Home > Publications database > Analog Softmax with Wide Input Current Range for In-Memory Computing > print

001     1050456
005     20260121204316.0
024 7 _ |a 10.1109/ISCAS56072.2025.11043251
|2 doi
037 _ _ |a FZJ-2026-00226
100 1 _ |a Dube, Aradhana
|0 P:(DE-HGF)0
|b 0
|e Corresponding author
111 2 _ |a 2025 IEEE International Symposium on Circuits and Systems (ISCAS)
|c London
|d 2025-05-25 - 2025-05-28
|w United Kingdom
245 _ _ |a Analog Softmax with Wide Input Current Range for In-Memory Computing
260 _ _ |c 2025
|b IEEE
295 1 0 |a 2025 IEEE International Symposium on Circuits and Systems (ISCAS) : [Proceedings] - IEEE, 2025. - ISBN 979-8-3503-5683-0 - doi:10.1109/ISCAS56072.2025.11043251
300 _ _ |a 1-5
336 7 _ |a CONFERENCE_PAPER
|2 ORCID
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a Output Types/Conference Paper
|2 DataCite
336 7 _ |a Contribution to a conference proceedings
|b contrib
|m contrib
|0 PUB:(DE-HGF)8
|s 1768997948_13601
|2 PUB:(DE-HGF)
336 7 _ |a Contribution to a book
|0 PUB:(DE-HGF)7
|2 PUB:(DE-HGF)
|m contb
520 _ _ |a The Softmax activation function plays a pivotalrole in both the attention mechanism of Transformers andin the final layer of neural networks performing classification.The Softmax function outputs probabilities by normalizing theinput values, emphasizing differences among them to highlightthe largest values. In digital implementations, the complexityof softmax grows linearly with the number of inputs. Incontrast, analog implementations enable parallel computationswith lower latency. In this work, we demonstrate that thisapproach achieves a more efficient linear scaling of latencyas vector size increases logarithmically. This analog softmaxcircuits are implemented in TSMC 28 nm PDK technology,capable of driving up to 128 inputs and producing an ana-log current output spanning three orders of magnitude. Thestudy examines the circuit’s power consumption, latency, anderror, emphasizing its efficiency compared to the alternativeapproach of converting outputs to digital signals via ADCsand performing the softmax calculation digitally. By reducingreliance on these power-intensive operations, this work aims tosignificantly enhance energy efficiency in in-memory computingsystems.
536 _ _ |a 5234 - Emerging NC Architectures (POF4-523)
|0 G:(DE-HGF)POF4-5234
|c POF4-523
|f POF IV
|x 0
588 _ _ |a Dataset connected to CrossRef Conference
700 1 _ |a Manea, Paul
|0 P:(DE-Juel1)192242
|b 1
|u fzj
700 1 _ |a Gibertini, Paolo
|0 P:(DE-HGF)0
|b 2
700 1 _ |a Covi, Erika
|0 P:(DE-HGF)0
|b 3
700 1 _ |a Strachan, John Paul
|0 P:(DE-Juel1)188145
|b 4
|u fzj
773 _ _ |a 10.1109/ISCAS56072.2025.11043251
856 4 _ |u https://ieeexplore.ieee.org/abstract/document/11043251
856 4 _ |u https://juser.fz-juelich.de/record/1050456/files/Analog_Softmax_with_Wide_Input_Current_Range_for_In-Memory_Computing.pdf
|y Restricted
909 C O |o oai:juser.fz-juelich.de:1050456
|p VDB
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-HGF)0
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)192242
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 4
|6 P:(DE-Juel1)188145
913 1 _ |a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|1 G:(DE-HGF)POF4-520
|0 G:(DE-HGF)POF4-523
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Neuromorphic Computing and Network Dynamics
|9 G:(DE-HGF)POF4-5234
|x 0
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)PGI-14-20210412
|k PGI-14
|l Neuromorphic Compute Nodes
|x 0
980 _ _ |a contrib
980 _ _ |a VDB
980 _ _ |a contb
980 _ _ |a I:(DE-Juel1)PGI-14-20210412
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21