Saved in:
Bibliographic Details
Main Authors: Gupta, Rajat, Elangovan, Yuvaraj, Hong, Tae Min, Ignowski, James, Moon, John, Natarajan, Aishwarya, Roche, Stephen, Buonanno, Luca
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918343680720896
author Gupta, Rajat
Elangovan, Yuvaraj
Hong, Tae Min
Ignowski, James
Moon, John
Natarajan, Aishwarya
Roche, Stephen
Buonanno, Luca
author_facet Gupta, Rajat
Elangovan, Yuvaraj
Hong, Tae Min
Ignowski, James
Moon, John
Natarajan, Aishwarya
Roche, Stephen
Buonanno, Luca
contents We present an implementation of edge AI to compress data on an in-memory analog content-addressable memory (ACAM) device. A variational autoencoder is trained on a simulated sample of energy measurements from incident high-energy electrons on a generic three-layer scintillator-based calorimeter. The encoding part is distilled into tabular format by regressing the latent space variables using decision trees, which is then programmed on a memristor-based ACAM. In real-time, the ACAM compresses 48 continuously valued incoming energies measured by the calorimeter sensors into the latent space, achieving a compression factor of 12x, which is transmitted off-detector for decompression. The performance result of the ACAM, obtained using the Structural Simulation Toolkit, the SST open source framework, gives a latency value of 24 ns and a throughput of 330M compressions per second, i.e., 3 ns between successive inputs, and an average energy consumption of 4.1 nJ per compression.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15990
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Memristive tabular variational autoencoder for compression of analog data in high energy physics
Gupta, Rajat
Elangovan, Yuvaraj
Hong, Tae Min
Ignowski, James
Moon, John
Natarajan, Aishwarya
Roche, Stephen
Buonanno, Luca
Instrumentation and Detectors
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
We present an implementation of edge AI to compress data on an in-memory analog content-addressable memory (ACAM) device. A variational autoencoder is trained on a simulated sample of energy measurements from incident high-energy electrons on a generic three-layer scintillator-based calorimeter. The encoding part is distilled into tabular format by regressing the latent space variables using decision trees, which is then programmed on a memristor-based ACAM. In real-time, the ACAM compresses 48 continuously valued incoming energies measured by the calorimeter sensors into the latent space, achieving a compression factor of 12x, which is transmitted off-detector for decompression. The performance result of the ACAM, obtained using the Structural Simulation Toolkit, the SST open source framework, gives a latency value of 24 ns and a throughput of 330M compressions per second, i.e., 3 ns between successive inputs, and an average energy consumption of 4.1 nJ per compression.
title Memristive tabular variational autoencoder for compression of analog data in high energy physics
topic Instrumentation and Detectors
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2602.15990