SENMAP: Multi-objective data-flow mapping and synthesis for hybrid scalable neuromorphic systems

TL;DR

This paper presents SENMap, a flexible mapping and synthesis tool that optimizes large-scale neuromorphic architectures for energy efficiency, throughput, and accuracy, demonstrated by significant energy savings in simulations.

Contribution

Introduces SENMap, a novel, open-source mapping software that efficiently maps large SNNs and ANNs onto adaptable neuromorphic architectures, improving energy efficiency and scalability.

Findings

SENMap achieves 40% energy savings in simulations.

Supports mapping of large SNNs and ANNs.

Facilitates flexible neuromorphic chip design.

Abstract

This paper introduces SENMap, a mapping and synthesis tool for scalable, energy-efficient neuromorphic computing architecture frameworks. SENECA is a flexible architectural design optimized for executing edge AI SNN/ANN inference applications efficiently. To speed up the silicon tape-out and chip design for SENECA, an accurate emulator, SENSIM, was designed. While SENSIM supports direct mapping of SNNs on neuromorphic architectures, as the SNN and ANNs grow in size, achieving optimal mapping for objectives like energy, throughput, area, and accuracy becomes challenging. This paper introduces SENMap, flexible mapping software for efficiently mapping large SNN and ANN applications onto adaptable architectures. SENMap considers architectural, pretrained SNN and ANN realistic examples, and event rate-based parameters and is open-sourced along with SENSIM to aid flexible neuromorphic chip design before fabrication. Experimental results show SENMap enables 40 percent energy improvements for a baseline SENSIM operating in timestep asynchronous mode of operation. SENMap is designed in such a way that it facilitates mapping large spiking neural networks for future modifications as well.