{"id":"https://openalex.org/W2024321119","doi":"https://doi.org/10.1145/2667522.2667530","title":"Microarchitectural characterization of irregular applications on GPGPUs","display_name":"Microarchitectural characterization of irregular applications on GPGPUs","publication_year":2014,"publication_date":"2014-09-04","ids":{"openalex":"https://openalex.org/W2024321119","doi":"https://doi.org/10.1145/2667522.2667530","mag":"2024321119"},"language":"en","primary_location":{"id":"doi:10.1145/2667522.2667530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2667522.2667530","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"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 SIGMETRICS Performance Evaluation Review","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/A5076310461","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-8440-9924"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China","[Shanghai Jiao Tong University, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085400565","display_name":"Guangshuo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangshuo Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, China","[Shanghai Jiao Tong University, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101606865","display_name":"Wei Shu","orcid":"https://orcid.org/0000-0002-9853-3037"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Shu","raw_affiliation_strings":["University of New Mexico, NM","University of New Mexico, NM,"],"affiliations":[{"raw_affiliation_string":"University of New Mexico, NM","institution_ids":["https://openalex.org/I169521973"]},{"raw_affiliation_string":"University of New Mexico, NM,","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102938931","display_name":"Min\u2010You Wu","orcid":"https://orcid.org/0000-0001-6221-5558"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min-You Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, China","[Shanghai Jiao Tong University, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, China]","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076310461"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.9451,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75398517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"42","issue":"2","first_page":"27","last_page":"29"},"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":0.9998000264167786,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8742033243179321},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7877577543258667},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6262788772583008},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6157789826393127},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5883612036705017},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5217086672782898},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5167321562767029},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.47425782680511475},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47195544838905334},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44855743646621704},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3389531075954437},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19433867931365967},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18495246767997742},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.14397752285003662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8742033243179321},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7877577543258667},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6262788772583008},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6157789826393127},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5883612036705017},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5217086672782898},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5167321562767029},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.47425782680511475},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47195544838905334},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44855743646621704},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3389531075954437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19433867931365967},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18495246767997742},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.14397752285003662},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2667522.2667530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2667522.2667530","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"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 SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.716.4335","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.4335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wirelesslab.sjtu.edu.cn/resource/publication/Conference/TaoZhang_ACM%20SIGMETRICS2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1463737727","https://openalex.org/W1979527452","https://openalex.org/W1997162567"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"GPGPUs":[3,54],"have":[4],"experienced":[5],"tremendous":[6],"growth":[7],"as":[8],"general-purpose":[9],"and":[10,33,41,84,98,100,114],"high-throughput":[11],"computing":[12],"devices.":[13],"However,":[14],"irregular":[15,30,47,72,116],"applications":[16,48,73,117],"cannot":[17],"fully":[18],"utilize":[19],"the":[20,43,63,86,91,102],"hardware":[21,64],"resource":[22],"because":[23],"of":[24,27,38,62,70,93],"their":[25,81],"plenty":[26],"control-flow":[28],"divergences,":[29],"memory":[31],"accesses":[32],"load":[34],"imbalances.":[35],"The":[36],"lack":[37],"in-depth":[39],"characterization":[40],"quantifying":[42],"ways":[44],"in":[45,95,112],"which":[46],"differ":[49],"from":[50,58],"regular":[51],"ones":[52],"on":[53,74,118],"has":[55],"prevented":[56],"users":[57],"effectively":[59],"making":[60],"use":[61],"resource.":[65],"We":[66,79,88],"examine":[67],"a":[68,75],"suite":[69],"representative":[71],"cycle-accurate":[76],"GPU":[77,105],"simulator.":[78],"characterize":[80],"performance":[82],"aspects":[83],"analyze":[85],"bottlenecks.":[87],"also":[89],"assess":[90],"impact":[92],"changes":[94],"cache,":[96],"DRAM":[97],"interconnect":[99],"discuss":[101],"implications":[103],"for":[104],"architecture":[106],"design.":[107],"This":[108],"work":[109],"is":[110],"useful":[111],"understanding":[113],"optimizing":[115],"GPUs.":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
