A Flash-Based Multi-Bit Content-Addressable Memory with Euclidean Squared Distance
Authors:
- 26 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Content-addressable memories (CAMs) can perform fast and energy-efficient search operations. Recently, ternary CAMs (TCAMs) have been utilized to measure Hamming distance for machine learning applications, where they offer significant energy savings and speed-ups. However, the binary precision of the Hamming distance can lead to severe degradation in application-level accuracies, thus mitigating the impact of gains with respect to other figures of merit. To enhance accuracy, multi-bit CAMs (MCAMs) have been proposed that offer higher density and energy savings than TCAMs by storing multiple bits in each cell. However, existing MCAMs are based on emerging nonvolatile memory technologies that are yet to be established. To this end, we propose a fast and extremely energy-efficient MCAM based on mature and widely used flash cells, called $\mathrm{E}^{2} -$MCAM. $\mathrm{E}^{2} -$MCAM can measure the Euclidean squared distance between search queries and data stored in the MCAM “in-memory”, and in a single cycle. We evaluate $\mathrm{E}^{2} -$MCAM using an experimentally calibrated flash model in HSPICE with 3-bit precision for proof of concept demonstration. $\mathrm{A}64 \times 32 \mathrm{E}^{2} -$MCAM array achieves a 0.34 fJ energy per bit per search and a 2.7 ns latency while operating at a $770 \mu \mathrm{W}$ power. Fast and efficient hardware support for Euclidean squared distance is highly valuable as it is widely used in a plethora of machine learning applications. As an example, we show that $\mathrm{E}^{2} -$MCAM achieves accuracies comparable to floating-point GPU implementations with only 3-bit precision for few-shot learning tasks with the ImageNet dataset while offering improvements in energy and latency.
Keywords
This publication has 17 references indexed in Scilit:
- A ferroelectric field effect transistor based synaptic weight cellJournal of Physics D: Applied Physics, 2018
- A 1Tb 4b/cell 64-stacked-WL 3D NAND flash memory with 12MB/s program throughput2018
- Model-based high-precision tuning of NOR flash memory cells for analog computing applications2016
- 7.7 A 768Gb 3b/cell 3D-floating-gate NAND flash memory2016
- Human-level concept learning through probabilistic program inductionScience, 2015
- Redesigning commercial floating-gate memory for analog computing applications2015
- Threshold Voltage Distribution in MLC NAND Flash Memory: Characterization, Analysis and Modeling2013
- Content-Addressable Memory (CAM) Circuits and Architectures: A Tutorial and SurveyIEEE Journal of Solid-State Circuits, 2006
- High-performance and low-voltage sense-amplifier techniques for sub-90nm SRAM2004
- Next generation routersProceedings of the IEEE, 2002