{"id":"https://openalex.org/W3210604792","doi":"https://doi.org/10.1145/3458817.3476221","title":"Hybrid, scalable, trace-driven performance modeling of GPGPUs","display_name":"Hybrid, scalable, trace-driven performance modeling of GPGPUs","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3210604792","doi":"https://doi.org/10.1145/3458817.3476221","mag":"3210604792"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476221","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476221","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 for High Performance Computing, Networking, Storage and Analysis","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/A5001017727","display_name":"Yehia Arafa","orcid":"https://orcid.org/0000-0002-5186-3012"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yehia Arafa","raw_affiliation_strings":["New Mexico State University"],"affiliations":[{"raw_affiliation_string":"New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed Badawy","raw_affiliation_strings":["New Mexico State University"],"affiliations":[{"raw_affiliation_string":"New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016538589","display_name":"Ammar ElWazir","orcid":null},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ammar ElWazir","raw_affiliation_strings":["New Mexico State University"],"affiliations":[{"raw_affiliation_string":"New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074965377","display_name":"Atanu Barai","orcid":"https://orcid.org/0000-0002-6879-4455"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanu Barai","raw_affiliation_strings":["New Mexico State University"],"affiliations":[{"raw_affiliation_string":"New Mexico State University","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023816112","display_name":"Ali Eker","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Eker","raw_affiliation_strings":["Binghamton University"],"affiliations":[{"raw_affiliation_string":"Binghamton University","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopinath Chennupati","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809539","display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Los Alamos National Laboratory"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073911119","display_name":"Stephan Eidenbenz","orcid":"https://orcid.org/0000-0002-2628-1854"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Eidenbenz","raw_affiliation_strings":["Los Alamos National Laboratory"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5001017727"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":4.3754,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95140423,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8996134400367737},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8730708360671997},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.744306206703186},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7092224955558777},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5840179324150085},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5626059770584106},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5023715496063232},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4861021041870117},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.48356911540031433},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3204459249973297},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13087090849876404},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12848728895187378},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.0949946939945221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8996134400367737},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8730708360671997},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.744306206703186},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7092224955558777},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5840179324150085},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5626059770584106},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5023715496063232},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4861021041870117},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.48356911540031433},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3204459249973297},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13087090849876404},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12848728895187378},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0949946939945221},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458817.3476221","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476221","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 for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1529391588","https://openalex.org/W1587142039","https://openalex.org/W1902930330","https://openalex.org/W1979527452","https://openalex.org/W2002555321","https://openalex.org/W2020035025","https://openalex.org/W2029891792","https://openalex.org/W2033486618","https://openalex.org/W2038666141","https://openalex.org/W2047060659","https://openalex.org/W2080592089","https://openalex.org/W2091250014","https://openalex.org/W2098290747","https://openalex.org/W2113282196","https://openalex.org/W2128120785","https://openalex.org/W2130336316","https://openalex.org/W2144264070","https://openalex.org/W2164705534","https://openalex.org/W2167334577","https://openalex.org/W2169828639","https://openalex.org/W2607112060","https://openalex.org/W2774906412","https://openalex.org/W2789572737","https://openalex.org/W2803466590","https://openalex.org/W2897830517","https://openalex.org/W2903738101","https://openalex.org/W2913407901","https://openalex.org/W2921788688","https://openalex.org/W2930604630","https://openalex.org/W2937249639","https://openalex.org/W2979340153","https://openalex.org/W2984189761","https://openalex.org/W2991330024","https://openalex.org/W2998901775","https://openalex.org/W3015498000","https://openalex.org/W3039972296","https://openalex.org/W3043184036","https://openalex.org/W3098742859","https://openalex.org/W3102510044","https://openalex.org/W3104094521","https://openalex.org/W3115175310","https://openalex.org/W3154492603","https://openalex.org/W3176967743","https://openalex.org/W4232955467","https://openalex.org/W4233029263","https://openalex.org/W4233077148","https://openalex.org/W4234178886","https://openalex.org/W4234265066","https://openalex.org/W4236293132","https://openalex.org/W4239277337","https://openalex.org/W4244399774","https://openalex.org/W4245223843","https://openalex.org/W4256236061","https://openalex.org/W4281668110","https://openalex.org/W4285719527","https://openalex.org/W4292907573","https://openalex.org/W4292915523","https://openalex.org/W4299358365","https://openalex.org/W4300119319","https://openalex.org/W4300490202"],"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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"PPT-GPU,":[5],"a":[6,17],"scalable":[7],"performance":[8],"prediction":[9,38],"toolkit":[10],"for":[11],"GPUs.":[12],"PPT-GPU":[13],"achieves":[14],"scalability":[15],"through":[16],"hybrid":[18],"high-level":[19],"modeling":[20],"approach":[21],"where":[22],"some":[23],"computations":[24],"are":[25,33],"extrapolated":[26],"and":[27,43],"multiple":[28],"parts":[29],"of":[30,46,55],"the":[31,47,52,56],"model":[32],"parallelized.":[34],"The":[35],"tool":[36],"primary":[37],"models":[39],"use":[40],"pre-collected":[41],"memory":[42],"instructions":[44],"traces":[45],"workloads":[48],"to":[49],"accurately":[50],"capture":[51],"dynamic":[53],"behavior":[54],"kernels.":[57]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
