{"id":"https://openalex.org/W4410582855","doi":"https://doi.org/10.23919/date64628.2025.10992862","title":"SoftmAP: Software-Hardware Co-Design for Integer-Only Softmax on Associative Processors","display_name":"SoftmAP: Software-Hardware Co-Design for Integer-Only Softmax on Associative Processors","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410582855","doi":"https://doi.org/10.23919/date64628.2025.10992862"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10992862","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation &amp;amp; Test in Europe Conference (DATE)","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/A5075139332","display_name":"Mariam Rakka","orcid":"https://orcid.org/0000-0002-2514-7960"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mariam Rakka","raw_affiliation_strings":["University of California,Irvine,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Irvine,CA,USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021616613","display_name":"Jinhao Li","orcid":"https://orcid.org/0000-0002-4812-3320"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102805465","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0002-8464-0130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013660772","display_name":"Ahmed M. Eltawil","orcid":"https://orcid.org/0000-0003-1849-083X"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ahmed Eltawil","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST),Thuwal,Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST),Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084829415","display_name":"Mohammed E. Fouda","orcid":"https://orcid.org/0000-0001-7139-3428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed E. Fouda","raw_affiliation_strings":["Rain Neuromorphics Inc.,San Francisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Rain Neuromorphics Inc.,San Francisco,CA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008034875","display_name":"Fadi Kurdahi","orcid":"https://orcid.org/0000-0002-6982-365X"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fadi Kurdahi","raw_affiliation_strings":["University of California,Irvine,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Irvine,CA,USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075139332"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11972892,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9923999905586243,"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":0.9923999905586243,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.984499990940094,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9735000133514404,"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/computer-science","display_name":"Computer science","score":0.7020277380943298},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.6506591439247131},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.6289548277854919},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5444108843803406},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5205401182174683},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40805745124816895},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40017762780189514},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3966406583786011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3923134207725525},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20778539776802063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1313818097114563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11346253752708435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10079345107078552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020277380943298},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.6506591439247131},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.6289548277854919},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5444108843803406},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5205401182174683},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40805745124816895},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40017762780189514},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3966406583786011},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3923134207725525},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20778539776802063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1313818097114563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11346253752708435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10079345107078552},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10992862","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1498685334","https://openalex.org/W2064367066","https://openalex.org/W2803022042","https://openalex.org/W2946480111","https://openalex.org/W3021972173","https://openalex.org/W3046387293","https://openalex.org/W3159727696","https://openalex.org/W3211525823","https://openalex.org/W4226117853","https://openalex.org/W4390190579","https://openalex.org/W4401043244","https://openalex.org/W4409307140"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W4303493643"],"abstract_inverted_index":{"Recent":[0],"research":[1],"efforts":[2],"focus":[3],"on":[4,20],"reducing":[5],"the":[6,71],"computational":[7],"and":[8,32,77],"memory":[9],"overheads":[10],"of":[11,67],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"to":[16,37,40,64,75],"make":[17],"them":[18],"feasible":[19],"resource-constrained":[21],"devices.":[22],"Despite":[23],"advancements":[24],"in":[25,70],"compression":[26],"techniques,":[27],"nonlinear":[28],"operators":[29],"like":[30],"Softmax":[31,54],"Layernorm":[33],"remain":[34],"bottlenecks":[35],"due":[36],"their":[38],"sensitivity":[39],"quantization.":[41],"We":[42],"propose":[43],"SoftmAP,":[44],"a":[45],"software-hardware":[46],"co-design":[47],"methodology":[48],"that":[49],"implements":[50],"an":[51],"integer-only":[52],"low-precision":[53],"using":[55],"In-Memory":[56],"Compute":[57],"(IMC)":[58],"hardware.":[59],"Our":[60],"method":[61],"achieves":[62],"up":[63],"three":[65],"orders":[66],"magnitude":[68],"improvement":[69],"energy-delay":[72],"product":[73],"compared":[74],"A100":[76],"RTX3090":[78],"GPUs,":[79],"making":[80],"LLMs":[81],"more":[82],"deployable":[83],"without":[84],"compromising":[85],"performance.":[86]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
