{"id":"https://openalex.org/W7125929730","doi":"https://doi.org/10.1145/3774934.3786420","title":"MixFusion: A Patch-Level Parallel Serving System for Mixed-Resolution Diffusion Models","display_name":"MixFusion: A Patch-Level Parallel Serving System for Mixed-Resolution Diffusion Models","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125929730","doi":"https://doi.org/10.1145/3774934.3786420"},"language":null,"primary_location":{"id":"doi:10.1145/3774934.3786420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","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":null,"display_name":"Desen Sun","orcid":"https://orcid.org/0000-0001-8630-7959"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Desen Sun","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8630-7959","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124132930","display_name":"Zepeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zepeng Zhao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0001-5791-3172","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022196610","display_name":"Yuke Wang","orcid":"https://orcid.org/0000-0003-1634-8549"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Wang","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0003-1634-8549","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":136.3,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99779736,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"522","last_page":"536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.4510999917984009,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.4510999917984009,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.09000000357627869,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.08739999681711197,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.9027000069618225},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6263999938964844},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5715000033378601},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.37380000948905945},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.3578000068664551},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.9027000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817799985408783},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5666000247001648},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5525000095367432},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774934.3786420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W3014988774","https://openalex.org/W4312933868","https://openalex.org/W4376851285","https://openalex.org/W4385570204","https://openalex.org/W4387321091","https://openalex.org/W4390872297","https://openalex.org/W4393160345","https://openalex.org/W4394892775","https://openalex.org/W4402726964","https://openalex.org/W4402727245","https://openalex.org/W4402778510","https://openalex.org/W4402816687","https://openalex.org/W4403780756","https://openalex.org/W4409248360","https://openalex.org/W4409367325"],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"diffusion":[2,20],"models":[3,21],"have":[4],"recently":[5],"attracted":[6],"significant":[7],"attention":[8],"due":[9,30],"to":[10,13,31,51,81,111],"their":[11],"ability":[12],"synthesize":[14],"high-fidelity":[15],"photorealistic":[16],"images.":[17],"However,":[18],"serving":[19,44],"would":[22],"suffer":[23],"from":[24],"hardware":[25],"underutilization":[26],"in":[27],"real-world":[28],"settings":[29],"highly":[32],"variable":[33],"request":[34],"resolutions.":[35],"To":[36],"this":[37],"end,":[38],"we":[39],"present":[40],"MixFusion,":[41],"a":[42,61,76],"parallel":[43],"system":[45],"that":[46,103],"exploits":[47],"fine-grained":[48],"patch-level":[49,84],"parallelism":[50],"enable":[52],"efficient":[53],"batching":[54],"of":[55],"mixed-resolution":[56],"requests.":[57,72],"Specifically,":[58],"MixFusion":[59,74,89,104],"introduces":[60],"novel":[62],"patch-based":[63],"processing":[64,69],"workflow,":[65],"significantly":[66],"enabling":[67],"concurrent":[68],"across":[70],"heterogeneous":[71],"Furthermore,":[73],"incorporates":[75],"patch-tailored":[77],"cache":[78],"management":[79],"policy":[80],"exploit":[82],"the":[83,112],"locality":[85],"benefits.":[86],"In":[87],"addition,":[88],"features":[90],"an":[91],"SLO-aware":[92],"scheduling":[93],"strategy":[94],"with":[95],"lightweight":[96],"online":[97],"latency":[98],"prediction.":[99],"Extensive":[100],"evaluation":[101],"demonstrates":[102],"achieves":[105],"30.1%":[106],"higher":[107],"SLO":[108],"satisfaction":[109],"compared":[110],"state-of-the-art":[113],"solutions":[114],"on":[115],"average.":[116],"Our":[117],"code":[118],"is":[119],"available":[120],"at":[121],"https://github.com/desenSunUBW/mixfusion.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}