{"id":"https://openalex.org/W2754674485","doi":"https://doi.org/10.1109/access.2017.2750923","title":"Acceleration by Inline Cache for Memory-Intensive Algorithms on FPGA via High-Level Synthesis","display_name":"Acceleration by Inline Cache for Memory-Intensive Algorithms on FPGA via High-Level Synthesis","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2754674485","doi":"https://doi.org/10.1109/access.2017.2750923","mag":"2754674485"},"language":"en","primary_location":{"id":"doi:10.1109/access.2017.2750923","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2750923","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2017.2750923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100733564","display_name":"Liang Ma","orcid":"https://orcid.org/0000-0002-3048-5112"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Liang Ma","raw_affiliation_strings":["Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050365912","display_name":"Luciano Lavagno","orcid":"https://orcid.org/0000-0002-9762-6522"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luciano Lavagno","raw_affiliation_strings":["Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030646218","display_name":"Mihai T. Lazarescu","orcid":"https://orcid.org/0000-0003-0884-5158"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mihai Teodor Lazarescu","raw_affiliation_strings":["Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066926780","display_name":"Arslan Arif","orcid":"https://orcid.org/0000-0002-0912-5008"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Arslan Arif","raw_affiliation_strings":["Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100733564"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9264,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75411914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"18953","last_page":"18974"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9995999932289124,"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":0.9970999956130981,"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":0.8880536556243896},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6167343258857727},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5254824757575989},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.5204818248748779},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5201975703239441},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5195934772491455},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.49514904618263245},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.46642476320266724},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.43816202878952026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36365729570388794},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35052168369293213},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.24048691987991333},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11187684535980225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880536556243896},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6167343258857727},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5254824757575989},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.5204818248748779},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5201975703239441},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5195934772491455},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.49514904618263245},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.46642476320266724},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.43816202878952026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36365729570388794},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35052168369293213},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.24048691987991333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11187684535980225}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2017.2750923","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2750923","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1bf3adca354043acbf8e40b89f0f15ec","is_oa":true,"landing_page_url":"https://doaj.org/article/1bf3adca354043acbf8e40b89f0f15ec","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 5, Pp 18953-18974 (2017)","raw_type":"article"},{"id":"pmh:oai:porto.polito.it:2685435","is_oa":true,"landing_page_url":"http://porto.polito.it/2685435/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"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":"ISSN:2169-3536","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/access.2017.2750923","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2750923","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G2629925963","display_name":null,"funder_award_id":"H2020-ICT-671632","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1565206031","https://openalex.org/W1999085092","https://openalex.org/W2005022399","https://openalex.org/W2013594929","https://openalex.org/W2022128349","https://openalex.org/W2024612992","https://openalex.org/W2061624656","https://openalex.org/W2064115172","https://openalex.org/W2087064593","https://openalex.org/W2097537332","https://openalex.org/W2107017163","https://openalex.org/W2109683087","https://openalex.org/W2115069592","https://openalex.org/W2118558147","https://openalex.org/W2118877769","https://openalex.org/W2127788760","https://openalex.org/W2131926352","https://openalex.org/W2138411892","https://openalex.org/W2139774022","https://openalex.org/W2143285027","https://openalex.org/W2149129840","https://openalex.org/W2149294210","https://openalex.org/W2165949232","https://openalex.org/W2253587711","https://openalex.org/W2286366494","https://openalex.org/W2527148519","https://openalex.org/W2560652762","https://openalex.org/W2564844125","https://openalex.org/W2589329959","https://openalex.org/W3003468330","https://openalex.org/W3145738314","https://openalex.org/W4233785673","https://openalex.org/W4237150160","https://openalex.org/W6675766548","https://openalex.org/W6677548441"],"related_works":["https://openalex.org/W2121492601","https://openalex.org/W2921149022","https://openalex.org/W1044727952","https://openalex.org/W3003393365","https://openalex.org/W2171845075","https://openalex.org/W1777852485","https://openalex.org/W1582003487","https://openalex.org/W1188123746","https://openalex.org/W2156848920","https://openalex.org/W2267745769"],"abstract_inverted_index":{"Using":[0],"FPGA-based":[1],"acceleration":[2],"of":[3,23,56,77,106,157],"high-performance":[4],"computing":[5],"(HPC)":[6],"applications":[7],"to":[8,20,112,126,196,225],"reduce":[9],"energy":[10,190],"and":[11,53,108,116,121,148,155,169,188],"power":[12],"consumption":[13],"is":[14],"becoming":[15],"an":[16,185,232],"interesting":[17],"option,":[18],"thanks":[19],"the":[21,78,93,104,153,219],"availability":[22],"high-level":[24],"synthesis":[25],"(HLS)":[26],"tools":[27],"that":[28,80,221],"enable":[29],"fast":[30],"design":[31,64,214],"cycles.":[32],"However,":[33],"obtaining":[34],"good":[35,54],"performance":[36,156,210],"for":[37,166,175,231],"memoryintensive":[38],"algorithms,":[39],"which":[40],"often":[41],"exchange":[42],"large":[43],"data":[44,70,146],"arrays":[45],"with":[46,194,211,218],"external":[47],"DRAM,":[48],"still":[49],"requires":[50],"timeconsuming":[51],"optimization":[52],"knowledge":[55],"hardware":[57],"design.":[58],"This":[59],"article":[60],"proposes":[61],"a":[62,167],"new":[63],"methodology,":[65],"based":[66],"on":[67,134,192],"dedicated":[68],"applicationand":[69],"array-specific":[71],"caches.":[72],"These":[73],"caches":[74,159,183],"provide":[75],"most":[76],"benefits":[79],"can":[81],"be":[82],"achieved":[83,184,208],"by":[84,90],"coding":[85],"optimized":[86,165,171,224],"DMA-like":[87],"transfer":[88],"strategies":[89],"hand":[91],"into":[92],"HPC":[94],"application":[95,127],"code,":[96],"but":[97],"require":[98,124],"only":[99,200],"limited":[100],"manual":[101],"tuning":[102],"(basically":[103],"selection":[105],"architecture":[107],"size),":[109],"are":[110],"neutral":[111],"target":[113],"HLS":[114],"tool":[115],"technology":[117],"(FPGA":[118],"or":[119],"ASIC),":[120],"do":[122],"not":[123],"changes":[125],"code.":[128],"We":[129,151],"show":[130],"experimental":[131],"results":[132],"obtained":[133],"five":[135],"common":[136],"memory-intensive":[137],"algorithms":[138],"from":[139],"very":[140],"diverse":[141],"domains,":[142],"namely":[143],"machine":[144],"learning,":[145],"sorting,":[147],"computer":[149],"vision.":[150],"test":[152],"cost":[154],"our":[158,182],"against":[160],"both":[161],"out-of-the-box":[162,197],"code":[163],"originally":[164],"GPU,":[168],"manually":[170,223],"implementations":[172],"specifically":[173,230],"targeted":[174],"FPGAs":[176],"via":[177],"HLS.":[178],"The":[179],"implementation":[180],"using":[181,199],"8X":[186],"speedup":[187],"2X":[189],"reduction":[191],"average":[193],"respect":[195],"models":[198],"simple":[201],"directive-based":[202],"optimizations":[203],"(e.g.,":[204],"pipelining).":[205],"They":[206],"also":[207],"comparable":[209],"much":[212],"less":[213],"effort":[215],"when":[216],"compared":[217],"versions":[220],"were":[222],"achieve":[226],"efficient":[227],"memory":[228],"transfers":[229],"FPGA.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}