{"id":"https://openalex.org/W2145493618","doi":"https://doi.org/10.1109/pact.2011.30","title":"Parameterized Micro-benchmarking: An Auto-tuning Approach for Complex Applications","display_name":"Parameterized Micro-benchmarking: An Auto-tuning Approach for Complex Applications","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2145493618","doi":"https://doi.org/10.1109/pact.2011.30","mag":"2145493618"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2011.30","pdf_url":null,"source":{"id":"https://openalex.org/S4306419751","display_name":"International Conference on Parallel Architectures and Compilation Techniques","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["Pacific Northwest National Laboratories Richland WA USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["Pacific Northwest National Laboratories Richland WA USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["Ohio State University; Columbus OH USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University; Columbus OH USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":65},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"182"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994,"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":0.9994,"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":0.9513,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9254,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.80993265},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.79208744},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"Auto tuning","score":0.72831595},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42117748}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.8263277},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.80993265},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.79208744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917912},{"id":"https://openalex.org/C2986422732","wikidata":"https://www.wikidata.org/wiki/Q753025","display_name":"Auto tuning","level":4,"score":0.72831595},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6042347},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5030739},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43408102},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42117748},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3658208},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3432852},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3423624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.097480625},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2011.30","pdf_url":null,"source":{"id":"https://openalex.org/S4306419751","display_name":"International Conference on Parallel Architectures and Compilation Techniques","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":1,"referenced_works":["https://openalex.org/W1967329527"],"related_works":["https://openalex.org/W435179959","https://openalex.org/W4238897586","https://openalex.org/W2619091065","https://openalex.org/W2329895846","https://openalex.org/W2291782699","https://openalex.org/W2284465472","https://openalex.org/W2059640416","https://openalex.org/W2011676020","https://openalex.org/W1993948687","https://openalex.org/W1490753184"],"abstract_inverted_index":{"Auto-tuning":[0],"has":[1,21],"emerged":[2],"as":[3],"an":[4,79],"important":[5],"practical":[6],"method":[7,81],"for":[8,82],"creating":[9],"highly":[10],"optimized":[11],"code.":[12],"However,":[13],"the":[14,37,106],"growing":[15],"complexity":[16],"of":[17,47,53,60,101],"architectures":[18],"and":[19,66,70],"applications":[20,43],"resulted":[22],"in":[23],"a":[24,50,57,99],"prohibitively":[25],"large":[26,58],"search":[27],"space":[28],"that":[29,44,62,108],"preclude":[30],"empirical":[31],"auto-tuning.":[32,113],"Here,":[33],"we":[34,97],"focus":[35],"on":[36,86,89],"challenge":[38],"to":[39,103],"auto-tuning":[40,46,80],"presented":[41],"by":[42],"require":[45,71],"not":[48],"just":[49],"small":[51],"number":[52,59],"distinct":[54],"kernels,":[55],"but":[56],"kernels":[61],"exhibit":[63],"similar":[64,74],"computation":[65],"memory":[67],"access":[68],"characteristics":[69],"optimization":[72],"over":[73,105],"problem":[75],"spaces.":[76],"We":[77],"propose":[78],"tensor":[83],"contraction":[84],"functions":[85],"GPUs,":[87],"based":[88],"parameterized":[90,94],"micro-benchmarks.":[91],"Using":[92],"our":[93],"micro-benchmarking":[95],"approach,":[96],"obtain":[98],"speedup":[100],"up":[102],"2":[104],"version":[107],"used":[109],"default":[110],"optimizations":[111],"without":[112]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2145493618","counts_by_year":[],"updated_date":"2024-12-07T19:00:23.855883","created_date":"2016-06-24"}