Fully-Binarized, Parallel, RRAM-based Computing Primitive for In-Memory Similarity Search

In this work, we propose a fully-binarized XOR-based IMSS (In-Memory Similarity Search) using RRAM (Resistive Random Access Memory) arrays. XOR (Exclusive OR) operation is realized using 2T-2R bitcells arranged along the column in an array. This enables simultaneous match operation across multiple s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems. II, Express briefs Vol. 70; no. 1; p. 1
Main Authors: Kingra, Sandeep Kaur, Parmar, Vivek, Verma, Deepak, Bricalli, Alessandro, Piccolboni, Giuseppe, Molas, Gabriel, Regev, Amir, Suri, Manan
Format: Journal Article
Language:English
Published: New York IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Arrays
Edge-AI
Energy dissipation
Image classification
In-Memory Computing
Logic gates
Low-power computing
Mathematical analysis
Nonvolatile memory
Performance evaluation
Programming
Random access memory
Resistance
RRAM
Similarity
Similarity Search
SPICE
ISSN:1549-7747, 1558-3791
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we propose a fully-binarized XOR-based IMSS (In-Memory Similarity Search) using RRAM (Resistive Random Access Memory) arrays. XOR (Exclusive OR) operation is realized using 2T-2R bitcells arranged along the column in an array. This enables simultaneous match operation across multiple stored data vectors by performing analog column-wise XOR operation and summation to compute HD (Hamming Distance). The proposed scheme is experimentally validated on fabricated RRAM arrays. Full-system validation is performed through SPICE simulations using open source Skywater 130 nm CMOS PDK demonstrating energy of 17 fJ per XOR operation using the proposed bitcell with a full-system power dissipation of 145 μW. Using projected estimations at advanced nodes (28 nm) energy savings of ≈1.5× compared to the state-of-the-art can be observed for a fixed workload. Application-level validation is performed on HSI (Hyper-Spectral Image) pixel classification task using the Salinas dataset demonstrating an accuracy of 91%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1549-7747
1558-3791
DOI:10.1109/TCSII.2022.3207378