Flexi-NeurA: A Configurable Neuromorphic Accelerator with Adaptive Bit-Precision Exploration for Edge SNNs

2026-02-20

AI Summary

This work proposes Flexi-NeurA, a highly configurable neuromorphic accelerator core designed to address the limitations of existing architectures, which suffer from rigidity and insufficient adaptability for diverse spiking neural network (SNN) requirements in edge scenarios. Flexi-NeurA enables custom neuron models, network topologies, and bit precision at design time, integrating time-multiplexing and event-driven mechanisms to enhance energy efficiency. The architecture innovatively combines parameterized RTL generation, LIF model mapping, a heuristic bit-width exploration algorithm, and the Flex-plorer design space exploration tool to achieve adaptive optimization between accuracy and hardware resources. Evaluated on MNIST, it achieves 97.23% accuracy with only 1,623 logic units, 7 BRAMs, 111 mW power consumption, and 1.1 ms latency, demonstrating its high energy efficiency, flexibility, and scalability.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Neuromorphic accelerators promise unparalleled energy efficiency and computational density for spiking neural networks (SNNs), especially in edge intelligence applications. However, most existing platforms exhibit rigid architectures with limited configurability, restricting their adaptability to heterogeneous workloads and diverse design objectives. To address these limitations, we present Flexi-NeurA -- a parameterizable neuromorphic accelerator (core) that unifies configurability, flexibility, and efficiency. Flexi-NeurA allows users to customize neuron models, network structures, and precision settings at design time. By pairing these design-time configurability and flexibility features with a time-multiplexed and event-driven processing approach, Flexi-NeurA substantially reduces the required hardware resources and total power while preserving high efficiency and low inference latency. Complementing this, we introduce Flex-plorer, a heuristic-guided design-space exploration (DSE) tool that determines cost-effective fixed-point precisions for critical parameters -- such as decay factors, synaptic weights, and membrane potentials -- based on user-defined trade-offs between accuracy and resource usage. Based on the configuration selected through the Flex-plorer process, RTL code is configured to match the specified design. Comprehensive evaluations across MNIST, SHD, and DVS benchmarks demonstrate that the Flexi-NeurA and Flex-plorer co-framework achieves substantial improvements in accuracy, latency, and energy efficiency. A three-layer 256--128--10 fully connected network with LIF neurons mapped onto two processing cores achieves 97.23% accuracy on MNIST with 1.1~ms inference latency, utilizing only 1,623 logic cells, 7 BRAMs, and 111~mW of total power -- establishing Flexi-NeurA as a scalable, edge-ready neuromorphic platform.

Problem

• neuromorphic accelerator
• configurability
• spiking neural networks
• edge intelligence
• bit-precision

Innovation

• configurable neuromorphic accelerator
• adaptive bit-precision
• design-space exploration
• event-driven processing
• edge SNNs