{"id":"https://openalex.org/W7128065446","doi":"https://doi.org/10.1145/3748173.3779190","title":"Hardware Accelerated FPGA Divide-and-Conquer Page Placement in Milliseconds","display_name":"Hardware Accelerated FPGA Divide-and-Conquer Page Placement in Milliseconds","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7128065446","doi":"https://doi.org/10.1145/3748173.3779190"},"language":null,"primary_location":{"id":"doi:10.1145/3748173.3779190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748173.3779190","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748173.3779190","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066752111","display_name":"Ezra Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ezra Thomas","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125102092","display_name":"Jing (Jane) Li","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087585086","display_name":"Andr\u00e9 DeHon","orcid":"https://orcid.org/0000-0001-9177-7699"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 DeHon","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066752111"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24186795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.44359999895095825,"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":0.44359999895095825,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.41830000281333923,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.023900000378489494,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/speedup","display_name":"Speedup","score":0.8240000009536743},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.781499981880188},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7005000114440918},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6718999743461609},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6247000098228455},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.6037999987602234},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8240000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091999888420105},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.781499981880188},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6718999743461609},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6247000098228455},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4077000021934509},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.3544999957084656},{"id":"https://openalex.org/C60327585","wikidata":"https://www.wikidata.org/wiki/Q723733","display_name":"Millisecond","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C203864433","wikidata":"https://www.wikidata.org/wiki/Q5426992","display_name":"FPGA prototype","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C127879752","wikidata":"https://www.wikidata.org/wiki/Q3390760","display_name":"Place and route","level":3,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748173.3779190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748173.3779190","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3748173.3779190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748173.3779190","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1978599303","https://openalex.org/W2015501954","https://openalex.org/W2064997970","https://openalex.org/W2075137913","https://openalex.org/W2100412947","https://openalex.org/W2113212295","https://openalex.org/W2114820519","https://openalex.org/W2138206217","https://openalex.org/W2766697190","https://openalex.org/W2788211964","https://openalex.org/W2794057135","https://openalex.org/W2912012512","https://openalex.org/W2918037051","https://openalex.org/W2925849311","https://openalex.org/W2989034947","https://openalex.org/W3004158308","https://openalex.org/W3008065314","https://openalex.org/W3125127664","https://openalex.org/W4211022608","https://openalex.org/W4212918377","https://openalex.org/W4214669391","https://openalex.org/W4234189062","https://openalex.org/W4312037452","https://openalex.org/W4393576218","https://openalex.org/W4393577071","https://openalex.org/W4410344137","https://openalex.org/W4413078307"],"related_works":[],"abstract_inverted_index":{"Excessive":[0],"FPGA":[1,55,155],"compilation":[2,34],"times,":[3],"often":[4],"measured":[5],"in":[6,60,129],"hours,":[7],"stifle":[8],"rapid":[9],"iterative":[10],"development,":[11],"design-space":[12],"exploration,":[13],"and":[14,75,107],"runtime":[15],"reconfiguration":[16],"applications.":[17],"Coarse-grain":[18],"divide-and-conquer":[19,101],"techniques,":[20],"which":[21],"break":[22],"large":[23],"applications":[24],"into":[25],"separately":[26],"compiled":[27],"pages,":[28],"offer":[29],"moderate":[30],"speedups,":[31],"potentially":[32],"bringing":[33],"down":[35],"to":[36,72],"minutes,":[37],"but":[38],"leave":[39],"significant":[40],"fine-grain":[41,65],"parallelism":[42],"opportunities":[43],"untapped.":[44],"Systolic-array-based":[45],"accelerators":[46],"have":[47],"previously":[48],"offered":[49],"orders":[50,114],"of":[51,77,99,104,115,145],"magnitude":[52,116],"speedup":[53,117],"for":[54,79],"placement":[56,96],"(a":[57],"major":[58],"bottleneck":[59],"compilation),":[61],"by":[62],"exploiting":[63],"massive":[64],"parallelism,":[66],"however":[67],"poor":[68],"scalability":[69],"restricts":[70],"them":[71],"small":[73],"designs,":[74,137],"lack":[76],"support":[78],"modern":[80,123],"heterogeneous":[81],"netlists":[82,103],"(CLBs,":[83],"BRAMs,":[84,106],"DSPs)":[85],"prevents":[86],"their":[87],"use":[88],"today.":[89],"We":[90,126],"introduce":[91],"an":[92,140],"enhanced,":[93],"FPGA-based":[94],"systolic":[95,147],"accelerator,":[97],"capable":[98],"placing":[100],"page-sized":[102],"CLBs,":[105],"DSPs":[108],"onto":[109],"VTR":[110],"architectures,":[111],"with":[112],"2-3":[113],"over":[118],"VTR-9":[119],"running":[120],"on":[121,131,139],"a":[122,150],"workstation-class":[124],"processor.":[125],"demonstrate":[127],"page-placement":[128],"milliseconds":[130],"realistic":[132],"benchmarks,":[133],"including":[134],"HLS":[135],"dataflow":[136],"run":[138],"AMD":[141],"Versal":[142],"VCK190":[143],"implementation":[144],"our":[146],"placer,":[148],"forging":[149],"path":[151],"towards":[152],"real-time,":[153],"self-hosted":[154],"compilation.":[156]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-07T00:00:00"}