A content addressable memory (CAM) is a special form of memory that compares an input search word against all rows of stored words in an array in a highly parallel manner.While supplying a very powerful functionality for many applications in pattern matching and search, CAMs suffer from large area, cost and power consumption, limiting their use.Past improvements have been realized by using non-volatile memristors to replace the staticrandom-access memory in conventional designs, but employ similar schemes based only on binary or ternary states for storage and search. We propose a new analog CAM concept and circuit to overcome these limitations by utilizing the analog conductance tunability of memristors. Our analog CAM stores data within the programmable conductance and can take as input either analog or digital search values. Experimental demonstrations and scaled simulations validated the concept and performance, with analysis showing that our analog CAM can reduce area and power consumption (37×) compared to a digital version. The analog processing nature enables the acceleration of existing CAM applications, but also new computing application areas including fuzzy logic, probabilistic computing, and decision trees.1 arXiv:1907.08177v1 [cs.ET] 18 Jul 2019 success in applications such as network routing 15, 16 , real-time network traffic monitoring 17 , and access control lists (ACL) 18 . While powerful, CAM performance benefits come at the cost of large power and low memory density, limiting modern usage to high cost niche areas that demand high performance. Recent work has shown that utilizing non-volatile memristors (or resistive memory devices) in TCAM circuits reduces area and power 19-27 and provides the flexibility to accelerate powerful finite state machines, particularly for Regular Expression matching used in Network Intrusion Detection Systems 23, 28 . However, nearly all memristor-based CAM designs utilize schemes similar to conventional static random-access-memory (SRAM) designs where the memristor only encodes binary states. The highly tunable analog conductance in memristor devices, with many stable intermediate states is not leveraged 29 .Here, we propose a memristor-based analog CAM that significantly increases data density and reduces operational energy and area for these in-memory processing circuits. Our analog CAM design stores a range of values in each cell using the tunable conductance of memristive devices, and compares an analog input with this stored range to determine a match or mis-match. The concept has been validated with proof-of-concept experiments, as well as simulations to establish performance and scalability. When used to store narrow ranges as discrete levels, our analog CAM can be a direct replacement to digital CAMs, but providing higher memory densities and smaller power consumption. This may enable the use of CAMs for more generic scenarios 30-33 that otherwise struggle with the limited memory densities and high power consumption of conventional CAMs. More importantly, o...
Tree-based machine learning techniques, such as Decision Trees and Random Forests, are top performers in several domains as they do well with limited training datasets and offer improved interpretability compared to Deep Neural Networks (DNN). However, these models are difficult to optimize for fast inference at scale without accuracy loss in von Neumann architectures due to non-uniform memory access patterns. Recently, we proposed a novel analog content addressable memory (CAM) based on emerging memristor devices for fast look-up table operations. Here, we propose for the first time to use the analog CAM as an in-memory computational primitive to accelerate tree-based model inference. We demonstrate an efficient mapping algorithm leveraging the new analog CAM capabilities such that each root to leaf path of a Decision Tree is programmed into a row. This new in-memory compute concept for enables few-cycle model inference, dramatically increasing 103 × the throughput over conventional approaches.
We developed nonvolatile metal/SiOx/Si memristive devices based on ultrathin (∼1 nm) silicon oxide that was produced in a Piranha solution. The devices exhibited repeatable resistive switching behavior with low programming voltages (as low as 0.5 V) and high ON/OFF conductance ratio. Devices with active metals as top electrodes were bipolar switches, while those with inert metal electrodes were unipolar. We also studied the switching mechanisms for both types of devices based on the filament formation and rupture, and proposed conduction models for Pt/SiOx/Si devices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.