# Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation

arXiv: https://arxiv.org/abs/1908.10017 · HTML: https://mlsanity.com/paper/1908.10017/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 9 of 9)

- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator](https://mlsanity.com/paper/2106.09144/) (2021)
- [Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI](https://mlsanity.com/paper/2106.09166/) (2021)
- [Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration](https://mlsanity.com/paper/2111.11581/) (2021)
- [All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management](https://mlsanity.com/paper/2212.05122/) (2022)
- [NAPER: Fault Protection for Real-Time Resource-Constrained Deep Neural Networks](https://mlsanity.com/paper/2504.06591/) (2025)
- [ReDy: A Novel ReRAM-centric Dynamic Quantization Approach for Energy-efficient CNN Inference](https://mlsanity.com/paper/2306.16298/) (2023)
- [Algorithm-hardware co-design for Energy-Efficient A/D conversion in ReRAM-based accelerators](https://mlsanity.com/paper/2402.06164/) (2024)

## Abstract (arXiv)

The state-of-art DNN structures involve intensive computation and high memory storage. To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications. However, the high accuracy solution for extreme model compression on memristor crossbar array architecture is still waiting for unraveling. In this paper, we propose a memristor-based DNN framework which combines both structured weight pruning and quantization by incorporating alternating direction method of multipliers (ADMM) algorithm for better pruning and quantization performance. We also discover the non-optimality of the ADMM solution in weight pruning and the unused data path in a structured pruned model. Motivated by these discoveries, we design a software-hardware co-optimization framework which contains the first proposed Network Purification and Unused Path Removal algorithms targeting on post-processing a structured pruned model after ADMM steps. By taking memristor hardware constraints into our whole framework, we achieve extreme high compression ratio on the state-of-art neural network structures with minimum accuracy loss. For quantizing structured pruned model, our framework achieves nearly no accuracy loss after quantizing weights to 8-bit memristor weight representation. We share our models at anonymous link https://bit.ly/2VnMUy0.