{"id":"https://openalex.org/W7164197384","doi":"https://doi.org/10.1109/fccm68464.2026.00064","title":"HAMG: A Hierarchical Automated MemTile-based GEMM Accelerator for Versal AIE-ML","display_name":"HAMG: A Hierarchical Automated MemTile-based GEMM Accelerator for Versal AIE-ML","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7164197384","doi":"https://doi.org/10.1109/fccm68464.2026.00064"},"language":null,"primary_location":{"id":"doi:10.1109/fccm68464.2026.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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/A5138380715","display_name":"Kai Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Shao","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013225839","display_name":"Erwei Wang","orcid":"https://orcid.org/0000-0002-3603-6852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erwei Wang","raw_affiliation_strings":["AMD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138357141","display_name":"He Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95038106,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10930000245571136,"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":0.10930000245571136,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.042399998754262924,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.028599999845027924,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.26030001044273376},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2596000134944916},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2556000053882599},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.23909999430179596},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.2272000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309000253677368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2410999983549118},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.23909999430179596},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2272000014781952},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.22339999675750732}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm68464.2026.00064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4410810249","https://openalex.org/W7124680514","https://openalex.org/W7140373340"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"GEMM":[1],"on":[2],"AMD":[3],"Versal":[4],"AIE-ML":[5],"requires":[6],"careful":[7],"coordination":[8],"among":[9],"AI":[10],"Engines,":[11],"MemTiles,":[12],"and":[13,46],"PL-side":[14],"BRAM/URAM":[15],"under":[16],"tight":[17],"off-chip":[18],"bandwidth":[19],"limits.":[20],"We":[21],"present":[22],"HAMG,":[23],"an":[24],"automated":[25],"generator":[26],"that":[27],"constructs":[28],"a":[29,57],"three-level":[30],"memory":[31],"hierarchy":[32],"with":[33],"replay-aware":[34],"array":[35],"mapping.":[36],"On":[37],"XCVE2302":[38],"FPGAs,":[39],"HAMG":[40],"reaches":[41],"2.29":[42],"TOPS":[43,48],"for":[44,49],"BF16":[45],"5.68":[47],"INT8,":[50],"delivering":[51],"up":[52],"to":[53],"2.8\u00d7":[54],"speedup":[55],"over":[56],"reproduced":[58],"GAMA-style":[59],"baseline.":[60]},"counts_by_year":[],"updated_date":"2026-06-12T06:20:11.936012","created_date":"2026-06-11T00:00:00"}
