{"id":"https://openalex.org/W7167097434","doi":"https://doi.org/10.1145/3797905.3800517","title":"GRASP: Fine-grained and Adaptive Sampled Simulation for GPU Performance Modeling","display_name":"GRASP: Fine-grained and Adaptive Sampled Simulation for GPU Performance Modeling","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167097434","doi":"https://doi.org/10.1145/3797905.3800517"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800517","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3800517","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047127750","display_name":"Ruini Xue","orcid":"https://orcid.org/0000-0003-1802-5188"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruini Xue","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1802-5188","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139870859","display_name":"Lingwei Chao","orcid":"https://orcid.org/0009-0007-5588-1596"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingwei Chao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0007-5588-1596","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125134527","display_name":"Z Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxing Huang","raw_affiliation_strings":["University of Electronic Science and Technology of China, 0009-0003-4135-6329, China"],"raw_orcid":"https://orcid.org/0009-0000-7613-6156","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, 0009-0003-4135-6329, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124149714","display_name":"Peilin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peilin Cai","raw_affiliation_strings":["University of Electronic Science and Technology of China, 0009-0003-4135-6329, China"],"raw_orcid":"https://orcid.org/0009-0002-5725-0513","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, 0009-0003-4135-6329, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119390965","display_name":"Jiangying Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangying Xue","raw_affiliation_strings":["University of Electronic Science and Technology of China, 0009-0003-4135-6329, China"],"raw_orcid":"https://orcid.org/0009-0002-4667-8741","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, 0009-0003-4135-6329, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119390966","display_name":"Tianyu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Xiong","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0003-4135-6329","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9462000131607056,"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":0.9462000131607056,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.010900000110268593,"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":0.006500000134110451,"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/acceleration","display_name":"Acceleration","score":0.6401000022888184},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.37400001287460327},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.3133000135421753},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3068999946117401},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3059000074863434},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.2816999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451000213623047},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6401000022888184},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2780974030","wikidata":"https://www.wikidata.org/wiki/Q16951926","display_name":"Co-simulation","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C108215451","wikidata":"https://www.wikidata.org/wiki/Q7263963","display_name":"Simulation modeling","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800517","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3800517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800517","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1031578623","https://openalex.org/W1902930330","https://openalex.org/W2080592089","https://openalex.org/W2084660366","https://openalex.org/W2086739451","https://openalex.org/W2103742924","https://openalex.org/W2144264070","https://openalex.org/W2149234156","https://openalex.org/W2167334577","https://openalex.org/W2194775991","https://openalex.org/W2234148183","https://openalex.org/W2239144794","https://openalex.org/W2587914027","https://openalex.org/W2952928793","https://openalex.org/W3013103997","https://openalex.org/W3097320606","https://openalex.org/W3102510044","https://openalex.org/W3104094521","https://openalex.org/W3115301563","https://openalex.org/W3157055696","https://openalex.org/W3198685994","https://openalex.org/W3207572920","https://openalex.org/W4205924567","https://openalex.org/W4281689389","https://openalex.org/W4283710864","https://openalex.org/W4289712286","https://openalex.org/W4381894551","https://openalex.org/W4389476192","https://openalex.org/W4389476196","https://openalex.org/W4393592128"],"related_works":[],"abstract_inverted_index":{"GPUs":[0],"have":[1],"emerged":[2],"as":[3],"foundational":[4],"platforms":[5],"for":[6,29],"high-performance":[7],"computing":[8],"and":[9,42],"machine":[10],"learning.":[11],"However,":[12],"rapid":[13],"architectural":[14],"evolution":[15],"challenges":[16],"existing":[17],"performance":[18],"evaluations.":[19],"Cycle-accurate":[20],"simulation":[21],"offers":[22],"high":[23],"precision":[24],"but":[25],"is":[26],"prohibitively":[27],"slow":[28],"large-scale":[30],"design":[31],"exploration.":[32],"Sampling-based":[33],"acceleration":[34],"techniques":[35],"struggle":[36],"with":[37],"behavior":[38],"characterization,":[39],"stable-state":[40],"detection,":[41],"execution":[43],"time":[44],"prediction,":[45],"thus":[46],"constraining":[47],"their":[48],"applicability":[49],"in":[50],"complex":[51],"GPU":[52],"workloads.":[53]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-07-03T00:00:00"}
