{"id":"https://openalex.org/W4413145118","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00023","title":"Benchmarking Floating Point Performance of Massively Parallel Dataflow Overlays on AMD Versal Compute Primitives","display_name":"Benchmarking Floating Point Performance of Massively Parallel Dataflow Overlays on AMD Versal Compute Primitives","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413145118","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00023"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","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/A5106662583","display_name":"Mohamed Bouaziz","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":"Mohamed Bouaziz","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Thuwal,Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Thuwal,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"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106662583"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":1.6028,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86995289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9966999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9966999888420105,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9918000102043152,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9858999848365784,"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/dataflow","display_name":"Dataflow","score":0.8939794301986694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.799950122833252},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7352294921875},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6321231126785278},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5840624570846558},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.5695571303367615},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4859010577201843},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4719594717025757},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32040897011756897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07826927304267883}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8939794301986694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799950122833252},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7352294921875},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6321231126785278},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5840624570846558},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.5695571303367615},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4859010577201843},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4719594717025757},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32040897011756897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07826927304267883},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2293118914","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967"],"abstract_inverted_index":{"Many":[0],"massively":[1,113,129],"parallel":[2,114,130],"applications":[3],"require":[4],"floating-point":[5],"(FP)":[6],"precision,":[7],"necessitating":[8],"specialized":[9],"hardware":[10],"support.":[11],"Novel":[12],"Reconfigurable":[13,20],"Dataflow":[14],"Accelerators":[15],"(RDAs)":[16],"and":[17,85,100],"Coarse":[18],"Grained":[19],"Arrays":[21],"(CGRAs)":[22],"like":[23],"the":[24,53,96,103,106,121],"AMD":[25,35,109],"Versal":[26,36],"AI":[27,40,126],"Engine":[28,41],"Array":[29],"can":[30,123],"implement":[31],"optimized":[32],"datapaths.":[33],"The":[34],"FPGA":[37],"family":[38],"integrates":[39],"cores":[42],"for":[43,56,112],"vector":[44],"FP":[45],"operations":[46],"as":[47,49],"well":[48],"DSP58":[50,104,122],"primitives":[51],"in":[52,58,128],"programmable":[54,125],"logic":[55],"use":[57],"fine-grained":[59],"architectures.":[60],"Configurability":[61],"at":[62],"these":[63,87],"levels":[64],"involves":[65],"factors,":[66],"particularly":[67],"data":[68],"movement,":[69],"that":[70,120],"complicate":[71],"measuring":[72],"empirical":[73],"compute":[74],"performance":[75,101],"limits.":[76,88],"This":[77],"paper":[78],"presents":[79],"an":[80],"architectural":[81],"model":[82],"to":[83],"isolate":[84],"measure":[86],"Using":[89],"this":[90],"model,":[91],"we":[92],"compare":[93],"resources,":[94],"showing":[95],"superior":[97],"operator":[98],"density":[99],"of":[102],"over":[105],"previous":[107],"generation":[108],"UltraScale+":[110],"DSP48E2":[111],"dataflow":[115],"overlays.":[116],"We":[117],"also":[118],"show":[119],"outperform":[124],"Engines":[127],"feedforward":[131],"applications.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
