{"id":"https://openalex.org/W2765909029","doi":"https://doi.org/10.1145/3148226.3148232","title":"Leveraging NVLINK and asynchronous data transfer to scale beyond the memory capacity of GPUs","display_name":"Leveraging NVLINK and asynchronous data transfer to scale beyond the memory capacity of GPUs","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2765909029","doi":"https://doi.org/10.1145/3148226.3148232","mag":"2765909029"},"language":"en","primary_location":{"id":"doi:10.1145/3148226.3148232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148226.3148232","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 Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","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/A5055298466","display_name":"David Appelhans","orcid":"https://orcid.org/0000-0003-1433-9198"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Appelhans","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032038945","display_name":"Bob Walkup","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bob Walkup","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055298466"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4506,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62721753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T13465","display_name":"Graphite, nuclear technology, radiation studies","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9944999814033508,"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/speedup","display_name":"Speedup","score":0.8482645750045776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8473595380783081},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7462388277053833},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7299760580062866},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6018902063369751},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4340651035308838},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4149092733860016},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32047125697135925},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1308775246143341},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08532541990280151}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8482645750045776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473595380783081},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7462388277053833},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7299760580062866},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6018902063369751},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4340651035308838},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4149092733860016},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32047125697135925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1308775246143341},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08532541990280151},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3148226.3148232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148226.3148232","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 Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W114646346","https://openalex.org/W1570327376","https://openalex.org/W2082821421","https://openalex.org/W2106657393","https://openalex.org/W2120250211","https://openalex.org/W2295675706","https://openalex.org/W2472854363","https://openalex.org/W2483785700","https://openalex.org/W2529487057","https://openalex.org/W2534432699","https://openalex.org/W2622717088"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2351992668","https://openalex.org/W1662038552","https://openalex.org/W2168758875","https://openalex.org/W4246549241","https://openalex.org/W2410733619","https://openalex.org/W3021568819","https://openalex.org/W2963483475"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,120],"demonstrate":[4,121],"the":[5,29,35,88,108,129,134,138,159,167,170],"utility":[6],"of":[7,42,55,59,65,81,86,137,161,172],"fast":[8],"GPU":[9,30,84],"to":[10,13,22,52,63,141,152],"CPU":[11],"interconnects":[12],"weak":[14,176],"scale":[15],"on":[16],"hierarchical":[17,83],"nodes":[18],"without":[19],"being":[20,50],"limited":[21],"problem":[23,130],"sizes":[24],"that":[25,67,124],"fit":[26],"only":[27],"in":[28,158],"memory":[31,135],"capacity.":[32],"We":[33],"show":[34],"speedup":[36,123],"possible":[37],"for":[38,94],"a":[39,122,149],"new":[40,74],"regime":[41],"algorithms":[43],"which":[44],"traditionally":[45],"have":[46],"not":[47],"benefited":[48],"from":[49],"ported":[51],"GPUs":[53],"because":[54],"an":[56,79],"insufficient":[57],"amount":[58],"computational":[60],"work":[61],"relative":[62],"bytes":[64],"data":[66,104],"must":[68],"be":[69],"transferred":[70],"(offload":[71],"intensity).":[72],"This":[73],"capability":[75],"is":[76,148],"demonstrated":[77],"with":[78],"example":[80],"our":[82],"port":[85],"UMT,":[87,162],"51K":[89],"line":[90],"CORAL":[91],"benchmark":[92],"application":[93],"Lawrence":[95],"Livermore":[96],"National":[97],"Lab's":[98],"radiation":[99],"transport":[100],"code.":[101],"By":[102],"overlapping":[103],"transfers":[105],"and":[106,116,157],"using":[107],"NVLINK":[109],"connection":[110],"between":[111],"IBM":[112],"POWER":[113],"8":[114],"CPUs":[115],"NVIDIA":[117],"P100":[118],"GPUs,":[119],"continues":[125],"even":[126],"when":[127],"scaling":[128],"size":[131],"well":[132],"beyond":[133],"capacity":[136],"GPUs.":[139],"Scaling":[140],"large":[142,155,163],"local":[143,164],"domains":[144,165],"per":[145],"MPI":[146,173],"process":[147],"necessary":[150],"step":[151],"solving":[153],"very":[154],"problems,":[156],"case":[160],"improve":[166],"convergence":[168],"as":[169],"number":[171],"ranks":[174],"are":[175],"scaled.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}