{"id":"https://openalex.org/W2005815910","doi":"https://doi.org/10.1145/2141702.2141706","title":"Efficient execution of time-step computations with pipelined parallelism and inter-thread data locality optimizaitions","display_name":"Efficient execution of time-step computations with pipelined parallelism and inter-thread data locality optimizaitions","publication_year":2012,"publication_date":"2012-02-26","ids":{"openalex":"https://openalex.org/W2005815910","doi":"https://doi.org/10.1145/2141702.2141706","mag":"2005815910"},"language":"en","primary_location":{"id":"doi:10.1145/2141702.2141706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2141702.2141706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores","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/A5112322145","display_name":"Apan Qasem","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Apan Qasem","raw_affiliation_strings":["Texas State University, San Marcos, TX"],"affiliations":[{"raw_affiliation_string":"Texas State University, San Marcos, TX","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112322145"],"corresponding_institution_ids":["https://openalex.org/I13511017"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08075698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"35"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.998199999332428,"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":0.877381443977356},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.8197637796401978},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7739865183830261},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6649653911590576},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.5346322059631348},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5027074813842773},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4912702441215515},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.4745762348175049},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.44291555881500244},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4423932433128357},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.43860673904418945},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.43157434463500977},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4287784993648529},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.36518338322639465},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3064561188220978},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12756091356277466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.877381443977356},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8197637796401978},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7739865183830261},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6649653911590576},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.5346322059631348},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5027074813842773},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4912702441215515},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.4745762348175049},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.44291555881500244},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4423932433128357},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.43860673904418945},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.43157434463500977},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4287784993648529},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.36518338322639465},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3064561188220978},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12756091356277466},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2141702.2141706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2141702.2141706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3873151713","display_name":null,"funder_award_id":"DE-SC001770","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1500117749","https://openalex.org/W1536051636","https://openalex.org/W1551026808","https://openalex.org/W1557976352","https://openalex.org/W1568192366","https://openalex.org/W1650934639","https://openalex.org/W1825294837","https://openalex.org/W2003798513","https://openalex.org/W2008056963","https://openalex.org/W2108730477","https://openalex.org/W2119609467","https://openalex.org/W2151307463","https://openalex.org/W2153499233","https://openalex.org/W2155312437","https://openalex.org/W2158158791","https://openalex.org/W2159456929","https://openalex.org/W2160106616","https://openalex.org/W3011180447","https://openalex.org/W4206232732","https://openalex.org/W6633991270","https://openalex.org/W6902605983"],"related_works":["https://openalex.org/W2526302199","https://openalex.org/W1860211040","https://openalex.org/W2009213655","https://openalex.org/W2003935582","https://openalex.org/W4240606930","https://openalex.org/W2154460420","https://openalex.org/W2950520577","https://openalex.org/W168408236","https://openalex.org/W2105992728","https://openalex.org/W3007272028"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,7,46,101,112],"strategy":[4,87,144],"that":[5,15,136,137],"integrates":[6],"set":[8,102],"of":[9,21,49,75,103],"compiler":[10],"optimizations":[11],"and":[12,19,44,60,96,120,153],"analysis":[13],"techniques":[14],"enable":[16],"the":[17,54,76,138,150],"detection":[18],"transformation":[20],"time":[22],"step":[23],"loops":[24],"for":[25,66],"efficient":[26],"execution":[27,157],"on":[28,131],"multicore":[29,68,133],"platforms.":[30],"Time-step":[31],"computations,":[32],"which":[33],"appear":[34],"frequently":[35],"in":[36,149],"scientific":[37],"applications,":[38],"are":[39],"amenable":[40],"to":[41,92],"pipelined":[42],"parallelism":[43,61,110],"exhibit":[45],"high":[47],"degree":[48],"temporal":[50],"locality.":[51],"However,":[52],"striking":[53],"right":[55],"balance":[56],"between":[57],"data":[58,94],"locality":[59,95],"often":[62],"proves":[63],"difficult,":[64],"particularly":[65],"current":[67],"architectures":[69],"where":[70],"one":[71],"or":[72],"more":[73],"levels":[74],"memory":[77],"hierarchy":[78],"is":[79],"shared":[80,151],"among":[81],"multiple":[82],"processing":[83],"units.":[84],"Our":[85],"proposed":[86],"addresses":[88],"performance":[89],"issues":[90],"related":[91],"both":[93],"parallelism.":[97],"By":[98],"carefully":[99],"orchestrating":[100],"source-to-source":[104],"transformations,":[105],"our":[106,143],"technique":[107],"exposes":[108],"fine-grain":[109],"within":[111],"time-step":[113,129],"loop,":[114],"while":[115],"improving":[116],"its":[117,122],"cache":[118],"utilization":[119],"reducing":[121],"bandwidth":[123],"requirements.":[124],"Preliminary":[125],"experiments":[126],"with":[127],"two":[128],"applications":[130],"three":[132],"platforms":[134],"show":[135],"code":[139],"variants":[140],"generated":[141],"by":[142],"have":[145],"significantly":[146],"fewer":[147],"misses":[148],"caches":[152],"also":[154],"achieve":[155],"better":[156],"times":[158],"through":[159],"reduced":[160],"synchronization":[161],"costs.":[162]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}