Performance Evaluation of Systolic DCNN Accelerators
- Title
- Performance Evaluation of Systolic DCNN Accelerators
- Authors
- RIM, DONGYOUNG; LEE, YOUNGJOO
- Date Issued
- 2021-11-02
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- For the given deep convolutional neural network (DCNN) models, in this work, we carefully evaluate systolic DNN accelerators associated with different array configurations. In order to find the optimal array structure in terms of the processing efficiency, the open-source evaluation framework is adopted for investigating the relationships between the network architecture and the hardware-level options. We also present the selection criteria of array structure that leads to the efficient accelerator designs.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/110210
- Article Type
- Conference
- Citation
- 2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021, 2021-11-02
- 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.