A Study on Group Pruning for Sparsity-Aware DNN Accelerator
- Title
- A Study on Group Pruning for Sparsity-Aware DNN Accelerator
- Authors
- 이호진
- Date Issued
- 2020
- Publisher
- 포항공과대학교
- Abstract
- To reduce model complexity of DNNs, pruning has been proposed to remove less important weights. The pruned networks is difficult to be accelerated on GPU due to the high irregularity, so the structure pruning was proposed, but its low degree of freedom lead the accuracy loss. Thus, sparsity-aware accelerators, which can utilize fine-grained pruning, has been proposed, and accelerator-aware pruning has also proposed to improve the performance of the accelerators. However, the current accelerator-aware pruning cannot consider both input and weight sparsity. In this thesis, we propose a group pruning algorithm that can operate on Cartesian product to deal with both input and weight sparsity, and achieve fine-grained level accuracy with a high degree of freedom. When we applied our algorithm to DNNs, there was little difference in accuracy compared to fine-grained pruning, and the accelerator with our algorithm achieved state of art speed-up.
- URI
- http://postech.dcollection.net/common/orgView/200000334382
https://oasis.postech.ac.kr/handle/2014.oak/111787
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.