{"id":"https://openalex.org/W7140442739","doi":"https://doi.org/10.1109/fpl68686.2025.00045","title":"Towards Instruction-Controlled In-Pipeline GEMM Acceleration in a Dual-Issue RISC-V Core for Edge Applications","display_name":"Towards Instruction-Controlled In-Pipeline GEMM Acceleration in a Dual-Issue RISC-V Core for Edge Applications","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W7140442739","doi":"https://doi.org/10.1109/fpl68686.2025.00045"},"language":null,"primary_location":{"id":"doi:10.1109/fpl68686.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl68686.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 35th International Conference on Field-Programmable Logic and Applications (FPL)","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/A5130660677","display_name":"Ahmad Othman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140143","display_name":"Dynamic Systems (United States)","ror":"https://ror.org/043vm9914","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140143"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmad Othman","raw_affiliation_strings":["Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany","institution_ids":["https://openalex.org/I4210140143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015211374","display_name":"Darmen Ilyas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140143","display_name":"Dynamic Systems (United States)","ror":"https://ror.org/043vm9914","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140143"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darmen Ilyas","raw_affiliation_strings":["Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany","institution_ids":["https://openalex.org/I4210140143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080510386","display_name":"Ahmed Kamaleldin","orcid":"https://orcid.org/0000-0002-7446-7741"},"institutions":[{"id":"https://openalex.org/I4210140143","display_name":"Dynamic Systems (United States)","ror":"https://ror.org/043vm9914","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140143"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Kamaleldin","raw_affiliation_strings":["Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany","institution_ids":["https://openalex.org/I4210140143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060626530","display_name":"Diana G\u00f6hringer","orcid":"https://orcid.org/0000-0003-2571-8441"},"institutions":[{"id":"https://openalex.org/I4210140143","display_name":"Dynamic Systems (United States)","ror":"https://ror.org/043vm9914","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140143"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana G\u00f6hringer","raw_affiliation_strings":["Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Adaptive Dynamic Systems,Technische Universit&#x00E4;t Dresden,Germany","institution_ids":["https://openalex.org/I4210140143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130660677"],"corresponding_institution_ids":["https://openalex.org/I4210140143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79262244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21549999713897705,"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":0.21549999713897705,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.15539999306201935,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.13920000195503235,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5983999967575073},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.46970000863075256},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4047999978065491},{"id":"https://openalex.org/keywords/displacement","display_name":"Displacement (psychology)","score":0.2833999991416931}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.4311999976634979},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40139999985694885},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpl68686.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl68686.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 35th International Conference on Field-Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7267161011695862,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G251804371","display_name":null,"funder_award_id":"16 ME 0433","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G821514941","display_name":null,"funder_award_id":"287022738","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1509422975","https://openalex.org/W2019254738","https://openalex.org/W2946048183","https://openalex.org/W4205954621","https://openalex.org/W4245302940","https://openalex.org/W4311995762","https://openalex.org/W4360831846","https://openalex.org/W4380874786","https://openalex.org/W4387886087","https://openalex.org/W4400224496","https://openalex.org/W4401210672","https://openalex.org/W4401568712","https://openalex.org/W4401753272","https://openalex.org/W4402196533","https://openalex.org/W4406265948","https://openalex.org/W4407578202","https://openalex.org/W4408151419","https://openalex.org/W4409568286"],"related_works":[],"abstract_inverted_index":{"GEMM":[0,50,73,97,164],"(General":[1],"Matrix":[2],"Multiplication)":[3],"is":[4,44],"a":[5,45,65],"fundamental":[6],"operation":[7],"in":[8],"deep":[9],"learning":[10],"(DL),":[11],"serving":[12],"as":[13,23],"the":[14,30,77,101,103,138,156,167,172],"key":[15],"computing":[16,38,182],"kernel":[17],"for":[18,48],"neural":[19],"network":[20],"layers,":[21],"such":[22],"convolutional":[24],"and":[25,58,85,92,108,117,133,177],"fully":[26],"connected":[27],"layers.":[28],"As":[29],"deployment":[31],"of":[32,112,149],"DL":[33],"models":[34],"expands":[35],"beyond":[36],"high-performance":[37],"to":[39,90],"resource-constrained":[40],"embedded":[41],"systems,":[42],"there":[43],"growing":[46],"demand":[47],"efficient":[49],"implementations":[51],"that":[52],"can":[53],"meet":[54],"strict":[55],"power":[56],"budgets":[57],"real-time":[59],"processing":[60],"requirements.":[61],"This":[62],"paper":[63],"introduces":[64],"dual-issue":[66],"in-order":[67],"RISC-V":[68],"core":[69,80,106],"with":[70],"an":[71,147],"inpipeline":[72],"accelerator":[74],"based":[75],"on":[76],"VeeR":[78,158],"EH1":[79,159],"[13],":[81],"eliminating":[82],"control":[83],"signals":[84],"data":[86],"transfer":[87],"overhead":[88],"inherent":[89],"coprocessors":[91],"standalone":[93],"accelerators.":[94],"By":[95,162],"integrating":[96,163],"execution":[98],"directly":[99],"into":[100],"pipeline,":[102,168],"design":[104],"leverages":[105],"utilization":[107],"enables":[109],"compiler-time":[110],"preloading":[111],"operands,":[113],"streamlining":[114],"memory":[115,130],"access":[116,131],"reducing":[118],"dynamic":[119],"branching,":[120],"thereby":[121,136],"minimizing":[122],"branch":[123],"mispredictions.":[124],"Further,":[125],"pipelined":[126],"load/store":[127],"operations":[128],"mitigate":[129],"stalls":[132],"cache":[134],"misses,":[135],"enhancing":[137],"pipeline":[139],"throughput.":[140],"Speedup,":[141],"measured":[142],"using":[143],"Verilator":[144],"simulation,":[145],"demonstrates":[146],"average":[148],"<tex":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\sim":[152],"5":[153],"\\times$</tex>":[154],"over":[155],"reference":[157],"baseline":[160],"core.":[161],"acceleration":[165],"within":[166],"this":[169],"work":[170],"bridges":[171],"gap":[173],"between":[174],"domain-specific":[175],"accelerators":[176],"general-purpose":[178],"cores,":[179],"delivering":[180],"scalable":[181],"performance.":[183]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-27T00:00:00"}