{"id":"https://openalex.org/W4396686371","doi":"https://doi.org/10.1145/3629527.3651428","title":"Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs","display_name":"Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396686371","doi":"https://doi.org/10.1145/3629527.3651428"},"language":"en","primary_location":{"id":"doi:10.1145/3629527.3651428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651428","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651428","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651428","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwu Peng","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0000-0003-2025-2195","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut, Storrs, CT, USA"],"raw_orcid":"https://orcid.org/0000-0003-0891-1231","affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078443672","display_name":"Tong Geng","orcid":"https://orcid.org/0000-0002-3644-2922"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Geng","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-3644-2922","affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016440514","display_name":"Sutanay Choudhury","orcid":"https://orcid.org/0000-0001-7352-2035"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sutanay Choudhury","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7352-2035","affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062469","display_name":"Kevin Barker","orcid":"https://orcid.org/0000-0003-4947-0559"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Barker","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4947-0559","affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3734-9137","affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9980999827384949,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9977999925613403,"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/dataflow","display_name":"Dataflow","score":0.897436261177063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485040426254272},{"id":"https://openalex.org/keywords/von-neumann-architecture","display_name":"Von Neumann architecture","score":0.5843853950500488},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5560339689254761},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4501693546772003},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4400365948677063},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4226996600627899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4056752026081085},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3620772957801819},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3413166105747223},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2473313808441162},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09872227907180786}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.897436261177063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485040426254272},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.5843853950500488},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5560339689254761},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4501693546772003},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4400365948677063},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4226996600627899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4056752026081085},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3620772957801819},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3413166105747223},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2473313808441162},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09872227907180786},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3629527.3651428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651428","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651428","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3629527.3651428","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3651428","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3651428","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.49000000953674316,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396686371.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2045271686","https://openalex.org/W2120230074","https://openalex.org/W2167956099","https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2798482398","https://openalex.org/W2799537975","https://openalex.org/W2963163009","https://openalex.org/W4220662607"],"related_works":["https://openalex.org/W274974089","https://openalex.org/W2100092435","https://openalex.org/W4255768083","https://openalex.org/W2119534391","https://openalex.org/W2503137108","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2765743988","https://openalex.org/W2062253548","https://openalex.org/W2393490604"],"abstract_inverted_index":{"The":[0],"relentless":[1],"advancement":[2],"of":[3,15,20,43,54],"artificial":[4],"intelligence":[5],"(AI)":[6],"and":[7,25,68,82,92],"machine":[8],"learning":[9],"(ML)":[10],"applications":[11],"necessitates":[12],"the":[13,22,33,41,52,57],"development":[14],"specialized":[16],"hardware":[17,73],"accelerators":[18,55,74],"capable":[19],"handling":[21],"increasing":[23],"complexity":[24],"computational":[26],"demands.":[27],"Traditional":[28],"computing":[29],"architectures,":[30],"based":[31],"on":[32],"von":[34],"Neumann":[35],"model,":[36],"are":[37,75],"being":[38],"outstripped":[39],"by":[40,77],"requirements":[42],"contemporary":[44],"AI/ML":[45,96],"algorithms,":[46],"leading":[47],"to":[48,88],"a":[49],"surge":[50],"in":[51],"creation":[53],"like":[56],"Graphcore":[58],"Intelligence":[59],"Processing":[60],"Unit":[61,66],"(IPU),":[62],"Sambanova":[63],"Reconfigurable":[64],"Dataflow":[65],"(RDU),":[67],"enhanced":[69],"GPU":[70],"platforms.":[71],"These":[72],"characterized":[76],"their":[78],"innovative":[79],"data-flow":[80],"architectures":[81],"other":[83],"design":[84],"optimizations":[85],"that":[86],"promise":[87],"deliver":[89],"superior":[90],"performance":[91],"energy":[93],"efficiency":[94],"for":[95],"tasks.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}