A Top-Down Design Methodology for Accuracy-to-Noise Mapping in Analog Compute-in-Memory Systems: Evaluation on Mamba

Authors:

Open Access

5 August 2026

conference paper
Published by Association for Computing Machinery (ACM)

p. 1-7
DOI:10.1145/3816440.3818597

Abstract

This work establishes a top-down design methodology for analog compute-in-memory (ACIM) systems that derives circuit-level noise bounds directly from application-specific accuracy constraints. Rather than relying on traditional bottom-up error simulation, we utilize a custom noise injection framework to extract layer-wise noise tolerance thresholds independent of the underlying hardware technology. These abstract thresholds are mathematically translated into minimum computational signal-to-noise ratio (compute SNR) requirements, forming a direct link between algorithm robustness and physical circuit limits. Hardware designers can utilize these SNR targets to reverse-engineer optimal design parameters, including bit precision, array sizing, and data converter scaling. Validated on the Mamba SSM architecture, our framework successfully isolates highly noise-tolerant operations from precision-critical layers, directly informing the design of energy-efficient ACIM systems tailored to specific machine learning workloads.

Keywords

Funding Information

National Science Foundation (2023-JU-3133)
Defense Advanced Research Projects Agency (GR00024712)
National Science Foundation (DGE-2545526)

This publication has 13 references indexed in Scilit:

MIX-ACIM: A 28nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication
IEEE Solid-State Circuits Letters, 2025
Deep learning software stacks for analogue in-memory computing-based accelerators
Nature Reviews Electrical Engineering, 2025
HamQ: Hamming Weight-Based Energy-Aware Quantization for Analog Compute-in-Memory Accelerator in Intelligent Sensors
IEEE Sensors Journal, 2024
A Charge Domain SRAM Compute-in-Memory Macro With C-2C Ladder-Based 8-Bit MAC Unit in 22-nm FinFET Process for Edge Inference
IEEE Journal of Solid-State Circuits, 2023
HERMES-Core—A 1.59-TOPS/mm ² PCM on 14-nm CMOS In-Memory Compute Core Using 300-ps/LSB Linearized CCO-Based ADCs
IEEE Journal of Solid-State Circuits, 2022
Scalable and Programmable Neural Network Inference Accelerator Based on In-Memory Computing
IEEE Journal of Solid-State Circuits, 2021
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-Chip Training
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020
Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices
IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2019
Statistical theory of quantization
IEEE Transactions on Instrumentation and Measurement, 1996
Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training
IEEE Transactions on Neural Networks, 1994