{"id":"https://openalex.org/W4416388688","doi":"https://doi.org/10.1145/3767295.3769370","title":"Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering","display_name":"Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W4416388688","doi":"https://doi.org/10.1145/3767295.3769370"},"language":"en","primary_location":{"id":"doi:10.1145/3767295.3769370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769370","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014087671","display_name":"Ke Hong","orcid":"https://orcid.org/0000-0002-5768-6037"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Hong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5768-6037","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663884","display_name":"Xiuhong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4896-121X","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036792719","display_name":"Minxu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minxu Liu","raw_affiliation_strings":["Infinigence-AI, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-1905-0977","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076000240","display_name":"Qiuli Mao","orcid":"https://orcid.org/0009-0004-8777-2579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuli Mao","raw_affiliation_strings":["Infinigence-AI, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-8777-2579","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101757650","display_name":"Tao Wu","orcid":"https://orcid.org/0000-0001-9456-4082"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianqi Wu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3445-7055","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101362200","display_name":"Zixiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiao Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1273-2573","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108270347","display_name":"Lufang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lufang Chen","raw_affiliation_strings":["Infinigence-AI, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-8345-3882","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435269","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-2254-7723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0500-5824","affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568856","display_name":"Yichong Zhang","orcid":"https://orcid.org/0000-0001-8282-3200"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichong Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0937-3116","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103138440","display_name":"Zhenhua Zhu","orcid":"https://orcid.org/0009-0007-9259-7180"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9259-7180","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102805465","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0002-8464-0130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0849-3252","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445112","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-8731-0156"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5014087671"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00714121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1894","last_page":"1911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8942000269889832,"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":0.8942000269889832,"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":0.039799999445676804,"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/T14347","display_name":"Big Data and Digital Economy","score":0.010200000368058681,"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/bottleneck","display_name":"Bottleneck","score":0.7799999713897705},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6883999705314636},{"id":"https://openalex.org/keywords/models-of-communication","display_name":"Models of communication","score":0.46549999713897705},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.39399999380111694},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.37869998812675476},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.37380000948905945},{"id":"https://openalex.org/keywords/communication-complexity","display_name":"Communication complexity","score":0.3434999883174896},{"id":"https://openalex.org/keywords/communications-protocol","display_name":"Communications protocol","score":0.34060001373291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829200029373169},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7799999713897705},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6883999705314636},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.37869998812675476},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767295.3769370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769370","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.19519","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.19519","pdf_url":"https://arxiv.org/pdf/2504.19519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3767295.3769370","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769370","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"models":[1],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"across":[6],"various":[7],"applications,":[8],"driving":[9],"the":[10,44,63,71,81],"demand":[11],"for":[12,42,95],"multi-GPU":[13,21],"computing.":[14],"Inter-GPU":[15],"communication":[16,36,45,77,86],"becomes":[17,38],"a":[18],"bottleneck":[19],"in":[20],"computing":[22],"systems,":[23],"particularly":[24],"on":[25],"consumer-grade":[26],"GPUs.":[27],"By":[28],"exploiting":[29],"concurrent":[30],"hardware":[31],"execution,":[32],"overlapping":[33,54,60,64],"computation":[34,68],"and":[35,52,75],"latency":[37],"an":[39,50],"effective":[40],"technique":[41],"mitigating":[43],"overhead.":[46],"We":[47],"identify":[48],"that":[49],"efficient":[51],"adaptable":[53],"design":[55],"should":[56],"satisfy":[57],"(1)":[58],"tile-wise":[59],"to":[61,69,79,92],"maximize":[62],"opportunity,":[65],"(2)":[66],"interference-free":[67],"maintain":[70],"original":[72],"computational":[73],"performance,":[74],"(3)":[76],"agnosticism":[78],"reduce":[80],"development":[82],"burden":[83],"against":[84],"varying":[85],"primitives.":[87],"Nevertheless,":[88],"current":[89],"designs":[90],"fail":[91],"simultaneously":[93],"optimize":[94],"all":[96],"of":[97],"those":[98],"features.":[99]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
