{"id":"https://openalex.org/W2619500264","doi":"https://doi.org/10.1145/3079079.3079083","title":"A performance analysis framework for exploiting GPU microarchitectural capability","display_name":"A performance analysis framework for exploiting GPU microarchitectural capability","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2619500264","doi":"https://doi.org/10.1145/3079079.3079083","mag":"2619500264"},"language":"en","primary_location":{"id":"doi:10.1145/3079079.3079083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079079.3079083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063326523","display_name":"Keren Zhou","orcid":"https://orcid.org/0000-0002-7977-3182"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keren Zhou","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104072170","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771802","display_name":"Xiuxia Zhang","orcid":"https://orcid.org/0000-0002-2666-1128"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuxia Zhang","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101864381","display_name":"Chaowei Wang","orcid":"https://orcid.org/0000-0001-7784-2685"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaowei Wang","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738014","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-4179-2660"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":1.0348,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.882879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9178228378295898},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7382411956787109},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6803798079490662},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5867332816123962},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49424007534980774},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.47926566004753113},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.47042250633239746},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4258122742176056},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42263147234916687},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4216848611831665},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.42158764600753784},{"id":"https://openalex.org/keywords/assembly-language","display_name":"Assembly language","score":0.4160165786743164},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4136536419391632},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4101673662662506},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4095756709575653},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.388374924659729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22727885842323303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20731481909751892},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19465425610542297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1755005419254303},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.16721788048744202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9178228378295898},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7382411956787109},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6803798079490662},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5867332816123962},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49424007534980774},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.47926566004753113},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.47042250633239746},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4258122742176056},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42263147234916687},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4216848611831665},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.42158764600753784},{"id":"https://openalex.org/C50831359","wikidata":"https://www.wikidata.org/wiki/Q165436","display_name":"Assembly language","level":3,"score":0.4160165786743164},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4136536419391632},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4101673662662506},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4095756709575653},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.388374924659729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22727885842323303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20731481909751892},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19465425610542297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1755005419254303},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.16721788048744202},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3079079.3079083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079079.3079083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1598866093","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1884620995","https://openalex.org/W1979740015","https://openalex.org/W2009832130","https://openalex.org/W2093843662","https://openalex.org/W2128539477","https://openalex.org/W2130336316","https://openalex.org/W2142769604","https://openalex.org/W2152175008","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2162390675","https://openalex.org/W2167334577","https://openalex.org/W2172654076","https://openalex.org/W2277932597","https://openalex.org/W2510697685","https://openalex.org/W2521727659","https://openalex.org/W2580538010","https://openalex.org/W2618530766","https://openalex.org/W2963542991","https://openalex.org/W2997701623","https://openalex.org/W3004171485","https://openalex.org/W3005101099","https://openalex.org/W3012526378","https://openalex.org/W4212788319","https://openalex.org/W4243261006","https://openalex.org/W4245145882"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W4382323155","https://openalex.org/W4315697128","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463","https://openalex.org/W1977763331"],"abstract_inverted_index":{"GPUs":[0],"are":[1],"widely":[2],"used":[3],"in":[4,189],"accelerating":[5],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"for":[10],"their":[11],"high":[12],"bandwidth":[13],"and":[14,35,84,94,115,127,144,164],"parallelism.":[15],"But":[16],"tuning":[17],"the":[18,71,116,124,134,152,173],"performance":[19,44,67,109,181],"of":[20,31,123,136,172,175],"DNN":[21],"computations":[22],"is":[23,159],"challenging,":[24],"as":[25,87,185,187],"it":[26],"requires":[27],"a":[28,66,97,101,108],"thorough":[29],"understanding":[30],"both":[32],"underlying":[33],"architectures":[34],"algorithm":[36],"implementations.":[37],"Traditional":[38],"research,":[39],"which":[40],"focused":[41],"on":[42],"analyzing":[43],"by":[45,139,169],"CUDA":[46],"C":[47],"language":[48],"or":[49],"PTX":[50],"instructions,":[51,177],"has":[52],"not":[53],"combined":[54],"hardware":[55,85],"features":[56,86],"tightly":[57],"with":[58,182],"source":[59,80,125],"code.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,178],"present":[65],"analysis":[68],"framework":[69,138],"at":[70],"assembly":[72,79,176],"level.":[73],"First,":[74],"an":[75,183],"instruction":[76,105],"parser":[77],"takes":[78],"code,":[81],"benchmark":[82],"results,":[83],"input":[88],"to":[89,119,149],"identify":[90],"each":[91],"instruction's":[92],"efficiency":[93],"latency.":[95],"Then,":[96],"DAG":[98,102,118],"constructor":[99],"builds":[100],"that":[103,156],"models":[104],"executions.":[106],"Finally,":[107],"advisor":[110],"incorporates":[111],"block":[112],"partitions,":[113],"occupancy,":[114],"generated":[117],"predict":[120,180],"running":[121],"cycles":[122],"code":[126],"presents":[128],"its":[129],"potential":[130],"bottlenecks.":[131],"We":[132],"demonstrate":[133],"effectiveness":[135],"our":[137,157,165],"optimizing":[140],"DNNs'":[141],"performance-critical":[142],"kernels-GEMM":[143],"convolution.":[145],"After":[146],"taking":[147],"steps":[148],"reduce":[150],"bottlenecks,":[151],"experimental":[153],"results":[154],"show":[155],"GEMM":[158],"20%":[160],"faster":[161],"than":[162],"cuBLAS,":[163],"convolution":[166],"outperforms":[167],"cuDNN":[168],"40%--60%.":[170],"Because":[171],"usage":[174],"can":[179],"error":[184],"low":[186],"2%":[188],"average.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}