MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks
Memory-augmented neural networks (MANNs) require large external memories to enable long-term memory storage and retrieval. Content-addressable memory (CAM) is a type of memory used for high-speed searching applications and is well-suited for MANNs. Recent advances in exploratory nonvolatile devices...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal on Exploratory Solid-State Computational Devices and Circuits |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10550938/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526346592813056 |
|---|---|
| author | Sai Sanjeet Jonathan Bird Bibhu Datta Sahoo |
| author_facet | Sai Sanjeet Jonathan Bird Bibhu Datta Sahoo |
| author_sort | Sai Sanjeet |
| collection | DOAJ |
| description | Memory-augmented neural networks (MANNs) require large external memories to enable long-term memory storage and retrieval. Content-addressable memory (CAM) is a type of memory used for high-speed searching applications and is well-suited for MANNs. Recent advances in exploratory nonvolatile devices have spurred the development of nonvolatile CAMs. However, these devices suffer from poor ON-OFF ratio, large write voltages, and long write times. This work proposes a nonvolatile ternary CAM (TCAM) using magnetoelectric field effect transistors (MEFETs). The energy and delay of various operations are simulated using the ASAP 7-nm predictive technology for the transistors and a Verilog-A model of the MEFET. The proposed structure achieves orders of magnitude improvement in search energy and <inline-formula> <tex-math notation="LaTeX">$\gt 45\times $ </tex-math></inline-formula> improvement in search energy-delay product compared with prior works. The write energy and delay are also improved by <inline-formula> <tex-math notation="LaTeX">$8\times $ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$12\times $ </tex-math></inline-formula>, respectively, compared with CAMs designed with other nonvolatile devices. A variability analysis is performed to study the effect of process variations on the CAM. The proposed CAM is then used to build a one-shot learning MANN and is benchmarked with the Modified National Institute of Standards and Technology (MNIST), extended MNIST (EMNIST), and labeled faces in the wild (LFW) datasets with binary embeddings, giving >99% accuracy on MNIST, a top-3 accuracy of 97.11% on the EMNIST dataset, and >97% accuracy on the LFW dataset, with embedding sizes of 16, 64, and 512, respectively. The proposed CAM is shown to be fast, energy-efficient, and scalable, making it suitable for MANNs. |
| format | Article |
| id | doaj-art-5ea8eca713e4442597a3ac1a5272f083 |
| institution | Kabale University |
| issn | 2329-9231 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal on Exploratory Solid-State Computational Devices and Circuits |
| spelling | doaj-art-5ea8eca713e4442597a3ac1a5272f0832025-01-17T00:00:32ZengIEEEIEEE Journal on Exploratory Solid-State Computational Devices and Circuits2329-92312024-01-0110313910.1109/JXCDC.2024.341068110550938MEFET-Based CAM/TCAM for Memory-Augmented Neural NetworksSai Sanjeet0Jonathan Bird1Bibhu Datta Sahoo2Department of Electrical Engineering, University at Buffalo, Buffalo, NY, USADepartment of Electrical Engineering, University at Buffalo, Buffalo, NY, USADepartment of Electrical Engineering, University at Buffalo, Buffalo, NY, USAMemory-augmented neural networks (MANNs) require large external memories to enable long-term memory storage and retrieval. Content-addressable memory (CAM) is a type of memory used for high-speed searching applications and is well-suited for MANNs. Recent advances in exploratory nonvolatile devices have spurred the development of nonvolatile CAMs. However, these devices suffer from poor ON-OFF ratio, large write voltages, and long write times. This work proposes a nonvolatile ternary CAM (TCAM) using magnetoelectric field effect transistors (MEFETs). The energy and delay of various operations are simulated using the ASAP 7-nm predictive technology for the transistors and a Verilog-A model of the MEFET. The proposed structure achieves orders of magnitude improvement in search energy and <inline-formula> <tex-math notation="LaTeX">$\gt 45\times $ </tex-math></inline-formula> improvement in search energy-delay product compared with prior works. The write energy and delay are also improved by <inline-formula> <tex-math notation="LaTeX">$8\times $ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$12\times $ </tex-math></inline-formula>, respectively, compared with CAMs designed with other nonvolatile devices. A variability analysis is performed to study the effect of process variations on the CAM. The proposed CAM is then used to build a one-shot learning MANN and is benchmarked with the Modified National Institute of Standards and Technology (MNIST), extended MNIST (EMNIST), and labeled faces in the wild (LFW) datasets with binary embeddings, giving >99% accuracy on MNIST, a top-3 accuracy of 97.11% on the EMNIST dataset, and >97% accuracy on the LFW dataset, with embedding sizes of 16, 64, and 512, respectively. The proposed CAM is shown to be fast, energy-efficient, and scalable, making it suitable for MANNs.https://ieeexplore.ieee.org/document/10550938/Content-addressable memory (CAM)ferroelectric field effect transistor (FeFET)magnetoelectric field effect transistors (MEFETs)magnetoelectric magnetic tunnel junction field effect transistor (ME-MTJ-FET)memory-augmented neural network (MANN)resistive random access memory (ReRAM) |
| spellingShingle | Sai Sanjeet Jonathan Bird Bibhu Datta Sahoo MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks IEEE Journal on Exploratory Solid-State Computational Devices and Circuits Content-addressable memory (CAM) ferroelectric field effect transistor (FeFET) magnetoelectric field effect transistors (MEFETs) magnetoelectric magnetic tunnel junction field effect transistor (ME-MTJ-FET) memory-augmented neural network (MANN) resistive random access memory (ReRAM) |
| title | MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks |
| title_full | MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks |
| title_fullStr | MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks |
| title_full_unstemmed | MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks |
| title_short | MEFET-Based CAM/TCAM for Memory-Augmented Neural Networks |
| title_sort | mefet based cam tcam for memory augmented neural networks |
| topic | Content-addressable memory (CAM) ferroelectric field effect transistor (FeFET) magnetoelectric field effect transistors (MEFETs) magnetoelectric magnetic tunnel junction field effect transistor (ME-MTJ-FET) memory-augmented neural network (MANN) resistive random access memory (ReRAM) |
| url | https://ieeexplore.ieee.org/document/10550938/ |
| work_keys_str_mv | AT saisanjeet mefetbasedcamtcamformemoryaugmentedneuralnetworks AT jonathanbird mefetbasedcamtcamformemoryaugmentedneuralnetworks AT bibhudattasahoo mefetbasedcamtcamformemoryaugmentedneuralnetworks |