{"id":"https://openalex.org/W4416199183","doi":"https://doi.org/10.1145/3712285.3759797","title":"C.A.T.S.: Memory and Control Flow Tracing for Whole-Program Performance Analysis","display_name":"C.A.T.S.: Memory and Control Flow Tracing for Whole-Program Performance Analysis","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199183","doi":"https://doi.org/10.1145/3712285.3759797"},"language":"en","primary_location":{"id":"doi:10.1145/3712285.3759797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009037320","display_name":"Philipp Schaad","orcid":"https://orcid.org/0000-0002-8429-7803"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Philipp Schaad","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002615744","display_name":"Tal Ben\u2010Nun","orcid":"https://orcid.org/0000-0002-3657-6568"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tal Ben-Nun","raw_affiliation_strings":["Lawrence Livermore National Laboratory (LLNL), Livermore, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory (LLNL), Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009037320"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.1983,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90049597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8841000199317932,"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":0.8841000199317932,"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/T10126","display_name":"Logic, programming, and type systems","score":0.030400000512599945,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.014299999922513962,"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/tracing","display_name":"Tracing","score":0.7443000078201294},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6618000268936157},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4943999946117401},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4796999990940094},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42899999022483826},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.4278999865055084},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41659998893737793},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3779999911785126},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3736000061035156},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3677999973297119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955999970436096},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.7443000078201294},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6618000268936157},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42899999022483826},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3474000096321106},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C156731835","wikidata":"https://www.wikidata.org/wiki/Q751740","display_name":"Memory leak","level":4,"score":0.3255999982357025},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C40866790","wikidata":"https://www.wikidata.org/wiki/Q956238","display_name":"Interactive computing","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C176359209","wikidata":"https://www.wikidata.org/wiki/Q2348963","display_name":"Control flow analysis","level":5,"score":0.27059999108314514},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C34339311","wikidata":"https://www.wikidata.org/wiki/Q1050390","display_name":"C dynamic memory allocation","level":4,"score":0.2669999897480011},{"id":"https://openalex.org/C121483023","wikidata":"https://www.wikidata.org/wiki/Q7298343","display_name":"Ray tracing (physics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2778994249","wikidata":"https://www.wikidata.org/wiki/Q2842324","display_name":"TRAC","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3712285.3759797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:doi:10.3929/ethz-c-000789874","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/789874","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759797","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759797","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2917824471","display_name":null,"funder_award_id":"DE-AC52-07NA2734","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5535250666","display_name":null,"funder_award_id":"101002047","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G5552550678","display_name":null,"funder_award_id":"LDRD 23-ERD-022","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1710734607","https://openalex.org/W1965100924","https://openalex.org/W1975269725","https://openalex.org/W1977857603","https://openalex.org/W1980282429","https://openalex.org/W2020214444","https://openalex.org/W2032391783","https://openalex.org/W2033486618","https://openalex.org/W2034761517","https://openalex.org/W2039128955","https://openalex.org/W2043064226","https://openalex.org/W2053885966","https://openalex.org/W2057387256","https://openalex.org/W2063364927","https://openalex.org/W2069422636","https://openalex.org/W2080046548","https://openalex.org/W2085765820","https://openalex.org/W2097699872","https://openalex.org/W2101778912","https://openalex.org/W2109222446","https://openalex.org/W2117562822","https://openalex.org/W2126658609","https://openalex.org/W2132431120","https://openalex.org/W2135708569","https://openalex.org/W2136434791","https://openalex.org/W2139471541","https://openalex.org/W2156858199","https://openalex.org/W2162831261","https://openalex.org/W2164705534","https://openalex.org/W2168161957","https://openalex.org/W2173174116","https://openalex.org/W2521708680","https://openalex.org/W2592263880","https://openalex.org/W2613618711","https://openalex.org/W2667607215","https://openalex.org/W2752493087","https://openalex.org/W2783728688","https://openalex.org/W2790911601","https://openalex.org/W2806355294","https://openalex.org/W2900882971","https://openalex.org/W2905253547","https://openalex.org/W2941905822","https://openalex.org/W2963723316","https://openalex.org/W2983323473","https://openalex.org/W2987684178","https://openalex.org/W3012303953","https://openalex.org/W3035965352","https://openalex.org/W3040626038","https://openalex.org/W3043619075","https://openalex.org/W3095199886","https://openalex.org/W3108779324","https://openalex.org/W3213073403","https://openalex.org/W4205520759","https://openalex.org/W4220912491","https://openalex.org/W4233184216","https://openalex.org/W4238138329","https://openalex.org/W4241057782","https://openalex.org/W4245072421","https://openalex.org/W4246569695","https://openalex.org/W4248806677","https://openalex.org/W4249809486","https://openalex.org/W4250054289","https://openalex.org/W4250730856","https://openalex.org/W4252521241","https://openalex.org/W4255861413","https://openalex.org/W4256386389","https://openalex.org/W4256483581","https://openalex.org/W4309620166","https://openalex.org/W4321636944","https://openalex.org/W4366714486","https://openalex.org/W4384009863","https://openalex.org/W4391952904","https://openalex.org/W4407857939"],"related_works":[],"abstract_inverted_index":{"Performance":[0],"engineering":[1],"often":[2],"involves":[3],"localized,":[4],"bottleneck-based":[5],"optimization,":[6,23],"supported":[7],"by":[8,47],"a":[9,36,54],"plethora":[10],"of":[11,25,70,74],"tools.":[12],"When":[13],"no":[14],"apparent":[15],"bottlenecks":[16],"exist,":[17],"engineers":[18],"resort":[19],"to":[20,34,43,88,109],"coarser":[21],"whole-program":[22,45],"consisting":[24],"data":[26,149],"layout,":[27],"sparsity,":[28],"allocation":[29],"strategy,":[30],"and":[31,67,77,85,93,101,104,114,122,133,148],"algorithmic":[32],"modifications,":[33],"name":[35],"few.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"aim":[42],"codify":[44],"optimization":[46],"providing":[48],"three":[49],"global":[50],"views":[51],"based":[52],"on":[53,117,126],"single":[55],"tracing":[56],"format.":[57],"The":[58,120],"format,":[59],"called":[60],"C.A.T.S.,":[61],"captures":[62],"information":[63],"necessary":[64],"for":[65],"static":[66],"runtime":[68],"analysis":[69,107],"large":[71],"applications.":[72],"Instead":[73],"call":[75],"stacks":[76,84],"function":[78],"annotations,":[79],"C.A.T.S.":[80,111],"uses":[81],"control":[82],"flow":[83],"memory":[86,139],"events":[87],"identify":[89],"common":[90],"performance":[91],"anti-patterns":[92],"potential":[94],"optimizations.":[95],"We":[96],"develop":[97],"interactive":[98],"timeline,":[99],"dataflow,":[100],"access":[102],"visualizations,":[103],"implement":[105],"compiler":[106],"passes":[108],"extract":[110],"traces":[112],"statically":[113],"in":[115,143],"seconds":[116],"consumer":[118],"hardware.":[119],"visualizations":[121],"analyses":[123],"are":[124],"demonstrated":[125],"case":[127],"studies":[128],"including":[129],"sparse":[130],"computations,":[131],"hydrodynamics":[132],"climate":[134],"modeling,":[135],"yielding":[136],"3":[137],"\u00d7":[138],"footprint":[140],"reduction,":[141],"improvements":[142],"communication-computation":[144],"overlap,":[145],"code":[146],"fusion,":[147],"layouts.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}
