中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow

文献类型：期刊论文

作者Wang, Zhen1,2; Liu, Tianyu1,2; Fan, Zhihua1,2; Li, Wenming1,2; Qiu, Yuhang1,2; Zhang, Zhiyuan1,2; An, Xuejun2; Fan, Dongrui2; Ye, Xiaochun2
刊名ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION
出版日期2025-12-01
卷号22期号:4页码:23
关键词Convolutional neural networks accelerators sparsity algorithm-hardware co-design
ISSN号1544-3566
DOI10.1145/3773995
英文摘要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 5.31x, 2.46x and 1.53x speedup and reducing energy consumption by 80.68%, 69.13% and 53.52%, respectively.
资助项目National Key R&D Program of China[2023YFB4503500] ; Beijing Natural Science Foundation[No.L234078] ; SKLP Foundation[CLQD202502]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001667494000011
出版者ASSOC COMPUTING MACHINERY
源URL[http://119.78.100.204/handle/2XEOYT63/42889]  
专题中国科学院计算技术研究所
通讯作者Wang, Zhen
作者单位1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
2.Chinese Acad Sci, State Key Lab Proc, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Zhen,Liu, Tianyu,Fan, Zhihua,et al. Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow[J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,2025,22(4):23.
APA Wang, Zhen.,Liu, Tianyu.,Fan, Zhihua.,Li, Wenming.,Qiu, Yuhang.,...&Ye, Xiaochun.(2025).Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow.ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION,22(4),23.
MLA Wang, Zhen,et al."Compressing and Accelerating Sparse CNNs Using Sign-Reserved Toeplitz Filters and Input Activation Density-aware Dataflow".ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 22.4(2025):23.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。