{"id":"https://openalex.org/W3177445289","doi":"https://doi.org/10.1109/ipdps49936.2021.00053","title":"Designing High-Performance MPI Libraries with On-the-fly Compression for Modern GPU Clusters","display_name":"Designing High-Performance MPI Libraries with On-the-fly Compression for Modern GPU Clusters","publication_year":2021,"publication_date":"2021-05-01","ids":{"openalex":"https://openalex.org/W3177445289","doi":"https://doi.org/10.1109/ipdps49936.2021.00053","mag":"3177445289"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps49936.2021.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5028296912","display_name":"Qinghua Zhou","orcid":"https://orcid.org/0009-0001-8490-7990"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Q. Zhou","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076405830","display_name":"Ching-Hsiang Chu","orcid":"https://orcid.org/0000-0002-6752-3135"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Chu","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063428704","display_name":"Naresh Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. S. Kumar","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057608531","display_name":"Pouya Kousha","orcid":"https://orcid.org/0009-0004-7507-0940"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Kousha","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066016137","display_name":"S. Mahdieh Ghazimirsaeed","orcid":"https://orcid.org/0000-0001-8510-3145"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. M. Ghazimirsaeed","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Subramoni","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. K. Panda","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.126,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.838194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Distributed Storage Systems and Network Coding","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Distributed Storage Systems and Network Coding","score":0.9999,"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/T11269","display_name":"Text Compression and Indexing Algorithms","score":0.9994,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Performance Optimization","score":0.9981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.8994744},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.6989928},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU Computing","score":0.640175},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"High-Performance Computing","score":0.593595},{"id":"https://openalex.org/keywords/performance-optimization","display_name":"Performance Optimization","score":0.57225},{"id":"https://openalex.org/keywords/compression","display_name":"Compression","score":0.536456},{"id":"https://openalex.org/keywords/multicore-architectures","display_name":"Multicore Architectures","score":0.519913}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.8994744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871536},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.6989928},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6482692},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.61378217},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6072386},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.48826933},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.4405774},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.430965},{"id":"https://openalex.org/C172173386","wikidata":"https://www.wikidata.org/wiki/Q79984","display_name":"Ethernet","level":2,"score":0.42312068},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41282165},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32386923},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26685926},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26431274},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22176138},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.12395531},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps49936.2021.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.46,"id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W1576599451","https://openalex.org/W1585237817","https://openalex.org/W1675745493","https://openalex.org/W1902814702","https://openalex.org/W1964981582","https://openalex.org/W2003343545","https://openalex.org/W2046288017","https://openalex.org/W2052440657","https://openalex.org/W2098641089","https://openalex.org/W2118906989","https://openalex.org/W2142265837","https://openalex.org/W2151434489","https://openalex.org/W2164030956","https://openalex.org/W2169084173","https://openalex.org/W2486202470","https://openalex.org/W2527672088","https://openalex.org/W2808274640","https://openalex.org/W2883037792","https://openalex.org/W2913395963","https://openalex.org/W2992165038","https://openalex.org/W3006113130","https://openalex.org/W3037565727","https://openalex.org/W3037979316","https://openalex.org/W3039165326","https://openalex.org/W3039861198","https://openalex.org/W3043058721","https://openalex.org/W57243869"],"related_works":["https://openalex.org/W4390917331","https://openalex.org/W4282599985","https://openalex.org/W4253931064","https://openalex.org/W4245217724","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W2139382794","https://openalex.org/W1984788566","https://openalex.org/W1978254186","https://openalex.org/W1964981582"],"abstract_inverted_index":{"While":[0],"the":[1,13,16,40,48,52,58,63,70,73,81,91,98,127,140,188,206,213,231,238,243,250],"memory":[2],"bandwidth":[3],"of":[4,28,83,93,160,210,233],"accelerators":[5],"such":[6,19],"as":[7,20],"GPU":[8,153,207,251],"has":[9],"significantly":[10,248],"improved":[11],"over":[12],"last":[14],"decade,":[15],"commodity":[17],"networks":[18],"Ethernet":[21],"and":[22,118,138,162,167,175,190,202,216,261],"InfiniBand":[23],"are":[24,34,112],"lagging":[25],"in":[26,76,205,227],"terms":[27],"raw":[29],"throughput":[30],"creating.":[31],"Although":[32],"there":[33],"significant":[35,185],"research":[36],"efforts":[37],"on":[38,100],"improving":[39],"large":[41],"message":[42,86,148,173],"data":[43,59,94,259],"transfers":[44],"for":[45,115,150,254],"GPU-resident":[46],"data,":[47],"inter-node":[49,104],"communication":[50,105,128,252],"remains":[51],"major":[53],"performance":[54,122,253],"bottleneck":[55],"due":[56],"to":[57,89,120,144,169,197,200,224,247],"explosion":[60],"created":[61],"by":[62],"emerging":[64],"High-Performance":[65],"Computing":[66],"(HPC)":[67],"applications.":[68,263],"On":[69],"other":[71],"hand,":[72],"recent":[74],"developments":[75],"GPU-based":[77,109,244],"compression":[78,87,110,149,164,174,245],"algorithms":[79],"exemplify":[80],"potential":[82],"using":[84],"high-performance":[85],"techniques":[88,246],"reduce":[90],"volume":[92],"transferred":[95],"thereby":[96],"reducing":[97],"load":[99],"an":[101],"already":[102],"overloaded":[103],"fabric.":[106],"The":[107,192],"existing":[108,158],"schemes":[111],"not":[113],"designed":[114],"\u201con-the-fly\u201d":[116],"execution":[117],"lead":[119],"severe":[121],"degradation":[123],"when":[124],"integrated":[125],"into":[126],"libraries.":[129],"In":[130],"this":[131,136,236],"paper,":[132],"we":[133,221],"take":[134],"up":[135,199,223],"challenge":[137],"redesign":[139],"MVAPICH2":[141],"MPI":[142,256],"library":[143],"enable":[145],"high-performance,":[146,171],"on-the-fly":[147,172],"modern,":[151],"dense":[152],"clusters.":[154],"We":[155,177],"also":[156],"enhance":[157],"implementations":[159],"lossless":[161],"lossy":[163],"algorithms,":[165],"MPC":[166],"ZFP,":[168],"provide":[170,198],"decompression.":[176],"demonstrate":[178],"that":[179,241],"our":[180,234],"proposed":[181,193],"designs":[182],"can":[183],"offer":[184],"benefits":[186],"at":[187],"microbenchmark":[189],"application-levels.":[191],"design":[194],"is":[195,237],"able":[196],"19%":[201],"37%":[203],"improvement":[204,226],"computing":[208],"flops":[209],"AWP-ODC":[211],"with":[212],"enhanced":[214],"MPCOPT":[215],"ZFP-OPT":[217],"schemes,":[218],"respectively.":[219],"Moreover,":[220],"gain":[222],"1.56x":[225],"Dask":[228],"throughput.":[229],"To":[230],"best":[232],"knowledge,":[235],"first":[239],"work":[240],"leverages":[242],"improve":[249],"various":[255],"primitives,":[257],"MPI-based":[258],"science,":[260],"HPC":[262]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3177445289","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7}],"updated_date":"2024-11-04T09:50:56.135629","created_date":"2021-07-05"}
