":[27],"energy":[28,119,141],"efficient":[29],"design":[30],"alternative":[31],"for":[32,109],"GPGPUs.":[33,122],"maps":[36],"a":[37,42,46,52,114],"compute":[38],"kernel,":[39],"represented":[40],"graph,":[44],"onto":[45],"fabric":[49],"composed":[50],"of":[51,54,63,82,96,134],"grid":[53],"interconnected":[55],"functional":[56,76,104],"units.":[57],"Each":[58],"unit":[59],"dynamically":[60,74],"schedules":[61],"instances":[62],"same":[65],"static":[66],"instruction":[67,111],"originating":[68],"from":[69],"different":[70],"CUDA":[71],"threads.":[72],"scheduled":[75],"units":[77,105],"enable":[78],"streaming":[79],"data":[81],"multiple":[83],"threads":[84],"(or":[85],"graph":[86],"flows,":[87],"in":[88],"parlance)":[90],"through":[91],"grid.":[93],"combination":[95],"statically":[97],"mapped":[98],"instructions":[99],"and":[100,113],"direct":[101],"communication":[102],"between":[103],"obviate":[106],"need":[108],"afull":[110],"pipeline":[112],"centralized":[115],"register":[116],"file,":[117],"whose":[118],"overheads":[120],"burden":[121],"show":[124],"delivers":[129],"performance":[130],"comparable":[131],"contemporary":[135],"GPGPUs":[136],"while":[137],"consuming":[138],"~57%":[139],"less":[140],"on":[142],"average.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}