{"id":"https://openalex.org/W7123335497","doi":"https://doi.org/10.1109/candarw68385.2025.00027","title":"Performance Estimation Using Both Source and Assembly Code for Data Layout Optimization on GPU","display_name":"Performance Estimation Using Both Source and Assembly Code for Data Layout Optimization on GPU","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7123335497","doi":"https://doi.org/10.1109/candarw68385.2025.00027"},"language":null,"primary_location":{"id":"doi:10.1109/candarw68385.2025.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/candarw68385.2025.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Thirteenth International Symposium on Computing and Networking Workshops (CANDARW)","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/A5023903901","display_name":"S. Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I178574317","display_name":"Mie University","ror":"https://ror.org/01529vy56","country_code":"JP","type":"education","lineage":["https://openalex.org/I178574317"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shintaro Yamamoto","raw_affiliation_strings":["Mie University,Mie,Japan"],"affiliations":[{"raw_affiliation_string":"Mie University,Mie,Japan","institution_ids":["https://openalex.org/I178574317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122874078","display_name":"Kazuhiko Ohno","orcid":null},"institutions":[{"id":"https://openalex.org/I178574317","display_name":"Mie University","ror":"https://ror.org/01529vy56","country_code":"JP","type":"education","lineage":["https://openalex.org/I178574317"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiko Ohno","raw_affiliation_strings":["Mie University,Mie,Japan"],"affiliations":[{"raw_affiliation_string":"Mie University,Mie,Japan","institution_ids":["https://openalex.org/I178574317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023903901"],"corresponding_institution_ids":["https://openalex.org/I178574317"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73934303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9491999745368958,"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":0.9491999745368958,"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/T14347","display_name":"Big Data and Digital Economy","score":0.015699999406933784,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.009100000374019146,"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/cuda","display_name":"CUDA","score":0.6577000021934509},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5501000285148621},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5472000241279602},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4970000088214874},{"id":"https://openalex.org/keywords/data-flow-analysis","display_name":"Data-flow analysis","score":0.4796999990940094},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.447299987077713},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.40720000863075256},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8783000111579895},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6930999755859375},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6577000021934509},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.4796999990940094},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C50831359","wikidata":"https://www.wikidata.org/wiki/Q165436","display_name":"Assembly language","level":3,"score":0.3443000018596649},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C27458966","wikidata":"https://www.wikidata.org/wiki/Q1187693","display_name":"Control flow graph","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/candarw68385.2025.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/candarw68385.2025.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Thirteenth International Symposium on Computing and Networking Workshops (CANDARW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,73],"recent":[1],"years,":[2],"GPUs":[3,22],"are":[4,29],"widely":[5],"used":[6],"as":[7,16,181],"highperformance":[8],"computing":[9,13,18,25],"platforms":[10],"in":[11,38],"various":[12],"domains":[14],"such":[15,45,180],"scientific":[17],"and":[19,143,204],"AI.":[20],"Although":[21],"have":[23],"high":[24],"power,":[26],"architecture-aware":[27],"optimizations":[28,46],"needed":[30],"to":[31,131,195],"exploit":[32],"the":[33,39,51,58,95,105,116,128,133,155,159,162,167,188,197],"performance.":[34,60],"Optimizing":[35],"data":[36,101,107,199],"layout":[37,102,108,200],"GPU":[40,59,63,83],"memory":[41,52,145],"is":[42,71,125],"crucial":[43],"among":[44],"because":[47],"it":[48,153],"directly":[49],"affects":[50],"access":[53,146],"efficiency":[54],"which":[55,124],"often":[56],"dominates":[57],"However,":[61],"current":[62],"programming":[64],"requires":[65],"low-level":[66],"hand-optimizations":[67],"thus":[68],"automatic":[69],"optimization":[70],"desired.":[72],"this":[74],"paper,":[75],"we":[76],"propose":[77],"a":[78,99,139,170],"performance":[79],"estimation":[80,189],"method":[81,112,137,192],"of":[82,94,158,166,172,190],"programs":[84],"based":[85],"on":[86],"static":[87],"code":[88,119],"analysis.":[89],"Estimating":[90],"each":[91],"execution":[92,156],"time":[93,157],"target":[96],"program":[97,160],"with":[98],"different":[100],"enables":[103],"selecting":[104],"optimal":[106,198],"automatically.":[109],"The":[110,136],"proposed":[111],"analyzes":[113],"not":[114],"only":[115],"CUDA":[117],"source":[118,129],"but":[120],"also":[121],"PTX":[122],"code,":[123,130],"compiled":[126],"from":[127,148,184,201],"obtain":[132],"executed":[134],"instructions.":[135],"constructs":[138],"control":[140],"flow":[141],"graph":[142],"extracts":[144],"patterns":[147],"array":[149],"index":[150],"expressions.":[151],"Then":[152],"estimates":[154],"using":[161,175],"instruction":[163],"latency":[164],"model":[165],"GPU.":[168],"As":[169],"result":[171],"an":[173],"evaluation":[174],"4":[176],"typical":[177],"computation":[178],"kernels":[179],"matrix":[182],"multiplication":[183],"PolyBench":[185],"benchmark":[186],"suite,":[187],"our":[191],"was":[193],"enough":[194],"select":[196],"AoS,":[202],"SoA":[203],"ASTA.":[205]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}