{"id":"https://openalex.org/W4316252433","doi":"https://doi.org/10.1145/3547276.3548626","title":"A framework for low communication approaches for large scale 3D convolution","display_name":"A framework for low communication approaches for large scale 3D convolution","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252433","doi":"https://doi.org/10.1145/3547276.3548626"},"language":"en","primary_location":{"id":"doi:10.1145/3547276.3548626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548626","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548626","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548626","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078947104","display_name":"Anuva Kulkarni","orcid":"https://orcid.org/0000-0001-8896-7504"},"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":"Anuva Kulkarni","raw_affiliation_strings":["Carnegie Mellon University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States of America","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863660","display_name":"Jelena Kova\u010devi\u0107","orcid":"https://orcid.org/0000-0003-0139-2803"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jelena Kovacevic","raw_affiliation_strings":["New York University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, United States of America","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"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":"Franz Franchetti","raw_affiliation_strings":["Carnegie Mellon University, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States of America","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.998199999332428,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9807999730110168,"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":0.820720911026001},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7251484394073486},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6740720272064209},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5615271329879761},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.543928325176239},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5093868374824524},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44507795572280884},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4382660388946533},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41873544454574585},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.390123188495636},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3809453845024109},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35658693313598633},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3290897309780121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11734819412231445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10318461060523987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820720911026001},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7251484394073486},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6740720272064209},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5615271329879761},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.543928325176239},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5093868374824524},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44507795572280884},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4382660388946533},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41873544454574585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.390123188495636},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3809453845024109},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35658693313598633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3290897309780121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11734819412231445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10318461060523987},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3547276.3548626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548626","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548626","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3547276.3548626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3547276.3548626","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3547276.3548626","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4316252433.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W658512522","https://openalex.org/W1494749725","https://openalex.org/W1573878051","https://openalex.org/W1589918049","https://openalex.org/W1965092590","https://openalex.org/W1979796968","https://openalex.org/W2011253351","https://openalex.org/W2014812733","https://openalex.org/W2024527159","https://openalex.org/W2025759093","https://openalex.org/W2027978766","https://openalex.org/W2029540202","https://openalex.org/W2058094241","https://openalex.org/W2071739952","https://openalex.org/W2102182691","https://openalex.org/W2133557963","https://openalex.org/W2140980608","https://openalex.org/W2147688967","https://openalex.org/W2546716216","https://openalex.org/W2803258762","https://openalex.org/W2898200251","https://openalex.org/W3017247523","https://openalex.org/W3036255981","https://openalex.org/W3036442151","https://openalex.org/W3197491507","https://openalex.org/W4251637954","https://openalex.org/W6759284451","https://openalex.org/W7131907535"],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W2978884468","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W4390971171","https://openalex.org/W4385338604","https://openalex.org/W3081626085","https://openalex.org/W4367355863"],"abstract_inverted_index":{"Large-scale":[0],"3D":[1,38,144],"convolutions":[2],"computed":[3],"using":[4],"parallel":[5],"Fast":[6],"Fourier":[7],"Transforms":[8],"(FFTs)":[9],"demand":[10],"multiple":[11,76,96],"all-to-all":[12,77,97],"communication":[13,43,71,78,194],"steps,":[14],"which":[15,218],"cause":[16],"bottlenecks":[17],"on":[18,50,64],"computing":[19,53,187],"clusters.":[20],"Since":[21],"data":[22,137,185],"transfer":[23],"speeds":[24],"to/from":[25],"memory":[26],"have":[27],"not":[28],"increased":[29,141],"proportionally":[30],"to":[31,47,188,198,231],"computational":[32],"capacity":[33],"(in":[34],"terms":[35],"of":[36,56,110,128,143,151,181,213],"FLOPs),":[37],"FFTs":[39],"become":[40],"bounded":[41],"by":[42,125,136],"and":[44,99,131,177,186,204,225],"are":[45],"difficult":[46],"scale,":[48],"especially":[49],"modern":[51],"heterogeneous":[52],"platforms":[54],"consisting":[55],"accelerators":[57],"like":[58],"GPUs.":[59],"Existing":[60],"HPC":[61],"frameworks":[62],"focus":[63],"optimizing":[65],"the":[66,114,129,133,159,182,184,211],"isolated":[67],"FFT":[68],"algorithm":[69],"or":[70],"patterns,":[72],"but":[73],"still":[74],"require":[75],"steps":[79],"during":[80],"convolution.":[81,145],"In":[82,196],"this":[83],"work,":[84],"we":[85,209],"present":[86],"a":[87,111,215],"strategy":[88],"for":[89,173,206,222,227],"scalable":[90],"convolution":[91,119,134,191],"such":[92],"that":[93],"it":[94],"avoids":[95],"exchanges,":[98],"also":[100],"optimizes":[101],"necessary":[102],"communication.":[103],"We":[104],"provide":[105],"proof-of-concept":[106],"results":[107,148],"under":[108],"assumptions":[109],"use":[112,212],"case,":[113],"MASSIF":[115],"Hooke\u2019s":[116],"law":[117],"simulation":[118],"kernel.":[120],"Our":[121,146,168],"method":[122,169],"localizes":[123],"computation":[124],"exploiting":[126],"properties":[127],"data,":[130],"approximates":[132],"result":[135,166],"compression,":[138],"resulting":[139],"in":[140,158],"scalability":[142,150],"preliminary":[147],"show":[149],"8":[152],"times":[153],"more":[154],"than":[155],"traditional":[156],"methods":[157],"same":[160],"compute":[161],"resources":[162],"without":[163],"adversely":[164],"affecting":[165],"accuracy.":[167],"can":[170,219],"be":[171,220],"adapted":[172],"first-principle":[174],"scientific":[175],"simulations":[176],"leverages":[178],"cross-disciplinary":[179],"knowledge":[180],"application,":[183],"perform":[189],"large-scale":[190],"while":[192],"avoiding":[193],"bottlenecks.":[195],"order":[197],"make":[199],"our":[200],"approach":[201],"widely":[202],"usable":[203],"adaptable":[205],"emerging":[207],"challenges,":[208],"discuss":[210],"FFTX,":[214],"novel":[216],"framework":[217],"used":[221],"platform-agnostic":[223],"specification":[224],"optimization":[226],"algorithmic":[228],"approaches":[229],"similar":[230],"ours.":[232]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}