{"id":"https://openalex.org/W2767106296","doi":"https://doi.org/10.1145/3232521","title":"CODA","display_name":"CODA","publication_year":2018,"publication_date":"2018-09-04","ids":{"openalex":"https://openalex.org/W2767106296","doi":"https://doi.org/10.1145/3232521","mag":"2767106296"},"language":"en","primary_location":{"id":"doi:10.1145/3232521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3232521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3232521","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3232521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hyojong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyojong Kim","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ramyad Hadidi","orcid":"https://orcid.org/0000-0002-8731-1084"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramyad Hadidi","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-8731-1084","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lifeng Nai","orcid":"https://orcid.org/0000-0002-8801-9384"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifeng Nai","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-8801-9384","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyesoon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nuwan Jayasena","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nuwan Jayasena","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yasuko Eckert","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yasuko Eckert","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Onur Kayiran","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Onur Kayiran","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gabriel Loh","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gabriel Loh","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6643,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.85657546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"23"},"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":0.9998999834060669,"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":0.9993000030517578,"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/thread","display_name":"Thread (computing)","score":0.6086000204086304},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5332000255584717},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47679999470710754},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.4634000062942505},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.39820000529289246},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.3619999885559082},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.3578000068664551},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887499988079071},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6593999862670898},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.4634000062942505},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.3619999885559082},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.34369999170303345},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3232521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3232521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3232521","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1710.09517","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.09517","pdf_url":"https://arxiv.org/pdf/1710.09517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3232521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3232521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3232521","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4510076937","display_name":"XPS:CLCCA: Optimizing Heterogeneous Platforms for Unstructured Parallelism","funder_award_id":"1337177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6395163341","display_name":"XPS: FULL: CCA: Cymric: A Flexible Processor-Near-Memory System Architecture","funder_award_id":"1533767","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767106296.pdf","grobid_xml":"https://content.openalex.org/works/W2767106296.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1529285927","https://openalex.org/W1584457851","https://openalex.org/W1966344015","https://openalex.org/W1975237352","https://openalex.org/W1975274780","https://openalex.org/W1981943579","https://openalex.org/W1987773847","https://openalex.org/W2007511350","https://openalex.org/W2007964763","https://openalex.org/W2022655850","https://openalex.org/W2031699282","https://openalex.org/W2051388139","https://openalex.org/W2057218453","https://openalex.org/W2078141470","https://openalex.org/W2080592089","https://openalex.org/W2086112773","https://openalex.org/W2090584832","https://openalex.org/W2092324191","https://openalex.org/W2093524602","https://openalex.org/W2100926301","https://openalex.org/W2112547256","https://openalex.org/W2112980698","https://openalex.org/W2114440330","https://openalex.org/W2136268150","https://openalex.org/W2141443190","https://openalex.org/W2150476673","https://openalex.org/W2151233837","https://openalex.org/W2153185479","https://openalex.org/W2155503253","https://openalex.org/W2160875256","https://openalex.org/W2162639668","https://openalex.org/W2164431468","https://openalex.org/W2165697076","https://openalex.org/W2167101788","https://openalex.org/W2169880332","https://openalex.org/W2268589658","https://openalex.org/W2559253174","https://openalex.org/W2612654866","https://openalex.org/W2622164283","https://openalex.org/W2625200202","https://openalex.org/W2738366405","https://openalex.org/W2764065518","https://openalex.org/W2776052384","https://openalex.org/W2887018074","https://openalex.org/W3007497337","https://openalex.org/W4233147525","https://openalex.org/W4236010665"],"related_works":[],"abstract_inverted_index":{"To":[0,117],"exploit":[1],"parallelism":[2,35],"and":[3,17,32,39,74,91,104,129,163,192,195,240],"scalability":[4],"of":[5,53,89,102,109,152,229],"multiple":[6,54,59],"GPUs":[7,60],"in":[8,43,95,106,141],"a":[9,114,122,157,226,246],"system,":[10],"it":[11,140],"is":[12,98],"critical":[13],"to":[14,28,61,82,99,173,205,207],"place":[15,130],"compute":[16,75,84,90,103,191],"data":[18,57,73,105,128,132,153,166,193,221],"together.":[19],"However,":[20],"two":[21],"key":[22,146],"techniques":[23],"that":[24,124,138,164,232],"have":[25],"been":[26],"used":[27,155],"hide":[29],"memory":[30,37,64,112,217],"latency":[31],"improve":[33,62,83],"thread-level":[34],"(TLP),":[36],"interleaving,":[38],"thread":[40,79,136,158,184],"block":[41,80,137,159,185],"scheduling,":[42],"traditional":[44],"GPU":[45,175],"systems":[46],"are":[47,76,148],"at":[48],"odds":[49],"with":[50,113,134,176,202],"efficient":[51],"use":[52],"GPUs.":[55],"Distributing":[56],"across":[58,225],"overall":[63],"bandwidth":[65],"utilization":[66,86],"incurs":[67],"high":[68],"remote":[69,243],"traffic":[70,244],"when":[71],"the":[72,107,131,135,142,150,182,233],"misaligned.":[77],"Nondeterministic":[78],"scheduling":[81,186],"resource":[85],"impedes":[87],"co-placement":[88,101],"data.":[92],"Our":[93,223],"goal":[94],"this":[96,118],"work":[97],"enable":[100],"presence":[108],"fine-grained":[110],"interleaved":[111,178,216],"low-cost":[115],"approach.":[116],"end,":[119],"we":[120,188,211],"propose":[121],"mechanism":[123,235],"identifies":[125],"exclusively":[126,154],"accessed":[127],"along":[133],"accesses":[139],"same":[143],"GPU.":[144],"The":[145],"ideas":[147],"(1)":[149],"amount":[151],"by":[156,197,238],"can":[160,170,189,212],"be":[161,171],"estimated,":[162],"exclusive":[165],"(of":[167],"any":[168],"size)":[169],"localized":[172],"one":[174],"coarse-grained":[177],"pages;":[179],"(2)":[180],"using":[181,198],"affinity-based":[183],"policy,":[187],"co-place":[190],"together;":[194],"(3)":[196],"dual":[199],"address":[200],"mode":[201],"lightweight":[203],"changes":[204],"virtual":[206],"physical":[208],"page":[209],"mappings,":[210],"selectively":[213],"choose":[214],"different":[215],"pages":[218],"for":[219],"each":[220],"structure.":[222],"evaluations":[224],"wide":[227],"range":[228],"workloads":[230],"show":[231],"proposed":[234],"improves":[236],"performance":[237],"31%":[239],"reduces":[241],"38%":[242],"over":[245],"baseline":[247],"system.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2017-11-10T00:00:00"}