{"id":"https://openalex.org/W7131099373","doi":"https://doi.org/10.1016/j.sysarc.2026.103736","title":"Integrating an open-source soft-GPU overlay with RISC-V control and high-bandwidth memory","display_name":"Integrating an open-source soft-GPU overlay with RISC-V control and high-bandwidth memory","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W7131099373","doi":"https://doi.org/10.1016/j.sysarc.2026.103736"},"language":"en","primary_location":{"id":"doi:10.1016/j.sysarc.2026.103736","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.103736","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.sysarc.2026.103736","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126605064","display_name":"Hector Gerardo Mu\u00f1oz Hernandez","orcid":null},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hector Gerardo Mu\u00f1oz Hernandez","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126638613","display_name":"Mahdi Taheri","orcid":null},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]},{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE","EE"],"is_corresponding":false,"raw_author_name":"Mahdi Taheri","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","Tallinn University of Technology, Tallinn, Estonia"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]},{"raw_affiliation_string":"Tallinn University of Technology, Tallinn, Estonia","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126659047","display_name":"Muhammad Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165059","display_name":"Hochschule f\u00fcr Technik und Wirtschaft Dresden \u2013 University of Applied Sciences","ror":"https://ror.org/05q5pk319","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210165059"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Muhammad Ali","raw_affiliation_strings":["University of Technology Dresden, Mommsenstra\u00dfe 9, Dresden, 01069, Germany"],"affiliations":[{"raw_affiliation_string":"University of Technology Dresden, Mommsenstra\u00dfe 9, Dresden, 01069, Germany","institution_ids":["https://openalex.org/I4210165059","https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037788474","display_name":"Keyvan Shahin","orcid":"https://orcid.org/0000-0002-6694-2821"},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Keyvan Shahin","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126599176","display_name":"Alireza Syavashi","orcid":null},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alireza Syavashi","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060626530","display_name":"Diana G\u00f6hringer","orcid":"https://orcid.org/0000-0003-2571-8441"},"institutions":[{"id":"https://openalex.org/I4210165059","display_name":"Hochschule f\u00fcr Technik und Wirtschaft Dresden \u2013 University of Applied Sciences","ror":"https://ror.org/05q5pk319","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210165059"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Diana G\u00f6hringer","raw_affiliation_strings":["University of Technology Dresden, Mommsenstra\u00dfe 9, Dresden, 01069, Germany"],"affiliations":[{"raw_affiliation_string":"University of Technology Dresden, Mommsenstra\u00dfe 9, Dresden, 01069, Germany","institution_ids":["https://openalex.org/I4210165059","https://openalex.org/I78650965"]}]},{"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/I4210098611","display_name":"Hanseatic University Rostock","ror":"https://ror.org/013kf9t32","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210098611"]},{"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, Pressestelle, Rostock, 18051, Germany"],"affiliations":[{"raw_affiliation_string":"University of Rostock, Pressestelle, Rostock, 18051, Germany","institution_ids":["https://openalex.org/I4665924","https://openalex.org/I4210098611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048500216","display_name":"Christian Herglotz","orcid":"https://orcid.org/0000-0001-8975-0171"},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Herglotz","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126607355","display_name":"Michael H\u00fcbner","orcid":null},"institutions":[{"id":"https://openalex.org/I51783024","display_name":"Brandenburg University of Technology Cottbus-Senftenberg","ror":"https://ror.org/02wxx3e24","country_code":"DE","type":"education","lineage":["https://openalex.org/I51783024"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael H\u00fcbner","raw_affiliation_strings":["Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany"],"affiliations":[{"raw_affiliation_string":"Brandenburg Techhnology University Cottbus-Senftenberg, Platz der Deutschen Einheit 1, Cottbus, 03046, Germany","institution_ids":["https://openalex.org/I51783024"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5126605064"],"corresponding_institution_ids":["https://openalex.org/I51783024"],"apc_list":{"value":2800,"currency":"USD","value_usd":2800},"apc_paid":{"value":2800,"currency":"USD","value_usd":2800},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34911433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"175","issue":null,"first_page":"103736","last_page":"103736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6582000255584717,"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":0.6582000255584717,"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":0.149399995803833,"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":0.03799999877810478,"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/overlay","display_name":"Overlay","score":0.6855999827384949},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.545799970626831},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.539900004863739},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5185999870300293},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44519999623298645},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42320001125335693},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.35359999537467957},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3269999921321869},{"id":"https://openalex.org/keywords/direct-memory-access","display_name":"Direct memory access","score":0.3151000142097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690999746322632},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.6855999827384949},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44519999623298645},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C37724790","wikidata":"https://www.wikidata.org/wiki/Q210813","display_name":"Direct memory access","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C161611012","wikidata":"https://www.wikidata.org/wiki/Q106370","display_name":"Digital signal processor","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C10597312","wikidata":"https://www.wikidata.org/wiki/Q5473302","display_name":"Forwarding plane","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.sysarc.2026.103736","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.103736","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.sysarc.2026.103736","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.103736","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7363054752349854,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2936567838","https://openalex.org/W2963255460","https://openalex.org/W3207700054","https://openalex.org/W3213990125","https://openalex.org/W4405838333"],"related_works":[],"abstract_inverted_index":{"Image":[0],"and":[1,16,25,70,96,102,121,147,164,181,187],"signal":[2,103],"processing":[3,104],"workloads":[4,142],"are":[5],"widely":[6],"deployed":[7],"on":[8,17,31,43,83,169,174],"Graphics":[9],"Processing":[10],"Units":[11],"(GPUs)":[12],"for":[13,22,184],"high":[14],"throughput":[15,146],"Field-Programmable":[18],"Gate":[19],"Arrays":[20],"(FPGAs)":[21],"hardware":[23],"specialization":[24],"energy":[26],"efficiency.":[27],"Soft":[28],"GPU":[29],"overlays":[30],"FPGAs":[32],"aim":[33],"to":[34,63],"combine":[35],"these":[36,158],"advantages,":[37],"yet":[38],"existing":[39],"solutions":[40],"often":[41],"depend":[42],"fixed":[44],"hard":[45,88,126,175],"processors":[46],"or":[47],"impose":[48],"platform":[49],"constraints":[50],"that":[51,161],"limit":[52],"portability.":[53],"This":[54],"work":[55],"extends":[56],"a":[57,65,87,116,125,179],"popular":[58],"open-source":[59],"soft":[60,66,107,118],"GPGPU":[61,108],"overlay":[62],"integrate":[64],"RISC-V":[67,119],"control":[68],"plane":[69],"enable":[71],"compatibility":[72],"with":[73,153],"High-Bandwidth":[74],"Memory":[75],"(HBM2).":[76],"The":[77],"resulting":[78],"system":[79,94],"can":[80,166],"be":[81,167],"instantiated":[82],"FPGA":[84,135],"boards":[85],"without":[86,172],"ARM":[89,127],"processor,":[90],"improving":[91],"portability,":[92],"simplifying":[93],"integration,":[95],"broadening":[97],"deployability.":[98],"Across":[99],"representative":[100],"image":[101],"kernels,":[105],"the":[106,149],"achieves":[109],"geometric-mean":[110],"speedups":[111],"of":[112],"114.60":[113],"\u00d7":[114,123],"over":[115,124],"scalar":[117],"core":[120],"19.72":[122],"core,":[128],"demonstrating":[129],"substantial":[130],"performance":[131,150,165],"benefits":[132,140],"while":[133],"retaining":[134],"reconfigurability.":[136],"HBM2":[137],"integration":[138],"further":[139],"bandwidth-sensitive":[141],"by":[143],"increasing":[144],"sustained":[145],"reducing":[148],"bottlenecks":[151],"associated":[152],"off-chip":[154],"memory":[155],"access.":[156],"Collectively,":[157],"results":[159],"indicate":[160],"GPU-like":[162],"programmability":[163],"delivered":[168],"reconfigurable":[170],"platforms":[171],"reliance":[173],"CPU":[176],"subsystems,":[177],"providing":[178],"portable":[180],"scalable":[182],"foundation":[183],"embedded":[185],"vision":[186],"DSP":[188],"acceleration.":[189]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-24T00:00:00"}
