Time-step interleaved weight reuse for LSTM neural network computing
- Title
- Time-step interleaved weight reuse for LSTM neural network computing
- Authors
- PARKNAEBEOM; 김율화; 안대현; 김태수; KIM, JAE JOON
- Date Issued
- 2020-08-11
- Publisher
- Association for Computing Machinery
- Abstract
- In Long Short-Term Memory (LSTM) neural network models, a weight matrix tends to be repeatedly loaded from DRAM if the size of on-chip storage of the processor is not large enough to store the entire matrix. To alleviate heavy overhead of DRAM access for weight loading in LSTM computations, we propose a weight reuse scheme which utilizes the weight sharing characteristics in two adjacent time-step computations. Experimental results show that the proposed weight reuse scheme reduces the energy consumption by 28.4-57.3% and increases the overall throughput by 110.8% compared to the conventional schemes.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/106068
- Article Type
- Conference
- Citation
- 2020 ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020, 2020-08-11
- 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.