{"id":"https://openalex.org/W4237020593","doi":"https://doi.org/10.1109/ipdps.2006.1639589","title":"On improving performance and energy profiles of sparse scientific applications","display_name":"On improving performance and energy profiles of sparse scientific applications","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W4237020593","doi":"https://doi.org/10.1109/ipdps.2006.1639589"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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/A5113655168","display_name":"Konrad Malkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K. Malkowski","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452810","display_name":"Ingyu Lee","orcid":"https://orcid.org/0000-0001-9143-6384"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ingyu Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102868534","display_name":"Padma Raghavan","orcid":"https://orcid.org/0009-0002-6785-2112"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Raghavan","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110890725","display_name":"M.J. Irwin","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.J. Irwin","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113655168"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.5575,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70320941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"8 pp.","last_page":"8 pp."},"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":0.9995999932289124,"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":0.9988999962806702,"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":0.8380623459815979},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7101690173149109},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.675194501876831},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.6602662801742554},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6511499881744385},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6239836812019348},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5070807933807373},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4893414378166199},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.48126548528671265},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47961151599884033},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44943299889564514},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4334099590778351},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42531710863113403},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.41318923234939575},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.1743687093257904},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13165774941444397},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12345746159553528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380623459815979},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7101690173149109},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.675194501876831},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.6602662801742554},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6511499881744385},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6239836812019348},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5070807933807373},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4893414378166199},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.48126548528671265},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47961151599884033},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44943299889564514},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4334099590778351},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42531710863113403},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.41318923234939575},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.1743687093257904},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13165774941444397},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12345746159553528},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2006.1639589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W111684325","https://openalex.org/W1609496979","https://openalex.org/W1987393840","https://openalex.org/W2038469228","https://openalex.org/W2080035108","https://openalex.org/W2104225326","https://openalex.org/W2150601144","https://openalex.org/W2343594199","https://openalex.org/W3140903683","https://openalex.org/W4237281620","https://openalex.org/W4251310970","https://openalex.org/W4252470283","https://openalex.org/W4256588782","https://openalex.org/W4301406976","https://openalex.org/W6670463535","https://openalex.org/W6684183497","https://openalex.org/W6792941224"],"related_works":["https://openalex.org/W2293771254","https://openalex.org/W2886568922","https://openalex.org/W2158210957","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2914631005","https://openalex.org/W2123154672","https://openalex.org/W2032786851","https://openalex.org/W2952630098"],"abstract_inverted_index":{"In":[0,90],"many":[1],"scientific":[2,215],"applications,":[3],"the":[4,7,34,86,139,152,161,177,181,193],"majority":[5],"of":[6,33,39,44,62,101,106,172,180,184,195,211,221],"execution":[8,155],"time":[9,156],"is":[10],"spent":[11],"within":[12],"a":[13,31],"few":[14],"basic":[15],"sparse":[16,20,26,95,214],"kernels":[17,27,97,209],"such":[18,74,84,132],"as":[19,85],"matrix":[21],"vector":[22],"multiplication":[23],"(SMV).":[24],"Such":[25],"can":[28,70,135,188],"utilize":[29],"only":[30],"fraction":[32],"available":[35,80],"processing":[36],"speed":[37],"because":[38],"their":[40],"relatively":[41],"large":[42],"number":[43],"data":[45,53,56],"accesses":[46],"per":[47],"floating":[48],"point":[49],"operation,":[50],"and":[51,55,60,66,118,125,144,160,174],"limited":[52],"locality":[54],"re-use.":[57],"Algorithmic":[58],"changes":[59],"tuning":[61,102,143],"codes":[63,216],"through":[64],"blocking":[65],"loop":[67],"unrolling":[68],"schemes":[69],"improve":[71],"performance":[72,124,213],"but":[73],"tuned":[75,208],"versions":[76],"are":[77,104],"typically":[78],"not":[79],"in":[81,123],"benchmark":[82],"suites":[83],"SPEC":[87],"CFP":[88],"2000.":[89],"this":[91,107],"paper,":[92],"we":[93],"consider":[94],"SMV":[96],"with":[98,168],"different":[99],"levels":[100],"that":[103,151],"representative":[105],"application":[108],"space.":[109],"We":[110,128],"emulate":[111],"certain":[112],"memory":[113,145,185],"subsystem":[114,146,186],"optimizations":[115,153,187],"using":[116],"SimpleScalar":[117],"Wattch":[119],"to":[120,203,217],"evaluate":[121],"improvements":[122],"energy":[126,162],"metrics.":[127],"also":[129],"characterize":[130],"how":[131],"an":[133],"evaluation":[134],"be":[136,201],"affected":[137],"by":[138,157,163,207],"interplay":[140],"between":[141],"code":[142,196],"optimizations.":[147],"Our":[148],"results":[149],"indicate":[150],"reduce":[154],"over":[158,164],"40%,":[159],"85%,":[165],"when":[166],"used":[167],"power":[169],"control":[170],"modes":[171],"CPUs":[173],"caches.":[175],"Furthermore,":[176],"relative":[178],"impact":[179],"same":[182],"set":[183],"vary":[189],"significantly":[190],"depending":[191],"on":[192],"level":[194],"tuning.":[197],"Consequently,":[198],"it":[199],"may":[200],"appropriate":[202],"augment":[204],"traditional":[205],"benchmarks":[206],"typical":[210],"high":[212],"enable":[218],"comprehensive":[219],"evaluations":[220],"future":[222],"systems.":[223]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}