{"id":"https://openalex.org/W6979316640","doi":null,"title":"Modeling Utilization to Identify Shared-Memory Atomic Bottlenecks","display_name":"Modeling Utilization to Identify Shared-Memory Atomic Bottlenecks","publication_year":2025,"publication_date":"2025-03-23","ids":{"openalex":"https://openalex.org/W6979316640"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.17893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17893","pdf_url":"https://arxiv.org/pdf/2503.17893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.17893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dong, Rongcui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Rongcui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006053754","display_name":"Sreepathi Pai","orcid":"https://orcid.org/0000-0002-3691-7238","observed_orcids":["https://orcid.org/0000-0002-3691-7238"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pai, Sreepathi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0,"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/compare-and-swap","display_name":"compare-and-swap","score":1.0},{"id":"https://openalex.org/keywords/analytical-performance-model","display_name":"analytical performance model","score":0.7440000176429749},{"id":"https://openalex.org/keywords/performance-profiling","display_name":"performance profiling","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.901199996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C194778546","wikidata":"https://www.wikidata.org/wiki/Q15308119","display_name":"Atomic model","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2503.17893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17893","pdf_url":"https://arxiv.org/pdf/2503.17893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.17893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17893","pdf_url":"https://arxiv.org/pdf/2503.17893","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Performance":[0],"analysis":[1],"is":[2,25,69],"critical":[3],"for":[4,18,35,63,135],"GPU":[5],"programs":[6],"with":[7],"data-dependent":[8],"behavior,":[9],"but":[10],"models":[11],"like":[12],"Roofline":[13],"are":[14,60,82],"not":[15],"very":[16],"useful":[17],"them":[19],"and":[20,40,46,93],"interpreting":[21],"raw":[22],"performance":[23,83,156],"counters":[24,108],"tedious.":[26],"In":[27],"this":[28,99,133,179],"work,":[29],"we":[30],"present":[31],"an":[32],"analytical":[33],"model":[34,68,79,100,131,142],"shared":[36,56],"memory":[37,57],"atomics":[38],"(\\emph{fetch-and-op}":[39],"\\emph{compare-and-swap}":[41],"instructions":[42],"on":[43,71],"NVIDIA":[44],"Volta":[45],"Ampere":[47],"GPU)":[48],"that":[49,104,148],"allows":[50],"users":[51],"to":[52,111,143,162],"immediately":[53],"determine":[54],"if":[55],"atomic":[58,118,137,173],"operations":[59],"a":[61,64,76,102,168],"bottleneck":[62,169],"program's":[65],"execution.":[66],"Our":[67,164],"based":[70],"modeling":[72],"the":[73,113,116,121,141,176],"architecture":[74],"as":[75,90,109,175],"single-server":[77],"queuing":[78],"whose":[80],"inputs":[81],"counters.":[84],"It":[85],"captures":[86],"load-dependent":[87],"behavior":[88],"such":[89],"pipelining,":[91],"parallelism,":[92],"different":[94,159],"access":[95],"patterns.":[96],"We":[97,139],"embody":[98],"in":[101],"tool":[103,129,165],"uses":[105],"CUDA":[106],"hardware":[107],"parameters":[110],"predict":[112],"utilization":[114],"of":[115,123,178],"shared-memory":[117,136,150,172],"unit.":[119],"To":[120],"best":[122],"our":[124],"knowledge,":[125],"no":[126],"existing":[127],"profiling":[128],"or":[130],"provides":[132],"capability":[134],"operations.":[138],"used":[140],"compare":[144],"two":[145],"histogram":[146],"kernels":[147],"use":[149],"atomics.":[151],"Although":[152],"nearly":[153],"identical,":[154],"their":[155],"can":[157],"be":[158],"by":[160],"up":[161],"30\\%.":[163],"correctly":[166],"identifies":[167],"shift":[170],"from":[171],"unit":[174],"cause":[177],"discrepancy.":[180]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}