{"id":"https://openalex.org/W3116086216","doi":"https://doi.org/10.1109/hpec43674.2020.9286189","title":"Accelerating Distributed Inference of Sparse Deep Neural Networks via Mitigating the Straggler Effect","display_name":"Accelerating Distributed Inference of Sparse Deep Neural Networks via Mitigating the Straggler Effect","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3116086216","doi":"https://doi.org/10.1109/hpec43674.2020.9286189","mag":"3116086216"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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":"https://openalex.org/A5101457271","display_name":"Mohammad Hasanzadeh Mofrad","orcid":"https://orcid.org/0000-0003-4369-6928"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Hasanzadeh Mofrad","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072934511","display_name":"Yousuf Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Yousuf Ahmad","raw_affiliation_strings":["Carnegie Mellon University in Qatar, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018894377","display_name":"Mohammad Hammoud","orcid":"https://orcid.org/0000-0002-5742-6147"},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohammad Hammoud","raw_affiliation_strings":["Carnegie Mellon University in Qatar, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University in Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I4210089979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101457271"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":0.4885,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66985951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.818557858467102},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.7895561456680298},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7233253121376038},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5921915173530579},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5762639045715332},{"id":"https://openalex.org/keywords/quicksort","display_name":"Quicksort","score":0.5479032397270203},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5344281196594238},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5247257351875305},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4552641212940216},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4339233636856079},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.41504332423210144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26679378747940063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20297542214393616},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.09206926822662354},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.07833302021026611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818557858467102},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.7895561456680298},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7233253121376038},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5921915173530579},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5762639045715332},{"id":"https://openalex.org/C2778937211","wikidata":"https://www.wikidata.org/wiki/Q486598","display_name":"Quicksort","level":4,"score":0.5479032397270203},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5344281196594238},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5247257351875305},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4552641212940216},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4339233636856079},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.41504332423210144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26679378747940063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20297542214393616},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.09206926822662354},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.07833302021026611},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7909653302","display_name":null,"funder_award_id":"CCF-1725657","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W40549020","https://openalex.org/W1442374986","https://openalex.org/W1999653836","https://openalex.org/W2007259720","https://openalex.org/W2015606516","https://openalex.org/W2016559894","https://openalex.org/W2062022900","https://openalex.org/W2089437293","https://openalex.org/W2102113734","https://openalex.org/W2112796928","https://openalex.org/W2134237243","https://openalex.org/W2168231600","https://openalex.org/W2186615578","https://openalex.org/W2198403777","https://openalex.org/W2300242332","https://openalex.org/W2512971201","https://openalex.org/W2787998955","https://openalex.org/W2803210444","https://openalex.org/W2808133870","https://openalex.org/W2859678021","https://openalex.org/W2889677830","https://openalex.org/W2892888505","https://openalex.org/W2896457183","https://openalex.org/W2953384591","https://openalex.org/W2962844195","https://openalex.org/W2962911728","https://openalex.org/W2963037989","https://openalex.org/W2963341956","https://openalex.org/W2964336816","https://openalex.org/W2964337156","https://openalex.org/W2972087877","https://openalex.org/W2973134322","https://openalex.org/W2977720775","https://openalex.org/W2987484405","https://openalex.org/W2990689488","https://openalex.org/W2991043234","https://openalex.org/W3095829752","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3101584733","https://openalex.org/W3101812505","https://openalex.org/W4285719527","https://openalex.org/W4301239768","https://openalex.org/W6601618085","https://openalex.org/W6628377381","https://openalex.org/W6675365184","https://openalex.org/W6684859321","https://openalex.org/W6698200048","https://openalex.org/W6713134421","https://openalex.org/W6910447991"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W2468095077","https://openalex.org/W305742777","https://openalex.org/W2121547511"],"abstract_inverted_index":{"Once":[0],"a":[1,32,92,114,119,131,169],"Deep":[2],"Neural":[3],"Network":[4],"(DNN)":[5],"is":[6],"trained,":[7],"an":[8],"inference":[9],"algorithm":[10],"retains":[11],"the":[12,67,70,73,76,85,150,175,196],"learning":[13],"and":[14,45,72,127,187],"applies":[15],"it":[16,158,162],"to":[17,49,53,118,164,167,208,210,214],"batches":[18],"of":[19,28,97,109,134,154,178],"data.":[20],"The":[21],"trained":[22],"DNN":[23,200],"can":[24,58],"be":[25,59],"sparse":[26,34,40,56,199],"because":[27,96],"pruning":[29],"or":[30,63],"following":[31],"preset":[33],"connectivity":[35],"pattern.":[36],"Inference":[37],"in":[38],"such":[39],"networks":[41],"requires":[42],"less":[43],"space":[44],"time":[46],"complexities":[47],"compared":[48,213],"dense":[50,54],"ones.":[51],"Similar":[52],"DNNs,":[55],"DNNs":[57],"parallelized":[60],"using":[61,195],"model":[62,128,155,165,188],"data":[64,104,126,146,179,186],"parallelism,":[65,147],"whereby":[66],"former":[68],"partitions":[69,75,110],"network":[71],"latter":[74],"input":[77],"among":[78,122],"multiple":[79],"threads.":[80],"Model":[81],"parallelism":[82,105,135,166,184],"efficiently":[83],"utilizes":[84],"Last":[86],"Level":[87],"Cache":[88],"(LLC)":[89],"but":[90,111],"has":[91],"heavy":[93],"synchronization":[94,152],"cost":[95,153],"compulsory":[98],"reductions":[99],"per":[100],"layer.":[101],"In":[102,140],"contrast,":[103],"allows":[106],"independent":[107],"execution":[108],"suffers":[112],"from":[113],"straggler":[115,176],"effect":[116,177],"due":[117],"load":[120],"imbalance":[121],"partitions.":[123],"We":[124,181],"combine":[125],"parallelisms":[129,189,194],"through":[130],"new":[132],"type":[133],"that":[136],"we":[137,205],"denote":[138],"data-then-model.":[139],"data-then-model,":[141],"each":[142],"thread":[143],"starts":[144],"with":[145,185],"thus":[148],"mitigating":[149],"per-layer":[151],"parallelism.":[156,180],"After":[157],"finishes":[159],"its":[160],"partition,":[161],"switches":[163],"support":[168],"slower":[170],"active":[171],"thread,":[172],"hence,":[173],"alleviating":[174],"compare":[182],"data-then-model":[183],"as":[190,192],"well":[191],"task-based":[193],"IEEE":[197],"HPEC":[198],"challenge":[201],"dataset.":[202],"On":[203],"average,":[204],"achieve":[206],"up":[207],"10":[209],"65%":[211],"speedup":[212],"these":[215],"parallelisms.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}