# SATA: Sparsity-Aware Training Accelerator for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2204.05422 · HTML: https://mlsanity.com/paper/2204.05422/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2022.

## Built on by (most cited first, 20 of 20)

- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [Reconsidering the Energy Efficiency of Spiking Neural Networks Inference from Analytical Perspectives](https://mlsanity.com/paper/2409.08290/) (2024)
- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [Input-Aware Dynamic Timestep Spiking Neural Networks for Efficient In-Memory Computing](https://mlsanity.com/paper/2305.17346/) (2023)
- [MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks](https://mlsanity.com/paper/2305.09850/) (2023)
- [SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks](https://mlsanity.com/paper/2210.12899/) (2022)
- [LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks](https://mlsanity.com/paper/2407.14073/) (2024)
- [Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks](https://mlsanity.com/paper/2212.02233/) (2022)
- [Hoyer regularizer is all you need for ultra low-latency spiking neural networks](https://mlsanity.com/paper/2212.10170/) (2022)
- [Spiking Neural Networks with Dynamic Time Steps for Vision Transformers](https://mlsanity.com/paper/2311.16456/) (2023)
- [Dynamic Tsetlin Machine Accelerators for On-Chip Training at the Edge using FPGAs](https://mlsanity.com/paper/2504.19797/) (2025)
- [When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design](https://mlsanity.com/paper/2408.12767/) (2024)
- [SpikeX: Exploring Accelerator Architecture and Network-Hardware Co-Optimization for Sparse Spiking Neural Networks](https://mlsanity.com/paper/2505.12292/) (2025)
- [When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks](https://mlsanity.com/paper/2312.06900/) (2023)
- [Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression](https://mlsanity.com/paper/2407.08744/) (2024)
- [Sparsity-Aware Hardware-Software Co-Design of Spiking Neural Networks: An Overview](https://mlsanity.com/paper/2408.14437/) (2024)
- [Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient](https://mlsanity.com/paper/2511.08708/) (2025)
- [MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network](https://mlsanity.com/paper/2512.04443/) (2025)
- [Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware](https://mlsanity.com/paper/2603.24891/) (2026)
- [L-SPINE: A Low-Precision SIMD Spiking Neural Compute Engine for Resource-efficient Edge Inference](https://mlsanity.com/paper/2604.03626/) (2026)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. Recently, SNNs with backpropagation through time (BPTT) have achieved a higher accuracy result on image recognition tasks than other SNN training algorithms. Despite the success from the algorithm perspective, prior works neglect the evaluation of the hardware energy overheads of BPTT due to the lack of a hardware evaluation platform for this SNN training algorithm. Moreover, although SNNs have long been seen as an energy-efficient counterpart of ANNs, a quantitative comparison between the training cost of SNNs and ANNs is missing. To address the aforementioned issues, in this work, we introduce SATA (Sparsity-Aware Training Accelerator), a BPTT-based training accelerator for SNNs. The proposed SATA provides a simple and re-configurable systolic-based accelerator architecture, which makes it easy to analyze the training energy for BPTT-based SNN training algorithms. By utilizing the sparsity, SATA increases its computation energy efficiency by 5.58 × compared to the one without using sparsity. Based on SATA, we show quantitative analyses of the energy efficiency of SNN training and compare the training cost of SNNs and ANNs. The results show that, on Eyeriss-like systolic-based architecture, SNNs consume 1.27× more total energy with sparsities when compared to ANNs. We find that such high training energy cost is from time-repetitive convolution operations and data movements during backpropagation. Moreover, to propel the future SNN training algorithm design, we provide several observations on energy efficiency for different SNN-specific training parameters and propose an energy estimation framework for SNN training. Code for our framework is made publicly available.