Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow
Open Access
- 16 December 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 22 (4) , 1-23
Abstract
Exploiting the sparsity in convolutional neural networks is crucial to accelerate computing and reduce energy consumption. Unstructured sparsity, benefiting from its flexibility to accommodate arbitrary sparse patterns, generally achieves higher accuracy, but it often introduces irregularity in convolutional operations, which complicates the control logic and undermines the benefits of sparsification. Structured sparsity alleviates these problems but sacrifices its application flexibility, which leads to lower accuracy. In this article, we propose TSCNN, an algorithm-hardware co-design solution that aims to compress and accelerate sparse CNNs while balancing both adaptability to sparsity and computational efficiency. In terms of algorithm, TSCNN adopts pruned filters compressed with sign-reserved Toeplitz matrix format (Tfilters), which systematically enhances the regularity of data reuse and flexibly reduces network parameters by 44%-86% while maintaining accuracy. In terms of hardware, TSCNN accelerator adapts to the structure of Tfilters and utilizes density-aware dataflows to support input activations with large sparsity variation, further optimizing the computational efficiency. Experiments show that TSCNN outperforms a dense CNN accelerator, sparse CNN accelerators SCNN and CSCNN, achieving 5.31× , 2.46× and 1.53× speedup and reducing energy consumption by 80.68%, 69.13% and 53.52%, respectively.Keywords
Funding Information
- National Key R&D Program of China (2023YFB4503500)
- Beijing Natural Science Foundation (L234078)
- SKLP Foundation (CLQD202502)
This publication has 33 references indexed in Scilit:
- T-BUS: Taming Bipartite Unstructured Sparsity for Energy-Efficient DNN Acceleration2024
- S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration2022
- Dual-side Sparse Tensor Core2021
- Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training2020
- Timeloop: A Systematic Approach to DNN Accelerator Evaluation2019
- Cambricon-S: Addressing Irregularity in Sparse Neural Networks through A Cooperative Software/Hardware Approach2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- ImageNet: A large-scale hierarchical image database2009