{"id":"https://openalex.org/W2917036561","doi":"https://doi.org/10.1109/cahpc.2018.8645892","title":"Exploiting Limited Access Distance for Kernel Fusion Across the Stages of Explicit One-Step Methods on GPUs","display_name":"Exploiting Limited Access Distance for Kernel Fusion Across the Stages of Explicit One-Step Methods on GPUs","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2917036561","doi":"https://doi.org/10.1109/cahpc.2018.8645892","mag":"2917036561"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","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/A5036300591","display_name":"Matthias Korch","orcid":"https://orcid.org/0000-0001-7267-0378"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Korch","raw_affiliation_strings":["Department of Computer Science, University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007164076","display_name":"Tim Werner","orcid":"https://orcid.org/0000-0002-3450-8019"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Werner","raw_affiliation_strings":["Department of Computer Science, University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036300591"],"corresponding_institution_ids":["https://openalex.org/I54009628"],"apc_list":null,"apc_paid":null,"fwci":0.9888,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75231369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11416","display_name":"Numerical methods for differential equations","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11416","display_name":"Numerical methods for differential equations","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.994700014591217,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796246767044067},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.5985033512115479},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5636749267578125},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5416678786277771},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.425582617521286},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4110734760761261},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3937883675098419},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3704019784927368},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.284814715385437},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.1624433398246765},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.15442830324172974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796246767044067},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.5985033512115479},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5636749267578125},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5416678786277771},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.425582617521286},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4110734760761261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3937883675098419},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3704019784927368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.284814715385437},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.1624433398246765},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.15442830324172974},{"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":2,"locations":[{"id":"doi:10.1109/cahpc.2018.8645892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},{"id":"pmh:oai::46038","is_oa":false,"landing_page_url":"https://eref.uni-bayreuth.de/46038/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196442","display_name":"ERef Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Aufsatz in einem Buch"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522400747","https://openalex.org/W1555915743","https://openalex.org/W1922926746","https://openalex.org/W1973532523","https://openalex.org/W1979457157","https://openalex.org/W2042388195","https://openalex.org/W2055312318","https://openalex.org/W2063656563","https://openalex.org/W2065728536","https://openalex.org/W2075814631","https://openalex.org/W2104512032","https://openalex.org/W2111389017","https://openalex.org/W2153190325","https://openalex.org/W2159959523","https://openalex.org/W2170669366","https://openalex.org/W2259348796","https://openalex.org/W2524055208","https://openalex.org/W2725179571","https://openalex.org/W2786544209","https://openalex.org/W2889184324","https://openalex.org/W2963242393","https://openalex.org/W3123057955","https://openalex.org/W6643480586"],"related_works":["https://openalex.org/W2371448224","https://openalex.org/W3134495997","https://openalex.org/W2363680170","https://openalex.org/W2376428685","https://openalex.org/W4256082577","https://openalex.org/W625783435","https://openalex.org/W2048742619","https://openalex.org/W2384641672","https://openalex.org/W2742179975","https://openalex.org/W2362647823"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,9,35,39,47,49,51,56,64,78],"explicit":[3],"parallel":[4],"methods":[5],"solving":[6],"large":[7,37],"systems":[8],"ordinary":[10],"differential":[11],"equations":[12],"(ODEs)":[13],"on":[14,75],"GPUs":[15],"is":[16,73],"often":[17],"memory":[18],"bound.":[19],"Therefore,":[20],"locality":[21],"optimizations,":[22],"such":[23],"as":[24],"kernel":[25],"fusion,":[26],"are":[27,115],"desirable.":[28],"This":[29,59],"paper":[30],"exploits":[31],"a":[32,36,62,76,83],"special":[33],"property":[34],"class":[38],"right-hand-side":[40],"(RHS)":[41],"functions":[42],"to":[43,61,95],"enable":[44],"the":[45,57,65,79],"fusion":[46],"computations":[48],"blocks":[50],"components":[52],"across":[53],"multiple":[54],"stages":[55,66],"method.":[58],"leads":[60],"tiling":[63,108],"within":[67],"one":[68],"time":[69],"step.":[70],"Our":[71],"approach":[72],"based":[74],"representation":[77],"ODE":[80],"method":[81],"by":[82],"data":[84],"flow":[85],"graph":[86],"and":[87,111],"allows":[88],"efficient":[89],"GPU":[90],"code":[91],"with":[92],"fused":[93],"kernels":[94],"be":[96],"generated":[97],"automatically":[98],"for":[99,118],"user-defined":[100],"tilings.":[101],"In":[102],"particular,":[103],"we":[104],"investigate":[105],"two":[106],"generalized":[107],"strategies,":[109],"trapezoidal":[110],"hexagonal":[112],"tiling,":[113],"which":[114],"evaluated":[116],"experimentally":[117],"several":[119],"different":[120],"high-order":[121],"Runge-Kutta":[122],"(RK)":[123],"methods.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}