{"id":"https://openalex.org/W2791628046","doi":"https://doi.org/10.1109/igcc.2017.8323599","title":"Mitigating register pressure in GPU kernels for improved energy efficiency","display_name":"Mitigating register pressure in GPU kernels for improved energy efficiency","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2791628046","doi":"https://doi.org/10.1109/igcc.2017.8323599","mag":"2791628046"},"language":"en","primary_location":{"id":"doi:10.1109/igcc.2017.8323599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2017.8323599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","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/A5112322145","display_name":"Apan Qasem","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apan Qasem","raw_affiliation_strings":["Computer Science Dept., Texas State University, San Marcos, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Texas State University, San Marcos, TX","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072034690","display_name":"Samuel Teich","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Teich","raw_affiliation_strings":["Computer Science Dept., Texas State University, San Marcos, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Texas State University, San Marcos, TX","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2312,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56287425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8342477679252625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8272929191589355},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6756329536437988},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.672694206237793},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6153275966644287},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.6037837862968445},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5955030918121338},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5501117706298828},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5233960747718811},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46039456129074097},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.4337036609649658},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4144125282764435},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.4109501838684082},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.27902084589004517},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25116491317749023},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.097409188747406}],"concepts":[{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8342477679252625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272929191589355},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6756329536437988},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.672694206237793},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6153275966644287},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.6037837862968445},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5955030918121338},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5501117706298828},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5233960747718811},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46039456129074097},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.4337036609649658},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4144125282764435},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.4109501838684082},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.27902084589004517},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25116491317749023},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.097409188747406},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igcc.2017.8323599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igcc.2017.8323599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Eighth International Green and Sustainable Computing Conference (IGSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1894701209","https://openalex.org/W1980489165","https://openalex.org/W1991518265","https://openalex.org/W2130967222","https://openalex.org/W2238992335","https://openalex.org/W2292282166","https://openalex.org/W2533256678","https://openalex.org/W2538356068","https://openalex.org/W2575503711","https://openalex.org/W2593812512","https://openalex.org/W2612048219","https://openalex.org/W2752953089","https://openalex.org/W3100760381","https://openalex.org/W4250602606"],"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/W4247209662","https://openalex.org/W2195435904","https://openalex.org/W2148662141","https://openalex.org/W2159389028","https://openalex.org/W3022691489"],"abstract_inverted_index":{"GPUs":[0,25],"have":[1],"become":[2],"an":[3,110],"integral":[4],"part":[5],"of":[6,24,39,50,62,144],"modern":[7],"HPC":[8,12],"systems.":[9],"As":[10],"the":[11,22,47,51,63],"landscape":[13],"moves":[14],"toward":[15],"over-provisioned":[16],"systems":[17],"with":[18],"heterogeneous":[19],"compute":[20],"nodes,":[21],"importance":[23],"is":[26,124],"likely":[27],"to":[28,126],"grow.":[29],"Therefore,":[30],"strategies":[31],"for":[32,84,101,112],"energy":[33,48,139],"savings":[34],"on":[35,54],"these":[36],"devices":[37],"are":[38],"critical":[40],"importance.":[41],"In":[42],"this":[43,77],"paper,":[44],"we":[45,79],"examine":[46],"efficiency":[49,140],"register":[52,64,86,103,130],"file":[53,65,131],"current":[55],"GPUs.":[56],"We":[57],"show":[58,120],"that":[59,121],"ineffective":[60],"utilization":[61],"not":[66],"only":[67],"degrades":[68],"performance":[69,137],"but":[70],"also":[71],"increases":[72],"power":[73],"consumption.":[74],"To":[75],"address":[76],"problem,":[78],"develop":[80],"a":[81,94,99,142],"multi-level":[82],"approach":[83],"mitigating":[85],"pressure":[87,104],"in":[88,129,141],"GPU":[89,145],"kernels.":[90,146],"Our":[91],"strategy":[92,123],"includes":[93],"source-to-source":[95],"data":[96],"layout":[97],"transformation,":[98],"method":[100],"modulating":[102],"(RP)":[105],"via":[106],"compiler":[107],"optimizations,":[108],"and":[109,133,138],"autotuner":[111],"selecting":[113],"RP-sensitive":[114],"kernel":[115],"launch":[116],"configurations.":[117],"Experimental":[118],"results":[119],"our":[122],"able":[125],"curb":[127],"inefficiency":[128],"usage":[132],"can":[134],"significantly":[135],"boost":[136],"range":[143]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
