{"id":"https://openalex.org/W7097842373","doi":null,"title":"Optimizing Data Locality And Parallelism For Scalable Multiprocessors","display_name":"Optimizing Data Locality And Parallelism For Scalable Multiprocessors","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7097842373"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.35.3276","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.3276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ee.lsu.edu/pub/jxr/papers/theses/ashish-ms.PS","raw_type":"text"},"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":null,"display_name":"Ashish Narayan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ashish Narayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-locality","display_name":"data locality","score":0.9909999966621399},{"id":"https://openalex.org/keywords/loop-level-parallelism","display_name":"loop-level parallelism","score":0.7059999704360962},{"id":"https://openalex.org/keywords/loop-restructuring","display_name":"loop restructuring","score":0.7239999771118164},{"id":"https://openalex.org/keywords/loop-transformation","display_name":"loop transformation","score":0.9179999828338623},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"memory hierarchy","score":0.6079999804496765},{"id":"https://openalex.org/keywords/memory-performance","display_name":"memory performance","score":0.6340000033378601},{"id":"https://openalex.org/keywords/multiprocessor-systems","display_name":"multiprocessor systems","score":0.7139999866485596},{"id":"https://openalex.org/keywords/scientific-codes","display_name":"scientific codes","score":0.6119999885559082},{"id":"https://openalex.org/keywords/communication-reduction","display_name":"communication reduction","score":0.49000000953674316},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.4189999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694999814033508},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6904000043869019},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5863999724388123},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.46399998664855957},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.41589999198913574},{"id":"https://openalex.org/C3543717","wikidata":"https://www.wikidata.org/wiki/Q6007302","display_name":"Implicit parallelism","level":4,"score":0.39570000767707825},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.29010000824928284},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.26089999079704285},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.35.3276","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.3276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ee.lsu.edu/pub/jxr/papers/theses/ashish-ms.PS","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2077960035","https://openalex.org/W1549048557","https://openalex.org/W48915323","https://openalex.org/W7096411912","https://openalex.org/W4238138329","https://openalex.org/W2011263215","https://openalex.org/W1591453641","https://openalex.org/W7095355789","https://openalex.org/W2590238087","https://openalex.org/W2070922326"],"abstract_inverted_index":{"As":[0],"processor":[1],"speeds":[2],"continue":[3],"to":[4,29,36,57,61,65,75,78,89,118,122],"increase":[5],"at":[6,154],"a":[7,144],"much":[8],"higher":[9],"rate":[10],"than":[11],"memory":[12,15,34,38,41,68],"speeds,":[13],"improving":[14],"performance":[16,22],"becomes":[17],"critical":[18],"in":[19,23,39,44,83,104],"realizing":[20],"high":[21,45],"parallel":[24],"machines.":[25],"The":[26,70],"aim":[27],"is":[28,54,102,142,152],"have":[30,74],"most":[31,97,128],"of":[32,47,98,110],"the":[33,40,63,80,84,99,108,114,127,147],"accesses":[35],"faster":[37],"hierarchy":[42],"resulting":[43],"levels":[46],"data":[48,91,124,150],"locality.":[49,92],"In":[50,93],"many":[51],"cases,":[52],"it":[53],"best":[55],"left":[56],"an":[58],"optimizing":[59],"compiler":[60],"restructure":[62],"program":[64],"extract":[66],"good":[67],"performance.":[69,115],"programmer":[71],"will":[72],"otherwise":[73],"write":[76],"code":[77,86],"exploit":[79,119],"parallelism":[81,120,136],"inherent":[82],"input":[85],"and":[87,121,135,140],"also":[88],"improve":[90,123],"scientific":[94],"codes,":[95],"since":[96],"CPU":[100],"time":[101],"spent":[103],"loops,":[105],"we":[106],"study":[107],"effect":[109],"restructuring":[111],"loops":[112],"on":[113],"Loop":[116],"transformations":[117],"locality":[125,134,151],"are":[126,137],"important":[129],"techniques":[130],"used":[131],"today.":[132],"Data":[133],"conflicting":[138],"goals":[139],"there":[141],"always":[143],"trade-off":[145],"between":[146],"two.":[148],"Improving":[149],"aimed":[153],"reducing":[155],"communication":[156],"betwee...":[157]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-27T00:00:00"}