{"id":"https://openalex.org/W7129097651","doi":"https://doi.org/10.1109/ccmcc67628.2025.11380528","title":"Design Space Exploration of a Direct Cached Memory Access Controller Optimized for HBM Memory Systems using TAPRE-HBM","display_name":"Design Space Exploration of a Direct Cached Memory Access Controller Optimized for HBM Memory Systems using TAPRE-HBM","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W7129097651","doi":"https://doi.org/10.1109/ccmcc67628.2025.11380528"},"language":null,"primary_location":{"id":"doi:10.1109/ccmcc67628.2025.11380528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccmcc67628.2025.11380528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Cross-Disciplinary Conference on Memory-Centric Computing (CCMCC)","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/A5039886741","display_name":"Gia Bao Thieu","orcid":"https://orcid.org/0000-0002-4045-3771"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gia Bao Thieu","raw_affiliation_strings":["Technische Universität Braunschweig,Chair for Chip Design for Embedded Computing,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Chair for Chip Design for Embedded Computing,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021970080","display_name":"Johannes Kn\u00f6dtel","orcid":"https://orcid.org/0000-0002-7298-8252"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Kn\u00f6dtel","raw_affiliation_strings":["University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany"],"affiliations":[{"raw_affiliation_string":"University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056696736","display_name":"Florian Rokohl","orcid":"https://orcid.org/0009-0001-6924-0585"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Rokohl","raw_affiliation_strings":["University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany"],"affiliations":[{"raw_affiliation_string":"University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014794132","display_name":"Marc Reichenbach","orcid":"https://orcid.org/0000-0002-9687-6247"},"institutions":[{"id":"https://openalex.org/I4665924","display_name":"University of Rostock","ror":"https://ror.org/03zdwsf69","country_code":"DE","type":"education","lineage":["https://openalex.org/I4665924"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Reichenbach","raw_affiliation_strings":["University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany"],"affiliations":[{"raw_affiliation_string":"University of Rostock,Institute of Applied Microelectronics and Computer Engineering,Germany","institution_ids":["https://openalex.org/I4665924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038123706","display_name":"Guillermo Pay\u00e1\u2013Vay\u00e1","orcid":"https://orcid.org/0000-0003-3503-8386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillermo Pay\u00e1-Vay\u00e1","raw_affiliation_strings":["Technische Universität Braunschweig,Chair for Chip Design for Embedded Computing,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Chair for Chip Design for Embedded Computing,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039886741"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80616851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9071999788284302,"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":0.9071999788284302,"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":0.043299999088048935,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.012799999676644802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.557200014591217},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5424000024795532},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.5156000256538391},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.5073999762535095},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4966000020503998},{"id":"https://openalex.org/keywords/cache-only-memory-architecture","display_name":"Cache-only memory architecture","score":0.49390000104904175},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.48899999260902405},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.45509999990463257},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.43380001187324524},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824400007724762},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.557200014591217},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5162000060081482},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.5156000256538391},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.5073999762535095},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.49390000104904175},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.43380001187324524},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.43160000443458557},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.35120001435279846},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.33640000224113464},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C152890283","wikidata":"https://www.wikidata.org/wiki/Q4129922","display_name":"Computing with Memory","level":5,"score":0.29899999499320984},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.2867000102996826},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C144240696","wikidata":"https://www.wikidata.org/wiki/Q367204","display_name":"Address space","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccmcc67628.2025.11380528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccmcc67628.2025.11380528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Cross-Disciplinary Conference on Memory-Centric Computing (CCMCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1791189328","https://openalex.org/W2135721541","https://openalex.org/W2622148586","https://openalex.org/W2962970995","https://openalex.org/W3013005428","https://openalex.org/W4221013715","https://openalex.org/W4285730081","https://openalex.org/W4291214133","https://openalex.org/W4380874786","https://openalex.org/W4386124159","https://openalex.org/W4386790141","https://openalex.org/W4390493789","https://openalex.org/W4392295490","https://openalex.org/W4409585609"],"related_works":[],"abstract_inverted_index":{"The":[0,206],"growth":[1],"of":[2,80,109,115,137,152,186],"artificial":[3],"intelligence":[4],"(AI)":[5],"applications":[6],"has":[7],"increased":[8],"the":[9,16,61,73,81,86,93,107,111,149,153,171,184,194,211,217],"demand":[10],"for":[11,98,198,216],"high-performance":[12],"computing":[13],"and":[14,76,102,166,221],"highlighted":[15],"critical":[17],"bottleneck":[18],"caused":[19],"by":[20,42,64,121],"slower":[21],"advances":[22],"in":[23,29],"memory":[24,39,103,117,138,223],"technologies":[25],"compared":[26],"to":[27,37,71,192,202,214],"those":[28],"computing.":[30],"This":[31],"paper":[32],"presents":[33],"a":[34,49,66,133,162,175,188,199],"comprehensive":[35],"approach":[36],"address":[38],"performance":[40,168,212],"challenges":[41],"integrating":[43],"High":[44],"Bandwidth":[45],"Memory":[46,54],"(HBM)":[47],"with":[48,161],"novel":[50],"multi-port":[51,156],"Direct":[52],"Cached":[53],"Access":[55],"(DCMA)":[56],"architecture":[57,151,196],"that":[58],"efficiently":[59],"leverages":[60],"HBM\u2019s":[62],"band-width":[63],"implementing":[65],"complex":[67],"parallel":[68],"cache":[69],"mechanism":[70],"exploit":[72],"inherent":[74],"spatial":[75],"temporal":[77],"data":[78,100],"locality":[79],"running":[82],"application.":[83],"However,":[84],"harnessing":[85],"proposed":[87,154],"DCMA\u2019s":[88],"full":[89],"potential":[90],"depends":[91],"on":[92,144,174],"application,":[94],"demanding":[95],"sophisticated":[96],"strategies":[97],"optimal":[99,195,207],"flow":[101],"access":[104],"management.":[105],"Therefore,":[106],"complexity":[108],"exploring":[110],"vast":[112],"parameter":[113],"space":[114,190],"such":[116],"architectures":[118],"is":[119],"addressed":[120],"employing":[122],"an":[123],"FPGA":[124,179],"emulation-based":[125],"rapid":[126],"prototyping":[127],"framework,":[128],"specifically":[129],"TAPRE-HBM,":[130],"which":[131],"provides":[132],"more":[134],"accurate":[135],"representation":[136],"behavior":[139],"through":[140],"direct":[141],"trace":[142],"processing":[143],"hardware.":[145],"Our":[146],"contributions":[147],"include":[148],"detailed":[150],"HBM-optimized,":[155],"DCMA":[157],"system,":[158],"its":[159],"integration":[160],"massive-parallel":[163],"vector":[164,219],"processor,":[165],"initial":[167],"evaluations":[169],"using":[170],"TAPRE-HBM":[172],"framework":[173],"Xilinx":[176],"Alveo":[177],"U55C":[178],"card.":[180],"Preliminary":[181],"results":[182],"show":[183],"importance":[185],"performing":[187],"design":[189],"exploration":[191],"choose":[193],"configuration":[197],"target":[200],"application":[201],"handle":[203],"memory-intensive":[204],"tasks.":[205],"choice":[208],"can":[209],"improve":[210],"up":[213],"32.8%":[215],"same":[218],"processor":[220],"HBM2":[222],"configuration.":[224]},"counts_by_year":[],"updated_date":"2026-02-18T06:20:13.636215","created_date":"2026-02-17T00:00:00"}