Title | In-Memory Nearest Neighbor Search with FeFET Multi-Bit Content-Addressable Memories |
Publication Type | Conference Paper |
Year of Publication | 2021 |
Authors | Kazemi, Arman, Sharifi, Mohammad Mehdi, Laguna, Ann Franchesca, Müller, Franz, Rajaei, Ramin, Olivo, Ricardo, Kämpfe, Thomas, Niemier, Michael, Hu, X. Sharon |
Conference Name | 2021 Design, Automation Test in Europe Conference Exhibition (DATE) |
Keywords | content-addressable memory, delays, ferroelectric FET, Hamming distance, Hardware, Measurement, Metrics, multi-bit design, Nearest neighbor methods, nearest neighbor search, pubcrawl, Software, Task Analysis |
Abstract | Nearest neighbor (NN) search is an essential operation in many applications, such as one/few-shot learning and image classification. As such, fast and low-energy hardware support for accurate NN search is highly desirable. Ternary content-addressable memories (TCAMs) have been proposed to accelerate NN search for few-shot learning tasks by implementing \$L\$ and Hamming distance metrics, but they cannot achieve software-comparable accuracies. This paper proposes a novel distance function that can be natively evaluated with multi-bit content-addressable memories (MCAMs) based on ferroelectric FETs (Fe-FETs) to perform a single-step, in-memory NN search. Moreover, this approach achieves accuracies comparable to floating-point precision implementations in software for NN classification and one/few-shot learning tasks. As an example, the proposed method achieves a 98.34% accuracy for a 5-way, 5-shot classification task for the Omniglot dataset (only 0.8% lower than software-based implementations) with a 3-bit MCAM. This represents a 13% accuracy improvement over state-of-the-art TCAM-based implementations at iso-energy and iso-delay. The presented distance function is resilient to the effects of FeFET device-to-device variations. Furthermore, this work experimentally demonstrates a 2-bit implementation of FeFET MCAM using AND arrays from GLOBALFOUNDRIES to further validate proof of concept. |
DOI | 10.23919/DATE51398.2021.9474025 |
Citation Key | kazemi_-memory_2021 |