{"id":"https://openalex.org/W2805149962","doi":"https://doi.org/10.1145/3217189.3217191","title":"rmalloc() and rpipe()","display_name":"rmalloc() and rpipe()","publication_year":2018,"publication_date":"2018-05-31","ids":{"openalex":"https://openalex.org/W2805149962","doi":"https://doi.org/10.1145/3217189.3217191","mag":"2805149962"},"language":"en","primary_location":{"id":"doi:10.1145/3217189.3217191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3217189.3217191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Workshop on Runtime and Operating Systems for Supercomputers","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108248757","display_name":"Udayanga Wickramasinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Udayanga Wickramasinghe","raw_affiliation_strings":["Indiana University, School of Informatics and Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, School of Informatics and Computing","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074260102","display_name":"Andrew Lumsdaine","orcid":"https://orcid.org/0000-0002-9153-6622"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Lumsdaine","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]}],"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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":0.8285545110702515},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.6584882736206055},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6173089742660522},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.5792244672775269},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5254769921302795},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5084037184715271},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4856225550174713},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4552156329154968},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43432140350341797},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34105658531188965},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3395634591579437},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2629227638244629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285545110702515},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.6584882736206055},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6173089742660522},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.5792244672775269},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5254769921302795},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5084037184715271},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4856225550174713},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4552156329154968},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43432140350341797},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34105658531188965},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3395634591579437},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2629227638244629},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3217189.3217191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3217189.3217191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Workshop on Runtime and Operating Systems for Supercomputers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309409","display_name":"Lilly Endowment","ror":"https://ror.org/00cpsd622"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1554453014","https://openalex.org/W1588544414","https://openalex.org/W1746694335","https://openalex.org/W1974070503","https://openalex.org/W2022263640","https://openalex.org/W2061004879","https://openalex.org/W2102650110","https://openalex.org/W2112769850","https://openalex.org/W2122814645","https://openalex.org/W2125102071","https://openalex.org/W2139119167","https://openalex.org/W2491480378","https://openalex.org/W2572246305","https://openalex.org/W2599054664","https://openalex.org/W2755567635","https://openalex.org/W2836867149","https://openalex.org/W3144608703","https://openalex.org/W4205733209","https://openalex.org/W4234689541"],"related_works":["https://openalex.org/W3090586438","https://openalex.org/W4252124899","https://openalex.org/W2782433361","https://openalex.org/W2416075414","https://openalex.org/W2475302168","https://openalex.org/W4366999533","https://openalex.org/W2134569538","https://openalex.org/W3198746232","https://openalex.org/W4322751585","https://openalex.org/W2586360131"],"abstract_inverted_index":{"Optimizing":[0],"communication":[1,119],"is":[2,134],"essential":[3],"for":[4,43,48,70,151,198],"high-performance":[5],"computing":[6,21],"because":[7],"synchronization":[8,79,127],"bottlenecks":[9],"inhibit":[10],"the":[11,71,194],"overall":[12],"performance":[13],"and":[14,35,80,100,117,138,170,188],"scalability":[15],"of":[16,85,95,180],"parallel":[17],"applications.":[18],"Today's":[19],"cutting-edge":[20],"hardware,":[22],"as":[23,25,145,147],"well":[24,146],"networking":[26],"interfaces":[27],"like":[28],"Cray":[29],"Aries/Gemini,":[30],"features":[31],"extremely":[32],"low":[33],"latency":[34],"high":[36],"bandwidth":[37],"remote":[38,86,107],"memory":[39,87,108,115],"access":[40,84],"(RMA)":[41],"operations":[42],"optimized":[44],"data":[45,51,154],"movement.":[46,155],"However":[47],"any":[49],"efficient":[50,153],"movement":[52],"to":[53,65,76,125,136,141,172],"occur":[54],"between":[55],"two":[56,92],"logical":[57],"processing":[58],"units,":[59],"software":[60],"substrates":[61],"must":[62],"be":[63],"able":[64],"properly":[66],"exploit":[67],"hardware":[68],"resources":[69],"underlying":[72],"fabric.":[73],"Overheads":[74],"due":[75],"coarse":[77],"granular":[78],"stalls":[81],"during":[82],"irregular":[83,199],"regions":[88],"may":[89],"hint":[90],"at":[91],"adverse":[93],"effects":[94],"resource":[96],"under-utilization":[97],"in":[98,174],"time":[99],"space.":[101],"We":[102],"introduce":[103],"a":[104,118],"uGNI-based":[105],"distributed":[106],"allocator":[109,164,197],"called":[110,121],"\"rmalloc\"":[111,161,181,196],"which":[112],"expands":[113],"RDMA-enabled":[114],"utilization,":[116],"substrate":[120],"\"rpipe\"":[122],"that":[123,160],"tries":[124],"mitigate":[126],"bottlenecks.":[128],"Our":[129,156],"UNIX-inspired":[130],"RMA":[131,167],"programming":[132],"model":[133],"simple":[135],"use":[137],"equally":[139],"applicable":[140],"both":[142],"higher-level":[143],"applications":[144],"lower-level":[148],"runtime":[149],"systems":[150],"enabling":[152],"micro-benchmark":[157],"results":[158],"suggest":[159],"default":[162,195],"next-fit":[163],"outperforms":[165],"MPI-3.0":[166],"by":[168],"1.5X":[169],"up":[171],"6X":[173],"most":[175],"cases,":[176],"while":[177],"other":[178],"variants":[179],"(i.e.":[182],"best-fit,":[183],"worst-fit)":[184],"reduce":[185],"external":[186],"fragmentation":[187],"perform":[189],"comparably":[190],"or":[191],"better":[192],"than":[193],"RMA.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}