{"id":"https://openalex.org/W4415517262","doi":"https://doi.org/10.1145/3773041","title":"Exploring Microscaling MX Minifloat Systolic Arrays on\u00a0FPGAs","display_name":"Exploring Microscaling MX Minifloat Systolic Arrays on\u00a0FPGAs","publication_year":2025,"publication_date":"2025-10-24","ids":{"openalex":"https://openalex.org/W4415517262","doi":"https://doi.org/10.1145/3773041"},"language":"en","primary_location":{"id":"doi:10.1145/3773041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773041","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-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/A5120124359","display_name":"Abdurauf Abdurakhmanov","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Abdurauf Abdurakhmanov","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","King Abdullah University of Science and Technology (KAUST), Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032556461","display_name":"Suhaib A. Fahmy","orcid":"https://orcid.org/0000-0003-0568-5048"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Suhaib A. Fahmy","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","King Abdullah University of Science and Technology (KAUST), Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120124359"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31884902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"4","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11737","display_name":"Advanced Materials and Mechanics","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11737","display_name":"Advanced Materials and Mechanics","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11527","display_name":"3D IC and TSV technologies","score":0.9779999852180481,"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/T11301","display_name":"Advanced Surface Polishing Techniques","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.7318999767303467},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.5907999873161316},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5748000144958496},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5275999903678894},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424000144004822},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7318999767303467},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.5907999873161316},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5748000144958496},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5175999999046326},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773041","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-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/W2044610542","https://openalex.org/W2133757342","https://openalex.org/W2303128970","https://openalex.org/W2554943000","https://openalex.org/W3023230498","https://openalex.org/W3152567310","https://openalex.org/W3216547854","https://openalex.org/W4362510878","https://openalex.org/W4387294240","https://openalex.org/W4393949386","https://openalex.org/W4400315128","https://openalex.org/W4403278766","https://openalex.org/W4405022468","https://openalex.org/W6910456049"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,9,16,66,81,87,120],"generative":[4],"AI":[5],"and":[6,84,97,104,125,133],"exponential":[7],"growth":[8],"model":[10],"parameters":[11],"has":[12],"driven":[13],"the":[14,41,47,63,82],"pursuit":[15],"alternative":[17],"arithmetic":[18],"formats":[19,35,44,73],"to":[20,30],"enhance":[21],"efficiency":[22],"while":[23,107],"maintaining":[24,108],"inference":[25],"accuracy.":[26],"While":[27],"earlier":[28],"efforts":[29],"implement":[31],"small":[32],"floating":[33],"point":[34],"(minifloats)":[36],"have":[37],"been":[38],"somewhat":[39],"ad-hoc,":[40],"Microscaling":[42,71],"MX":[43,72,99],"proposed":[45],"by":[46],"Open":[48],"Compute":[49],"Project":[50],"offer":[51],"a":[52,78,117],"standard":[53],"around":[54],"which":[55],"hardware":[56],"designers":[57],"can":[58],"converge.":[59],"This":[60],"article":[61],"explores":[62],"design":[64,115],"space":[65],"systolic":[67,88],"array":[68],"architectures":[69],"for":[70,95,130],"on":[74,91],"FPGAs.":[75],"It":[76],"provides":[77],"detailed":[79],"analysis":[80],"area":[83],"timing":[85],"characteristics":[86],"arrays":[89],"implemented":[90],"AMD":[92],"UltraScale+":[93],"FPGAs":[94],"6-bit":[96],"8-bit":[98],"formats,":[100],"exploring":[101],"different":[102],"accumulation":[103,129],"pipelining":[105],"strategies":[106],"high":[109],"computational":[110],"throughput.":[111],"Our":[112],"most":[113],"optimized":[114],"reaches":[116],"peak":[118],"throughput":[119],"568":[121],"GOPS":[122],"using":[123],"4-stage":[124],"3-stage":[126],"pipelined":[127],"Exact":[128],"MXFP6":[131],"E3M2":[132],"E2M3,":[134],"respectively.":[135]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}