Publications
Detailed Information
ShortcutFusion: From Tensorflow to FPGA-Based Accelerator With a Reuse-Aware Memory Allocation for Shortcut Data
Cited 8 time in
Web of Science
Cited 10 time in Scopus
- Authors
- Issue Date
- 2022-06
- Citation
- IEEE Transactions on Circuits and Systems I: Regular Papers, Vol.69 No.6, pp.2477-2489
- Abstract
- IEEEResidual block is a very common component in recent state-of-the art CNNs such as EfficientNet/EfficientDet. Shortcut data accounts for nearly 40% of feature-maps access in ResNet152. Most of the previous DNN compilers/accelerators ignore the shortcut data optimization. This paper presents ShortcutFusion, an optimization tool for FPGA-based accelerator with a reuse-aware static memory allocation for shortcut data, to maximize on-chip data reuse given resource constraints. From TensorFlow DNN models, the proposed design generates instruction sets for a group of nodes which uses an optimized data reuse for each residual block. The accelerator design implemented on the Xilinx KCU1500 FPGA card 2.8x faster and 9.9x more power efficient than NVIDIA RTX 2080 Ti for 256x 256 input size. Compared to the result from baseline, in which the weights/inputs/outputs are accessed from the off-chip memory exactly once per each layer, ShortcutFusion reduces the DRAM access by 47.8-84.8% for RetinaNet, Yolov3, ResNet152, and EfficientNet. Given a similar buffer size to ShortcutMining, which also ``mine'' the shortcut data in hardware, the proposed work reduces off-chip access for feature-maps 5.27x while accessing weight from off-chip memory exactly once.
- ISSN
- 1549-8328
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.