{"id":"https://openalex.org/W2293076069","doi":"https://doi.org/10.1145/2830018.2830024","title":"Optimizing the LULESH stencil code using concurrent collections","display_name":"Optimizing the LULESH stencil code using concurrent collections","publication_year":2015,"publication_date":"2015-11-05","ids":{"openalex":"https://openalex.org/W2293076069","doi":"https://doi.org/10.1145/2830018.2830024","mag":"2293076069"},"language":"en","primary_location":{"id":"doi:10.1145/2830018.2830024","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830018.2830024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing","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/A5100631721","display_name":"Chenyang Liu","orcid":"https://orcid.org/0000-0001-8033-9941"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chenyang Liu","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075916086","display_name":"Milind Kulkarni","orcid":"https://orcid.org/0000-0001-6827-345X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Kulkarni","raw_affiliation_strings":["Purdue University, West Lafayette, Indiana"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, Indiana","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100631721"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.9689,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77462377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9930999875068665,"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":0.8685548305511475},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6716718673706055},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6542948484420776},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6437541246414185},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6355361938476562},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5170788764953613},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5034543871879578},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.4998140335083008},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4907320737838745},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4661411643028259},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4400772452354431},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4324647784233093},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4147305488586426},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2529529333114624},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15012988448143005},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1133958101272583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8685548305511475},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6716718673706055},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6542948484420776},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6437541246414185},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6355361938476562},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5170788764953613},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5034543871879578},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.4998140335083008},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4907320737838745},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4661411643028259},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4400772452354431},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4324647784233093},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4147305488586426},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2529529333114624},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15012988448143005},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1133958101272583},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830018.2830024","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830018.2830024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W38098785","https://openalex.org/W138450674","https://openalex.org/W288065879","https://openalex.org/W1566461485","https://openalex.org/W2034761517","https://openalex.org/W2050989056","https://openalex.org/W2072725684","https://openalex.org/W2105601023","https://openalex.org/W2130604611","https://openalex.org/W2474594241","https://openalex.org/W2533312342","https://openalex.org/W2911472304","https://openalex.org/W4234858060"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2359835790","https://openalex.org/W2122403474","https://openalex.org/W2391715591","https://openalex.org/W2171750108","https://openalex.org/W1754116331","https://openalex.org/W2105520056"],"abstract_inverted_index":{"Writing":[0],"scientific":[1],"applications":[2],"for":[3,19,211],"modern":[4],"multicore":[5],"machines":[6],"is":[7,34,130,144],"a":[8,13,40,57,133,186],"challenging":[9],"task.":[10],"There":[11],"are":[12,93],"myriad":[14],"of":[15,47,88,112,136,157],"hardware":[16],"solutions":[17],"available":[18,85],"many":[20],"different":[21],"target":[22],"applications,":[23],"each":[24],"having":[25],"their":[26],"own":[27],"advantages":[28],"and":[29,59,71,149,162,182,188],"trade-offs.":[30],"An":[31],"attractive":[32],"approach":[33],"Concurrent":[35,125],"Collections":[36],"(CnC),":[37],"which":[38],"provides":[39],"programming":[41,69,78],"model":[42,62],"that":[43,167],"separates":[44],"the":[45,48,52,76,80,89,100,110,113,154,205],"concerns":[46],"application":[49,190],"expert":[50],"from":[51,66],"performance":[53,111,143],"expert.":[54],"CnC":[55,77,170,177],"uses":[56],"data":[58],"control":[60],"flow":[61],"paired":[63],"with":[64,139,208],"philosophies":[65],"previous":[67],"data-flow":[68],"models":[70],"tuple-space":[72],"influences.":[73],"By":[74],"following":[75],"paradigm,":[79],"runtime":[81],"will":[82],"seamlessly":[83],"exploit":[84],"parallelism":[86],"regardless":[87],"platform;":[90],"however,":[91],"there":[92],"limitations":[94],"to":[95,108,184,201,213],"its":[96],"effectiveness":[97],"depending":[98],"on":[99,192],"algorithm.":[101],"In":[102,160],"this":[103],"paper,":[104],"we":[105,165,198],"explore":[106],"ways":[107],"optimize":[109],"proxy":[114],"application,":[115],"Livermore":[116],"Unstructured":[117],"Lagrange":[118],"Explicit":[119],"Shock":[120],"Hydrodynamics":[121],"(LULESH),":[122],"written":[123],"using":[124],"Collections.":[126],"The":[127],"LULESH":[128,161],"algorithm":[129],"expressed":[131],"as":[132],"minimally-constrained":[134],"set":[135],"partially-ordered":[137],"operations":[138],"explicit":[140],"dependencies.":[141],"However,":[142],"plagued":[145],"by":[146,153,175],"scheduling":[147],"overhead":[148],"synchronization":[150],"costs":[151],"caused":[152],"fine":[155],"granularity":[156],"computation":[158],"steps.":[159],"similar":[163],"stencil-codes,":[164],"show":[166],"an":[168],"algorithmic":[169],"program":[171],"can":[172],"be":[173],"tuned":[174],"coalescing":[176],"elements":[178],"through":[179],"step":[180],"fusion":[181],"tiling":[183],"become":[185],"well-tuned":[187],"scalable":[189],"running":[191],"multi-core":[193],"systems.":[194],"With":[195],"these":[196],"optimizations,":[197],"achieve":[199],"up":[200,212],"38x":[202],"speedup":[203],"over":[204],"original":[206],"implementation":[207],"good":[209],"scalability":[210],"48":[214],"processor":[215],"machines.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}