{"id":"https://openalex.org/W68254204","doi":null,"title":"Architectural Considerations for Compiler-guided Unroll-and-Jam of CUDA Kernels","display_name":"Architectural Considerations for Compiler-guided Unroll-and-Jam of CUDA Kernels","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W68254204","mag":"68254204"},"language":"en","primary_location":{"id":"mag:68254204","doi":null,"is_oa":false,"landing_page_url":"http://www.sapub.org/global/showpaperpdf.aspx?doi=10.5923/j.ajca.20120102.01","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5112322145","display_name":"Apan Qasem","orcid":"https://orcid.org/0009-0000-6213-829X","observed_orcids":["https://orcid.org/0009-0000-6213-829X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Apan Qasem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5112322145"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00665381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":"2","first_page":"12","last_page":"20"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda-kernels","display_name":"CUDA kernels","score":0.859000027179718},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.8029999732971191},{"id":"https://openalex.org/keywords/gpu-programming","display_name":"GPU programming","score":0.5130000114440918},{"id":"https://openalex.org/keywords/register-pressure","display_name":"register pressure","score":0.6759999990463257},{"id":"https://openalex.org/keywords/source-code-annotation","display_name":"source code annotation","score":0.828000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758622407913208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7124736905097961},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6940856575965881},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6710458397865295},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15538597106933594}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:68254204","doi":null,"is_oa":false,"landing_page_url":"http://www.sapub.org/global/showpaperpdf.aspx?doi=10.5923/j.ajca.20120102.01","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W178660737","https://openalex.org/W1500117749","https://openalex.org/W1527464046","https://openalex.org/W1555946726","https://openalex.org/W1665412445","https://openalex.org/W1963545097","https://openalex.org/W1965307606","https://openalex.org/W1992851788","https://openalex.org/W1993402810","https://openalex.org/W2007648666","https://openalex.org/W2063186542","https://openalex.org/W2071150184","https://openalex.org/W2098220211","https://openalex.org/W2101778912","https://openalex.org/W2102582914","https://openalex.org/W2104659803","https://openalex.org/W2105524676","https://openalex.org/W2108600626","https://openalex.org/W2108792719","https://openalex.org/W2125955291","https://openalex.org/W2128539477","https://openalex.org/W2138007781","https://openalex.org/W2139205226","https://openalex.org/W2146959317","https://openalex.org/W2154786353","https://openalex.org/W2160245390","https://openalex.org/W2160786443","https://openalex.org/W2170255449","https://openalex.org/W2170634604"],"related_works":["https://openalex.org/W2104659803","https://openalex.org/W1975001341","https://openalex.org/W2158161220","https://openalex.org/W7098524175","https://openalex.org/W2083056254","https://openalex.org/W1482990698","https://openalex.org/W7096712613","https://openalex.org/W7096127225","https://openalex.org/W7099170035","https://openalex.org/W2808709390"],"abstract_inverted_index":{"Hundreds":[0],"of":[1,23,26,58,69],"cores":[2],"per":[3],"chip":[4],"and":[5,54,75,84,139],"support":[6],"for":[7,51,90],"fine-grain":[8],"mult":[9],"ithreading":[10],"have":[11],"made":[12],"GPUs":[13],"a":[14,47,78,100],"central":[15],"p":[16],"layer":[17],"in":[18],"todays":[19],"HPC":[20],"world.":[21],"Much":[22],"the":[24,40,59,112,128,133],"responsibility":[25],"achieving":[27],"h":[28],"igh":[29],"performance":[30],"on":[31,81,99,104],"these":[32],"comp":[33],"lex":[34],"systems":[35],"lies":[36],"with":[37],"software":[38],"like":[39],"co":[41,48],"mpiler.":[42],"Th":[43],"is":[44,115],"paper":[45],"describes":[46],"mpiler-based":[49],"strategy":[50,114],"automat":[52],"ic":[53],"profitable":[55,120],"applicat":[56],"ion":[57],"unroll-and-jam":[60],"transformation":[61],"to":[62,118],"CUDA":[63,106],"kernels.":[64,107],"The":[65,108,123],"framework":[66],"supports":[67],"specification":[68],"unroll":[70,88,121,130],"factors":[71,89],"through":[72],"source-code":[73],"annotation":[74],"also":[76,125],"implements":[77],"heuristic":[79],"based":[80],"register":[82,137],"pressure":[83,138],"occupancy":[85],"that":[86,111,127],"recommends":[87],"improved":[91],"memo":[92],"ry":[93],"performance.":[94],"We":[95],"present":[96],"experimental":[97],"results":[98,109,124],"GE":[101],"9800":[102],"GT":[103],"four":[105],"show":[110],"proposed":[113],"generally":[116],"able":[117],"select":[119],"factors.":[122],"indicate":[126],"selected":[129],"amounts":[131],"strike":[132],"right":[134],"balance":[135],"between":[136],"occupancy.":[140]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}