{"id":"https://openalex.org/W2892817096","doi":"https://doi.org/10.1145/3243905","title":"Software-Directed Techniques for Improved GPU Register File Utilization","display_name":"Software-Directed Techniques for Improved GPU Register File Utilization","publication_year":2018,"publication_date":"2018-09-24","ids":{"openalex":"https://openalex.org/W2892817096","doi":"https://doi.org/10.1145/3243905","mag":"2892817096"},"language":"en","primary_location":{"id":"doi:10.1145/3243905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243905","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-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/A5079954440","display_name":"Dani Voitsechov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dani Voitsechov","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065112065","display_name":"Arslan Zulfiqar","orcid":"https://orcid.org/0009-0003-6240-5900"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arslan Zulfiqar","raw_affiliation_strings":["NVIDIA, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015391591","display_name":"Mark W. Stephenson","orcid":"https://orcid.org/0000-0002-1350-0165"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Stephenson","raw_affiliation_strings":["NVIDIA, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003674142","display_name":"Mark Gebhart","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Gebhart","raw_affiliation_strings":["NVIDIA, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112796474","display_name":"Stephen W. Keckler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6338-4297","affiliations":[{"raw_affiliation_string":"NVIDIA, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1877,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79880018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.996999979019165,"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/register-file","display_name":"Register file","score":0.9027652740478516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8883033394813538},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.6983760595321655},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.661719024181366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5962191820144653},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5303968191146851},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.508604884147644},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.486438512802124},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4295784831047058},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32332563400268555},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.314893901348114},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.10332134366035461}],"concepts":[{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.9027652740478516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8883033394813538},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.6983760595321655},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.661719024181366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5962191820144653},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5303968191146851},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.508604884147644},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.486438512802124},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4295784831047058},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32332563400268555},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.314893901348114},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.10332134366035461},{"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/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3243905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243905","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1490482062","https://openalex.org/W1516536978","https://openalex.org/W1667652561","https://openalex.org/W1965864973","https://openalex.org/W1968775993","https://openalex.org/W1991518265","https://openalex.org/W1997162567","https://openalex.org/W2022632182","https://openalex.org/W2026186397","https://openalex.org/W2079735306","https://openalex.org/W2080592089","https://openalex.org/W2084110734","https://openalex.org/W2088440019","https://openalex.org/W2089854225","https://openalex.org/W2091599698","https://openalex.org/W2096661534","https://openalex.org/W2098290747","https://openalex.org/W2103078980","https://openalex.org/W2111948219","https://openalex.org/W2114067856","https://openalex.org/W2115157620","https://openalex.org/W2117877698","https://openalex.org/W2128252715","https://openalex.org/W2143798346","https://openalex.org/W2145462867","https://openalex.org/W2147098645","https://openalex.org/W2147692971","https://openalex.org/W2155503253","https://openalex.org/W2159254447","https://openalex.org/W2164474450","https://openalex.org/W2166908913","https://openalex.org/W2238992335","https://openalex.org/W2273440736","https://openalex.org/W2322230929","https://openalex.org/W2563249257","https://openalex.org/W2564688911","https://openalex.org/W2618530766","https://openalex.org/W2952230511","https://openalex.org/W4245044310"],"related_works":["https://openalex.org/W2224192221","https://openalex.org/W1967889241","https://openalex.org/W2111377238","https://openalex.org/W2161297616","https://openalex.org/W3117494601","https://openalex.org/W2159389028","https://openalex.org/W2195435904","https://openalex.org/W2148662141","https://openalex.org/W3022691489","https://openalex.org/W2130747473"],"abstract_inverted_index":{"Throughput":[0],"architectures":[1],"such":[2],"as":[3,106],"GPUs":[4],"require":[5],"substantial":[6],"hardware":[7],"resources":[8,93,101],"to":[9,56,64,115,149,201,212],"hold":[10],"the":[11,66,82,112,145,183],"state":[12],"of":[13,17,30,41,72,81,111,139,144,165,185,224],"a":[14,52,129,140,166,221],"massive":[15],"number":[16],"simultaneously":[18],"executing":[19],"threads.":[20,60],"While":[21],"GPU":[22,262],"register":[23,54,84,92,100,141,152,231,238,255],"files":[24],"are":[25,46],"already":[26,259],"enormous,":[27],"reaching":[28],"capacities":[29],"256KB":[31],"per":[32],"streaming":[33],"multiprocessor":[34],"(SM),":[35],"we":[36,44],"find":[37],"that":[38,98,133,194,227],"nearly":[39],"half":[40],"real-world":[42],"applications":[43,75,225,257],"examined":[45],"register-bound":[47,74],"and":[48,69,118,135,161,192,240],"would":[49],"benefit":[50],"from":[51],"larger":[53],"file":[55,85],"enable":[57],"more":[58,78],"concurrent":[59],"This":[61],"article":[62,127,181],"seeks":[63],"increase":[65],"thread":[67,174,190,252],"occupancy":[68,175,191],"improve":[70],"performance":[71,117,248],"these":[73,124,186,242],"by":[76],"making":[77],"efficient":[79],"use":[80,138],"existing":[83],"capacity.":[86],"Our":[87,180],"first":[88],"technique":[89,232],"eagerly":[90,150],"deallocates":[91],"during":[94],"execution.":[95],"We":[96],"show":[97],"releasing":[99],"based":[102],"on":[103,173,220,236,244,254],"value":[104,146],"liveness":[105],"proposed":[107],"in":[108,188],"prior":[109],"states":[110],"art":[113],"leads":[114],"unreliable":[116],"undue":[119],"design":[120],"complexity.":[121],"To":[122],"address":[123],"deficiencies,":[125],"our":[126,229],"presents":[128],"novel":[130],"compiler-driven":[131],"approach":[132,198],"identifies":[134],"exploits":[136],"last":[137],"name":[142],"(instead":[143],"contained":[147],"within)":[148],"release":[151],"resources.":[153,263],"Furthermore,":[154],"while":[155,195],"previous":[156,234],"works":[157],"have":[158],"leveraged":[159],"\u201cscalar\u201d":[160],"\u201cnarrow\u201d":[162],"operand":[163],"properties":[164],"program":[167],"for":[168],"various":[169],"optimizations,":[170],"their":[171],"impact":[172],"has":[176],"been":[177],"relatively":[178],"unexplored.":[179],"evaluates":[182],"effectiveness":[184],"techniques":[187],"improving":[189],"demonstrates":[193],"any":[196],"one":[197],"may":[199],"fail":[200],"free":[202,209],"very":[203],"many":[204],"registers,":[205],"together":[206,241],"they":[207],"synergistically":[208],"enough":[210],"registers":[211],"launch":[213],"additional":[214],"parallel":[215],"work.":[216],"An":[217],"in-depth":[218],"evaluation":[219],"large":[222],"suite":[223],"shows":[226],"just":[228],"early":[230],"outperforms":[233],"work":[235],"dynamic":[237],"allocation,":[239],"approaches,":[243],"average,":[245],"provide":[246],"12%":[247],"speedup":[249],"(23%":[250],"higher":[251],"occupancy)":[253],"bound":[256],"not":[258],"saturating":[260],"other":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
