{"id":"https://openalex.org/W2898048683","doi":"https://doi.org/10.1145/3243176.3243179","title":"ComP-net","display_name":"ComP-net","publication_year":2018,"publication_date":"2018-10-10","ids":{"openalex":"https://openalex.org/W2898048683","doi":"https://doi.org/10.1145/3243176.3243179","mag":"2898048683"},"language":"en","primary_location":{"id":"doi:10.1145/3243176.3243179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3243176.3243179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3243176.3243179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3243176.3243179","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005659585","display_name":"Michael LeBeane","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael LeBeane","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048039700","display_name":"Khaled Hamidouche","orcid":"https://orcid.org/0000-0003-4836-5335"},"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":"Khaled Hamidouche","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009103835","display_name":"Brad Benton","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":"Brad Benton","raw_affiliation_strings":["Advanced Micro Devices, Inc"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021886781","display_name":"Maur\u00edcio Breternitz","orcid":"https://orcid.org/0000-0003-1752-6255"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Mauricio Breternitz","raw_affiliation_strings":["University of Lisbon"],"affiliations":[{"raw_affiliation_string":"University of Lisbon","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109010789","display_name":"Steven K. Reinhardt","orcid":"https://orcid.org/0000-0002-2479-0030"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Steven K. Reinhardt","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068885069","display_name":"Lizy K. John","orcid":"https://orcid.org/0000-0002-8747-5214"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizy K. John","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005659585"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.2627,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53865682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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/T11478","display_name":"Caching and Content Delivery","score":0.998199999332428,"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":0.8634263277053833},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7097063064575195},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6796066164970398},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5749682188034058},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.542711079120636},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5240938067436218},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5115779042243958},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5004415512084961},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49238812923431396},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.44351381063461304},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.4412706792354584},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4175562858581543},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3397807478904724},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2698117792606354},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.12027531862258911},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.11484494805335999},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0966501533985138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8634263277053833},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7097063064575195},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6796066164970398},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5749682188034058},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.542711079120636},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5240938067436218},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5115779042243958},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5004415512084961},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49238812923431396},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.44351381063461304},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.4412706792354584},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4175562858581543},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3397807478904724},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2698117792606354},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.12027531862258911},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.11484494805335999},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0966501533985138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3243176.3243179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3243176.3243179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3243176.3243179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3243176.3243179","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3243176.3243179","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3243176.3243179","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G1886981331","display_name":null,"funder_award_id":"project UID","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2262735342","display_name":null,"funder_award_id":"UID/CEC/50021/2013","funder_id":"https://openalex.org/F4320335059","funder_display_name":"Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa"},{"id":"https://openalex.org/G2475301043","display_name":"EAGER: Improving Reproducibility of Computing Research using Proxy Workloads","funder_award_id":"1745813","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G309696157","display_name":null,"funder_award_id":"UID/CEC/50021/2013","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5351565279","display_name":null,"funder_award_id":"1745813 and 1725743","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7340972926","display_name":null,"funder_award_id":"other","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"},{"id":"https://openalex.org/F4320335059","display_name":"Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2898048683.pdf","grobid_xml":"https://content.openalex.org/works/W2898048683.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1446278828","https://openalex.org/W1590013973","https://openalex.org/W1968188490","https://openalex.org/W1988756252","https://openalex.org/W2054522323","https://openalex.org/W2057363235","https://openalex.org/W2062964224","https://openalex.org/W2121444153","https://openalex.org/W2143700077","https://openalex.org/W2147657366","https://openalex.org/W2150618958","https://openalex.org/W2170382128","https://openalex.org/W2398969933","https://openalex.org/W2402285027","https://openalex.org/W2488497244","https://openalex.org/W2521121845","https://openalex.org/W2557367833","https://openalex.org/W2730016893","https://openalex.org/W2767210925","https://openalex.org/W2767308239","https://openalex.org/W2785822536","https://openalex.org/W2884677265"],"related_works":["https://openalex.org/W2385763152","https://openalex.org/W1571368810","https://openalex.org/W2506225776","https://openalex.org/W1558545464","https://openalex.org/W1484089092","https://openalex.org/W1579918296","https://openalex.org/W1503860218","https://openalex.org/W2962978274","https://openalex.org/W1534227216","https://openalex.org/W2289958017"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"in":[2,97,121],"GPU":[3,26,70,90],"networking":[4,23,126],"advocates":[5],"a":[6,25,49,92,129],"host-centric":[7],"model":[8],"that":[9,105],"reduces":[10],"performance":[11,110],"and":[12,41,85,115,134],"increases":[13],"code":[14],"complexity.":[15],"Recently,":[16],"researchers":[17],"have":[18],"explored":[19],"several":[20],"techniques":[21,127],"for":[22],"within":[24],"kernel":[27],"itself.":[28],"These":[29],"approaches,":[30],"however,":[31],"suffer":[32],"from":[33],"high":[34],"latency,":[35],"waste":[36],"energy":[37,122],"on":[38,48,68,88],"the":[39,62,69,82,89,98],"host,":[40],"are":[42],"not":[43],"scalable":[44],"with":[45],"larger/more":[46],"GPUs":[47],"node.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"introduce":[55],"Command":[56,83],"Processor":[57],"Networking":[58],"(ComP-Net),":[59],"which":[60],"leverages":[61],"availability":[63],"of":[64],"scalar":[65],"cores":[66],"integrated":[67],"itself":[71],"to":[72,113,118],"provide":[73,116],"high-performance":[74],"intra-kernel":[75],"networking.":[76],"ComP-Net":[77,106],"enables":[78],"efficient":[79],"synchronization":[80],"between":[81],"Processors":[84],"Compute":[86],"Units":[87],"through":[91],"line":[93],"locking":[94],"scheme":[95],"implemented":[96],"GPU's":[99],"shared":[100],"last-level":[101],"cache.":[102],"We":[103],"illustrate":[104],"can":[107],"improve":[108],"application":[109],"by":[111],"up":[112,117],"20%":[114],"50%":[119],"reduction":[120],"consumption":[123],"vs.":[124],"competing":[125],"across":[128],"Jacobi":[130],"stencil,":[131],"allreduce":[132],"collective,":[133],"machine":[135],"learning":[136],"applications.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2018-10-26T00:00:00"}
