{"id":"https://openalex.org/W7148594380","doi":"https://doi.org/10.1109/hipcw66559.2025.00025","title":"Performance Evaluation of AI Inference on the Tenstorrent Wormhole RISC-V Accelerator","display_name":"Performance Evaluation of AI Inference on the Tenstorrent Wormhole RISC-V Accelerator","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7148594380","doi":"https://doi.org/10.1109/hipcw66559.2025.00025"},"language":null,"primary_location":{"id":"doi:10.1109/hipcw66559.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5123441854","display_name":"Kishor Yerol Damodaran","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kishor Yerol Damodaran","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064282205","display_name":"Abhishek N. Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Patel","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102568316","display_name":"Krishan Gopal Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishan Gopal Gupta","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103511695","display_name":"Shashank Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashank Sharma","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042337736","display_name":"Samrit Kumar Maity","orcid":"https://orcid.org/0000-0002-4050-9624"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Samrit Kumar Maity","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081038961","display_name":"Sanjay Wandhekar","orcid":"https://orcid.org/0000-0001-9618-4411"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjay Wandhekar","raw_affiliation_strings":["C-DAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C-DAC,India","institution_ids":["https://openalex.org/I1331500379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1331500379"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69316375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.08739999681711197,"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":0.08739999681711197,"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/T10951","display_name":"Cryptographic Implementations and Security","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.021700000390410423,"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/inference","display_name":"Inference","score":0.4332999885082245},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2782000005245209},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2678000032901764},{"id":"https://openalex.org/keywords/wormhole","display_name":"Wormhole","score":0.24699999392032623},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2418999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406999945640564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C29013271","wikidata":"https://www.wikidata.org/wiki/Q7544","display_name":"Wormhole","level":2,"score":0.24699999392032623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2418999969959259},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.23639999330043793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22439999878406525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw66559.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W3013692244","https://openalex.org/W3135242540","https://openalex.org/W4380874786","https://openalex.org/W4385199915","https://openalex.org/W4402475821","https://openalex.org/W4406171852","https://openalex.org/W4416003955"],"related_works":[],"abstract_inverted_index":{"The":[0,93],"growing":[1],"computational":[2],"demands":[3],"of":[4,22,28,64,148],"large-scale":[5],"AI":[6,38,156],"inference":[7,77,142],"have":[8],"shifted":[9],"performance":[10,62],"bottlenecks":[11],"from":[12],"algorithms":[13],"to":[14],"hardware,":[15],"underscoring":[16],"the":[17,65,103,111,120,127,146],"need":[18],"for":[19,36,151],"systematic":[20],"evaluation":[21,63],"accelerator":[23],"efficiency.":[24,92],"Consequently,":[25],"architectural":[26],"analysis":[27],"performance,":[29,143],"scalability,":[30],"and":[31,46,54,73,90,98,106,140],"energy":[32,91],"efficiency":[33],"is":[34],"critical":[35],"sustainable":[37],"deployment.":[39],"Existing":[40],"evaluations":[41],"predominantly":[42],"target":[43],"proprietary":[44],"GPU":[45],"TPU":[47],"platforms,":[48],"leaving":[49],"limited":[50],"insight":[51],"into":[52],"open":[53],"customizable":[55],"alternatives.":[56],"This":[57],"study":[58],"presents":[59],"a":[60],"cross-domain":[61],"RISC-V\u2013based":[66],"Tenstorrent":[67],"Wormhole":[68],"n300":[69],"across":[70,82],"vision":[71,94],"(ResNet-50)":[72],"language":[74,112],"(Llama-1B\u20138B,":[75],"Qwen-7B)":[76],"workloads.":[78,157],"Experiments":[79],"were":[80],"analyzed":[81],"four":[83],"quantitative":[84],"metrics:":[85],"throughput,":[86],"latency,":[87],"scaling":[88],"efficiency,":[89],"model":[95,113],"achieved":[96,114],"6.3\u00d7":[97],"4.9\u00d7":[99],"higher":[100,124],"throughput":[101,117],"than":[102,126],"Grayskull":[104],"e150":[105],"RTX":[107],"A4000,":[108],"respectively,":[109],"while":[110,144],"comparable":[115],"GPU-class":[116],"at":[118],"one-third":[119],"power,":[121],"delivering":[122],"3.5\u00d7":[123],"throughput-per-cost":[125],"H100":[128],"PCIe":[129],"GPU.":[130],"These":[131],"findings":[132],"demonstrate":[133],"that":[134],"RISC-V":[135],"accelerators":[136],"can":[137],"deliver":[138],"competitive":[139],"cost-efficient":[141],"highlighting":[145],"importance":[147],"software-stack":[149],"maturity":[150],"broader":[152],"adoption":[153],"in":[154],"HPC":[155]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-03T00:00:00"}