{"id":"https://openalex.org/W1762825919","doi":"https://doi.org/10.4018/ijghpc.2015040102","title":"Exploring Vectorization and Prefetching Techniques on Scientific Kernels and Inferring the Cache Performance Metrics","display_name":"Exploring Vectorization and Prefetching Techniques on Scientific Kernels and Inferring the Cache Performance Metrics","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1762825919","doi":"https://doi.org/10.4018/ijghpc.2015040102","mag":"1762825919"},"language":"en","primary_location":{"id":"doi:10.4018/ijghpc.2015040102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijghpc.2015040102","pdf_url":null,"source":{"id":"https://openalex.org/S43307632","display_name":"International Journal of Grid and High Performance Computing","issn_l":"1938-0259","issn":["1938-0259","1938-0267"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Grid and High Performance Computing","raw_type":"journal-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/A5030003069","display_name":"J. Saira Banu","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"J. Saira Banu","raw_affiliation_strings":["School of Computing Science and Engineering, VIT University, Vellore, India"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Engineering, VIT University, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058669474","display_name":"M. Rajasekhara Babu","orcid":"https://orcid.org/0000-0002-3557-1917"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M. Rajasekhara Babu","raw_affiliation_strings":["School of Computing Science and Engineering, VIT University, Vellore, India"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Engineering, VIT University, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030003069"],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":null,"apc_paid":null,"fwci":1.2919,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79282689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":"2","first_page":"18","last_page":"36"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9979000091552734,"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":0.8707538843154907},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7999545335769653},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7918598651885986},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6380570530891418},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5596224069595337},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5579379796981812},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5324234962463379},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4285143315792084},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4197317957878113},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4189457595348358},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32990574836730957},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11868494749069214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707538843154907},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7999545335769653},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7918598651885986},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6380570530891418},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5596224069595337},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5579379796981812},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5324234962463379},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4285143315792084},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4197317957878113},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4189457595348358},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32990574836730957},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11868494749069214},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4018/ijghpc.2015040102","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijghpc.2015040102","pdf_url":null,"source":{"id":"https://openalex.org/S43307632","display_name":"International Journal of Grid and High Performance Computing","issn_l":"1938-0259","issn":["1938-0259","1938-0267"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Grid and High Performance Computing","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jghpc0:v:7:y:2015:i:2:p:18-36","is_oa":false,"landing_page_url":"http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJGHPC.2015040102","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1531802798","https://openalex.org/W1963630936","https://openalex.org/W1964876237","https://openalex.org/W1987433500","https://openalex.org/W1987840949","https://openalex.org/W1989568755","https://openalex.org/W1994515555","https://openalex.org/W2010041292","https://openalex.org/W2025108891","https://openalex.org/W2025979739","https://openalex.org/W2035080386","https://openalex.org/W2067354926","https://openalex.org/W2073061372","https://openalex.org/W2092608522","https://openalex.org/W2095656382","https://openalex.org/W2098220211","https://openalex.org/W2103359842","https://openalex.org/W2107307723","https://openalex.org/W2112855222","https://openalex.org/W2116431830","https://openalex.org/W2135063202","https://openalex.org/W2137572097","https://openalex.org/W2139774022","https://openalex.org/W2150887845","https://openalex.org/W2158323365","https://openalex.org/W2168464434","https://openalex.org/W2168956691","https://openalex.org/W3101982753"],"related_works":["https://openalex.org/W4245302940","https://openalex.org/W1571368810","https://openalex.org/W2506225776","https://openalex.org/W1784146144","https://openalex.org/W2735785139","https://openalex.org/W4239295894","https://openalex.org/W1534227216","https://openalex.org/W1762825919","https://openalex.org/W2189230148","https://openalex.org/W1967186960"],"abstract_inverted_index":{"Performance":[0],"improvement":[1],"in":[2,64,119,154],"modern":[3],"processor":[4],"is":[5,21,32,41,161,183],"staggering":[6],"due":[7],"to":[8,84,104,187],"power":[9,18],"wall":[10,13,19,30,108],"and":[11,67,117,127,132,138,142],"memory":[12,74,107],"problem.":[14,109],"In":[15,37],"general,":[16],"the":[17,51,60,65,70,106,113,136,145,150,155,157,188],"problem":[20,31],"addressed":[22],"by":[23,58,68,173],"various":[24],"vectorization":[25,40,116],"design":[26],"techniques.":[27],"The":[28],"Memory":[29],"diminished":[33],"through":[34,43],"prefetching":[35,97,118],"technique.":[36],"this":[38],"paper":[39,94],"achieved":[42],"Single":[44],"Instruction":[45],"Multiple":[46],"Data":[47],"(SIMD)":[48],"registers":[49,77,182],"of":[50,62,72,115,170,180],"current":[52],"processor.":[53,176],"It":[54],"provides":[55],"architecture":[56],"optimization":[57],"reducing":[59],"number":[61],"instructions":[63,103],"pipeline":[66],"minimizing":[69],"utilization":[71,179],"multi-level":[73],"hierarchy.":[75],"These":[76],"provide":[78],"an":[79],"economical":[80],"computing":[81],"platform":[82],"compared":[83],"Graphics":[85],"Processing":[86],"Unit":[87],"(GPU)":[88],"for":[89],"compute":[90],"intensive":[91],"applications.":[92],"This":[93,110],"explores":[95],"software":[96],"via":[98],"Streaming":[99],"SIMD":[100,181],"extension":[101],"(SSE)":[102],"mitigate":[105],"work":[111],"quantifies":[112],"effect":[114],"Matrix":[120],"Vector":[121],"Multiplication":[122],"(MVM)":[123],"kernel":[124,172],"with":[125],"dense":[126],"sparse":[128],"structure.":[129],"Both":[130],"Prefetching":[131],"Vectorization":[133],"method":[134],"reduces":[135],"data":[137],"instruction":[139],"cache":[140,146,151],"pressure":[141],"thereby":[143],"improving":[144],"performance.":[147],"To":[148],"show":[149],"performance":[152,169],"improvements":[153],"kernel,":[156],"Intel":[158,174],"VTune":[159],"amplifier":[160],"used.":[162],"Finally,":[163],"experimental":[164],"results":[165],"demonstrate":[166],"a":[167,184],"promising":[168],"matrix":[171],"Haswell's":[175],"However,":[177],"effective":[178],"programming":[185],"challenge":[186],"developers.":[189]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
