{"id":"https://openalex.org/W4417250114","doi":"https://doi.org/10.48550/arxiv.2504.07538","title":"A 950 MHz SIMT Soft Processor","display_name":"A 950 MHz SIMT Soft Processor","publication_year":2025,"publication_date":"2025-04-10","ids":{"openalex":"https://openalex.org/W4417250114","doi":"https://doi.org/10.48550/arxiv.2504.07538"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.07538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07538","pdf_url":"https://arxiv.org/pdf/2504.07538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.07538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082265695","display_name":"Martin Langhammer","orcid":"https://orcid.org/0000-0001-8206-2077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Langhammer, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067241056","display_name":"Gregg Baeckler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baeckler, Gregg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039454513","display_name":"Kim Bozman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bozman, Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.31540000438690186,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.31540000438690186,"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":0.22300000488758087,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.13770000636577606,"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/thread","display_name":"Thread (computing)","score":0.6955000162124634},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.6062999963760376},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.49639999866485596},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.4797999858856201},{"id":"https://openalex.org/keywords/digital-signal-processor","display_name":"Digital signal processor","score":0.46459999680519104},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.40119999647140503},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.39910000562667847},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.35569998621940613},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.3127000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985999941825867},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6955000162124634},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5554999709129333},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.4797999858856201},{"id":"https://openalex.org/C161611012","wikidata":"https://www.wikidata.org/wiki/Q106370","display_name":"Digital signal processor","level":3,"score":0.46459999680519104},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.39910000562667847},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.28040000796318054},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C22716491","wikidata":"https://www.wikidata.org/wiki/Q590170","display_name":"Clock gating","level":5,"score":0.2513999938964844},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C126298526","wikidata":"https://www.wikidata.org/wiki/Q189376","display_name":"Reduced instruction set computing","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.07538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07538","pdf_url":"https://arxiv.org/pdf/2504.07538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.07538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.07538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.07538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07538","pdf_url":"https://arxiv.org/pdf/2504.07538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417250114.pdf","grobid_xml":"https://content.openalex.org/works/W4417250114.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"modern":[1],"FPGAs":[2],"have":[3],"a":[4,8,59,74,106,112],"performance":[5],"potential":[6],"of":[7,28,47],"1":[9],"GHz":[10],"clock":[11,16,30],"frequency":[12],"-":[13,32],"with":[14,84,108],"both":[15],"networks":[17],"and":[18,24,87,94,111,123],"embedded":[19],"blocks":[20],"such":[21,50],"as":[22,51],"memories":[23],"DSP":[25,125],"Blocks":[26],"capable":[27],"these":[29],"rates":[31],"user":[33],"implementations":[34],"approaching":[35],"this":[36,55],"speed":[37],"are":[38],"rarely":[39],"realized":[40],"in":[41,66],"practice.":[42],"This":[43],"is":[44,73],"especially":[45],"true":[46],"complex":[48],"designs":[49],"soft":[52,60],"processors.":[53],"In":[54,103],"work":[56],"we":[57],"implement":[58],"GPGPU":[61],"which":[62],"exceeds":[63],"950":[64],"MHz":[65],"an":[67],"Altera":[68],"Agilex-7":[69],"FPGA.":[70],"The":[71],"architecture":[72],"32-bit":[75],"fixed":[76],"point":[77],"Single":[78],"Instruction,":[79],"Multiple":[80],"Thread":[81],"(SIMT)":[82],"design,":[83],"parameterized":[85],"thread":[86],"register":[88],"spaces.":[89],"Up":[90],"to":[91],"4096":[92],"threads":[93],"64K":[95],"registers":[96,110],"can":[97],"be":[98],"specified":[99],"by":[100],"the":[101],"user.":[102],"one":[104],"example,":[105],"processor":[107],"16K":[109],"16KB":[113],"shared":[114],"memory":[115],"required":[116],"approximately":[117],"7K":[118],"ALMs,":[119],"99":[120],"M20K":[121],"memories,":[122],"32":[124],"Blocks.":[126]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}
