Towards Delta Aware Training: Efficient DNN Weight Storage for Resource-Constrained FPGAs
A new compression technique is introduced to reduce memory footprint on FPGAs by saving weights in deltas with lower bitwidth.
The novelty of this paper lies in the introduction of a new compression technique that uses delta compression with lower bitwidth to reduce memory footprint on FPGAs.
Before reading this…
Applications
- →Hardware acceleration
- →Neural networks on FPGAs
To understand this paper, make sure you know these concepts first:
- Neural networksfind papers →
- FPGAsfind papers →
Abstract
More Like ThisThe deployment of embedded deep neural networks on resource-constrained field programmable gate arrays (FPGAs) is challenging due to limited memory and computational capacities. We introduce a new compression technique to reduce the memory footprint by saving weights in deltas with lower bitwidth and training the network to cope with compressed deltas. Two delta schemes are investigated: consecutive deltas and deltas with a fixed-reference value. We evaluate both on the FashionMNIST data set with a multi-layer-perceptron. The results indicate that fixed-reference delta compression outperforms the consecutive variant, achieving a validation accuracy of approximately 78.6 %, with 4 bit weight deltas, representing an accuracy loss of roughly 8.3 % compared to a fixed-point network with 8 bit. Our specialized hardware accelerator with a delta-compressed multiply-and-accumulate operator compresses weights by nearly 50 % and achieves a maximum throughput of 7.992M MACs/s on an AMD Spartan-7 S15 FPGA.