{"id":"https://openalex.org/W4410049459","doi":"https://doi.org/10.1145/3676151.3719375","title":"Multi-Strided Access Patterns to Boost Hardware Prefetching","display_name":"Multi-Strided Access Patterns to Boost Hardware Prefetching","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410049459","doi":"https://doi.org/10.1145/3676151.3719375"},"language":"en","primary_location":{"id":"doi:10.1145/3676151.3719375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719375","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3676151.3719375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111273152","display_name":"M. Blom","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Miguel O. Blom","raw_affiliation_strings":["LIACS, Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0009-0003-2174-9184","affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074964009","display_name":"Kristian F. D. Rietveld","orcid":"https://orcid.org/0000-0003-0455-3430"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kristian F. D. Rietveld","raw_affiliation_strings":["LIACS, Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0455-3430","affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063310768","display_name":"Rob V. van Nieuwpoort","orcid":"https://orcid.org/0000-0002-2947-9444"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rob V. van Nieuwpoort","raw_affiliation_strings":["LIACS, Leiden University, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-2947-9444","affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":null,"apc_paid":null,"fwci":2.55,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86177576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"215"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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":0.7504643797874451},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.44925105571746826},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42529916763305664},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4113103747367859},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.333889365196228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504643797874451},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.44925105571746826},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42529916763305664},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4113103747367859},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.333889365196228}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3676151.3719375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719375","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/b6191868-bb20-46e7-943c-13c0587d6286","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/multistrided-access-patterns-to-boost-hardware-prefetching(b6191868-bb20-46e7-943c-13c0587d6286).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Blom, M O, Rietveld, K F D & van Nieuwpoort, R V 2025, Multi-Strided Access Patterns to Boost Hardware Prefetching. in ICPE '25 : Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering : May 5-9, 2025, Toronto, Canada. Association for Computing Machinery, New York, NY, pp. 204-215, 16th ACM/SPEC International Conference on Performance, ICPE 2025, Toronto, Canada, 5/05/25. https://doi.org/10.1145/3676151.3719375","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dare.uva.nl:openaire/b6191868-bb20-46e7-943c-13c0587d6286","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/b6191868-bb20-46e7-943c-13c0587d6286","pdf_url":"https://pure.uva.nl/ws/files/270386129/3676151.3719375.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Blom, M O, Rietveld, K F D & van Nieuwpoort, R V 2025, Multi-Strided Access Patterns to Boost Hardware Prefetching. in ICPE '25 : Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering : May 5-9, 2025, Toronto, Canada. Association for Computing Machinery, New York, NY, pp. 204-215, 16th ACM/SPEC International Conference on Performance, ICPE 2025, Toronto, Canada, 5/05/25. https://doi.org/10.1145/3676151.3719375","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_4295555","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/4295555","pdf_url":"https://scholarlypublications.universiteitleiden.nl/access/item%3A4295556/view","source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Performance Engineering -- ICPE '25: proceedings of the 16th ACM/SPEC international conference on performance engineering","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3676151.3719375","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719375","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1706882832","https://openalex.org/W1856606395","https://openalex.org/W1963963558","https://openalex.org/W1964304048","https://openalex.org/W2010128395","https://openalex.org/W2016558956","https://openalex.org/W2036162037","https://openalex.org/W2053464325","https://openalex.org/W2055312318","https://openalex.org/W2055761985","https://openalex.org/W2063397164","https://openalex.org/W2078081736","https://openalex.org/W2098688018","https://openalex.org/W2109763887","https://openalex.org/W2117560661","https://openalex.org/W2121492601","https://openalex.org/W2154847378","https://openalex.org/W2171006257","https://openalex.org/W2180890913","https://openalex.org/W2329976284","https://openalex.org/W2357843841","https://openalex.org/W2414782828","https://openalex.org/W2416944327","https://openalex.org/W2434397002","https://openalex.org/W2471164860","https://openalex.org/W2537450429","https://openalex.org/W2789602589","https://openalex.org/W2793666465","https://openalex.org/W2810610794","https://openalex.org/W2950959891","https://openalex.org/W2961619211","https://openalex.org/W2962807014","https://openalex.org/W3003529076","https://openalex.org/W3021447659","https://openalex.org/W4221095718","https://openalex.org/W4238606955","https://openalex.org/W4239660062","https://openalex.org/W4239696737","https://openalex.org/W4245636261","https://openalex.org/W4251798485","https://openalex.org/W4308083829","https://openalex.org/W4378801305","https://openalex.org/W4394871742","https://openalex.org/W4399163533","https://openalex.org/W4399282165","https://openalex.org/W4399304198","https://openalex.org/W4401753418","https://openalex.org/W4403875551"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Important":[0],"memory-bound":[1,86,144],"kernels,":[2],"such":[3],"as":[4,14,16],"linear":[5],"algebra,":[6],"convolutions,":[7],"and":[8,23,79,120,166,189,211],"stencils,":[9],"rely":[10],"on":[11,151],"SIMD":[12],"instructions":[13],"well":[15],"optimizations":[17],"targeting":[18],"improved":[19,116],"vectorized":[20],"data":[21,24],"traversal":[22],"re-use":[25],"to":[26,64,107,176,196,218],"attain":[27],"satisfactory":[28],"performance.":[29],"On":[30],"contemporary":[31],"CPU":[32],"architectures,":[33],"the":[34,45,73,76,83,112,126,208,225],"hardware":[35,77],"prefetcher":[36],"is":[37,203],"of":[38,44,60,75,85,92,128,139,142,174,199,207],"key":[39],"importance":[40],"for":[41,157],"efficient":[42],"utilization":[43,74],"memory":[46,56,98,123,201],"hierarchy.":[47],"In":[48],"this":[49,216],"paper,":[50],"we":[51,94,134,170],"demonstrate":[52],"that":[53,66,96,136],"transforming":[54],"a":[55,61,90,100,140,204],"access":[57,202],"pattern":[58],"consisting":[59],"single":[62],"stride":[63],"one":[65],"concurrently":[67,109],"accesses":[68],"multiple":[69],"strides,":[70],"can":[71],"boost":[72],"prefetcher,":[78],"in":[80,99,115,224],"turn":[81],"improves":[82],"performance":[84],"kernels":[87,147,158,167],"significantly.":[88],"Using":[89],"set":[91],"micro-benchmarks,":[93],"establish":[95],"accessing":[97],"multi-strided":[101,137,200],"manner":[102],"enables":[103],"more":[104],"cache":[105,117],"lines":[106],"be":[108,219],"brought":[110],"into":[111,221],"cache,":[113],"resulting":[114],"hit":[118],"ratios":[119],"higher":[121],"effective":[122],"bandwidth":[124],"without":[125],"introduction":[127],"costly":[129],"software":[130],"prefetch":[131],"instructions.":[132],"Subsequently,":[133],"show":[135],"variants":[138],"collection":[141],"six":[143],"dense":[145],"compute":[146],"outperform":[148],"state-of-the-art":[149],"counterparts":[150],"three":[152],"different":[153],"micro-architectures.":[154],"More":[155],"specifically,":[156],"among":[159],"which":[160],"Matrix":[161],"Vector":[162],"Multiplication,":[163],"Convolution":[164],"Stencil":[165],"from":[168],"PolyBench,":[169],"achieve":[171],"significant":[172],"speedups":[173],"up":[175],"12.55x":[177],"over":[178,181,184,187,191],"Polly,":[179],"2.99x":[180],"MKL,":[182],"1.98x":[183],"OpenBLAS,":[185],"1.08x":[186],"Halide":[188],"1.87x":[190],"OpenCV.":[192],"The":[193],"code":[194],"transformation":[195],"take":[197],"advantage":[198],"natural":[205],"extension":[206],"loop":[209,212],"unroll":[210],"interchange":[213],"techniques,":[214],"allowing":[215],"method":[217],"incorporated":[220],"compiler":[222],"pipelines":[223],"future.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}