{"id":"https://openalex.org/W3139083165","doi":"https://doi.org/10.1109/pact.2013.6618834","title":"Exposing ILP in custom hardware with a dataflow compiler IR","display_name":"Exposing ILP in custom hardware with a dataflow compiler IR","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W3139083165","doi":"https://doi.org/10.1109/pact.2013.6618834","mag":"3139083165"},"language":"en","primary_location":{"id":"doi:10.1109/pact.2013.6618834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2013.6618834","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/A5114677150","display_name":"Sangmin Seo","orcid":"https://orcid.org/0000-0002-9515-9836"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sangmin Seo","raw_affiliation_strings":["ManyCoreSoft, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"ManyCoreSoft, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442887","display_name":"Jun Lee","orcid":"https://orcid.org/0000-0002-5756-5470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103690204","display_name":"Gangwon Jo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gangwon Jo","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767182","display_name":"Jaejin Lee","orcid":"https://orcid.org/0000-0003-4638-8170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaejin Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114677150"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6304,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73359521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"412"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8485982418060303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6735084056854248},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6284399032592773},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5342601537704468},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5069842338562012},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5052366852760315},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4505218267440796},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4500456750392914},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4434199035167694},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4309549629688263},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33472174406051636},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16813823580741882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08918121457099915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485982418060303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6735084056854248},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6284399032592773},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5342601537704468},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5069842338562012},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5052366852760315},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4505218267440796},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4500456750392914},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4434199035167694},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4309549629688263},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33472174406051636},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16813823580741882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08918121457099915},{"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/pact.2013.6618834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2013.6618834","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":[{"display_name":"Affordable and clean energy","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W1500117749","https://openalex.org/W1562841074","https://openalex.org/W1977964157","https://openalex.org/W2010936531","https://openalex.org/W2016357834","https://openalex.org/W2020505145","https://openalex.org/W2028914809","https://openalex.org/W2031781358","https://openalex.org/W2055813380","https://openalex.org/W2062296288","https://openalex.org/W2078845975","https://openalex.org/W2108737583","https://openalex.org/W2110954112","https://openalex.org/W2119609467","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W2147543317","https://openalex.org/W2152301833","https://openalex.org/W2158158791","https://openalex.org/W2186274015","https://openalex.org/W2725179571","https://openalex.org/W3140973819"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2058965144","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2187181201","https://openalex.org/W2132173263","https://openalex.org/W3012895752"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,8,12,33,43,56,61,65,76,81,87,100,133,140,151,163,167,215,226,234],"effect":[6],"of":[7,14,30,67,75,89,121,135,197,233],"work-group":[9,26,73,91,106,111,173,221],"size":[10,63,74,112,165,222],"on":[11,80,183,209],"performance":[13,224],"OpenCL":[15,77,181],"kernels.":[16],"We":[17,108,175,188],"propose":[18],"a":[19,24,71,104,116,122,126,145,171,220],"profiling-based":[20],"algorithm":[21,39,114],"that":[22,119,147,205,232],"finds":[23,170],"good":[25],"size,":[27],"in":[28,42],"terms":[29],"performance,":[31],"for":[32,70],"target":[34],"multicore":[35,186],"CPU":[36],"architecture.":[37],"Our":[38,93],"reduces":[40],"misses":[41,69],"private":[44],"L1":[45],"data":[46],"cache":[47,68],"and":[48,64,125,143,154,169,192,218],"achieves":[49],"load":[50],"balancing":[51],"between":[52],"cores.":[53],"It":[54],"exploits":[55],"polyhedral":[57],"model":[58],"to":[59,98,102,195,231],"estimate":[60],"working-set":[62,164],"number":[66],"parameterized":[72,90],"kernel.":[78],"Based":[79],"profiling":[82],"information,":[83],"it":[84],"heuristically":[85],"searches":[86],"space":[88,96],"sizes.":[92],"virtually-extended":[94],"index":[95],"helps":[97],"increase":[99],"probability":[101],"find":[103],"better":[105],"size.":[107,174],"implement":[109],"our":[110,177,206],"selection":[113],"as":[115,228],"development":[117],"tool":[118,207],"consists":[120],"code":[123,130,142],"generator":[124,131],"search":[127,156,160,193,200,217],"library.":[128],"The":[129,159],"extracts":[132],"polytope":[134],"each":[136],"memory":[137],"reference":[138],"from":[139],"kernel":[141],"generates":[144],"function":[146],"simplifies":[148],"polytopes":[149,168],"using":[150,166,179],"run-time":[152],"information":[153],"invokes":[155],"library":[157,161],"routines.":[158],"calculates":[162],"proper":[172],"evaluate":[176],"approach":[178],"31":[180],"kernels":[182],"four":[184],"different":[185],"CPUs.":[187],"compare":[189],"its":[190],"accuracy":[191],"time":[194],"those":[196],"an":[198],"exhaustive":[199,216,235],"method.":[201],"Experimental":[202],"results":[203],"show":[204],"is,":[208],"average,":[210],"1566":[211],"times":[212],"faster":[213],"than":[214],"selects":[219],"whose":[223],"is":[225],"same":[227],"or":[229],"comparable":[230],"search.":[236]},"counts_by_year":[{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}