{"id":"https://openalex.org/W2076066374","doi":"https://doi.org/10.1145/2684746.2689147","title":"Customizable and High Performance Matrix Multiplication Kernel on FPGA (Abstract Only)","display_name":"Customizable and High Performance Matrix Multiplication Kernel on FPGA (Abstract Only)","publication_year":2015,"publication_date":"2015-02-10","ids":{"openalex":"https://openalex.org/W2076066374","doi":"https://doi.org/10.1145/2684746.2689147","mag":"2076066374"},"language":"en","primary_location":{"id":"doi:10.1145/2684746.2689147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2684746.2689147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5106290765","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-9937-2351"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["University of California at Los Angeles, Los Angeles, USA","University of California at Los Angeles, Los Angeles, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California at Los Angeles, Los Angeles, USA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106290765"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.323,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59673786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9975000023841858,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9934999942779541,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.835976243019104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544771432876587},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6857737898826599},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6612175703048706},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6455562114715576},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6074739694595337},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5851691961288452},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4542520344257355},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4534003436565399},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4291115999221802},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42855730652809143},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36961525678634644},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3433286249637604},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11318507790565491}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.835976243019104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544771432876587},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6857737898826599},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6612175703048706},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6455562114715576},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6074739694595337},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5851691961288452},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4542520344257355},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4534003436565399},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4291115999221802},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42855730652809143},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36961525678634644},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3433286249637604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11318507790565491},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2684746.2689147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2684746.2689147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W1970548269","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Matrix":[0],"multiplication":[1],"(MM)":[2],"is":[3],"an":[4],"important":[5],"kernel":[6],"in":[7],"many":[8],"application":[9],"domains,":[10],"including":[11],"scientific":[12],"computing,":[13],"image":[14],"processing,":[15],"machine":[16],"learning,":[17],"etc.":[18],"Numerous":[19],"accelerator":[20,39,108],"designs":[21],"have":[22],"been":[23],"proposed":[24],"for":[25,84],"higher":[26],"throughput":[27,59],"and":[28,64],"energy":[29],"efficiency.":[30],"In":[31],"this":[32],"paper":[33],"we":[34,89],"present":[35],"a":[36,46,76],"customizable":[37],"FPGA":[38,66,107],"of":[40],"matrix":[41,62],"multiplication.":[42],"We":[43],"also":[44],"develop":[45],"design":[47,54,109],"automation":[48],"flow":[49],"to":[50],"generate":[51],"the":[52,57,61,98],"optimal":[53],"configuration":[55],"with":[56,72],"highest":[58],"given":[60],"size":[63],"target":[65],"platform.":[67],"It":[68],"can":[69,90],"be":[70],"integrated":[71],"HLS":[73],"tools":[74],"as":[75,92,94],"basic":[77],"parameterizable":[78],"library":[79],"component.":[80],"Experiments":[81],"show":[82],"that":[83],"512\u00d7512":[85],"single":[86],"precision":[87],"MM,":[88],"achieve":[91],"high":[93],"358":[95],"GFLOPs":[96],"on":[97],"Xilinx":[99],"Virtix-7":[100],"XC7VX485T-2,":[101],"which":[102],"outperforms":[103],"any":[104],"published":[105],"state-of-the-art":[106],"by":[110],"at":[111],"least":[112],"28.3%.":[113]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}