Journal
TSINGHUA SCIENCE AND TECHNOLOGY
Volume 26, Issue 3, Pages 322-334Publisher
TSINGHUA UNIV PRESS
DOI: 10.26599/TST.2019.9010070
Keywords
deep neural network; Resistive Random Access Memory (ReRAM); simulation; accelerator; processing in memory
Categories
Funding
- Beijing Academy of Artificial Intelligence (BAAI) [BAAI2019ZD0403]
- Beijing Innovation Center for Future Chip, Tsinghua University
- Science and Technology Innovation Special Zone Project, China
Ask authors/readers for more resources
The XB-SIM* framework allows flexible configuration for ReRAM-crossbar-based CNN accelerators, including neural network training algorithms and mappers, to improve simulation speed and efficiency. The batch processing mode in the framework effectively applies computational concurrency to accelerate the simulation of ReRAM-crossbar circuit behaviors.
Resistive Random Access Memory (ReRAM)-based neural network accelerators have potential to surpass their digital counterparts in computational efficiency and performance. However, design of these accelerators faces a number of challenges including imperfections of the ReRAM device and a large amount of calculations required to accurately simulate the former. We present XB-SIM*, a simulation framework for ReRAM-crossbar-based Convolutional Neural Network (CNN) accelerators. XB-SIM* can be flexibly configured to simulate the accelerator's structure and clock-driven behaviors at the architecture level. This framework also includes an ReRAM-aware Neural Network (NN) training algorithm and a CNN-oriented mapper to train an NN and map it onto the simulated design efficiently. Behavior of the simulator has been verified by the corresponding circuit simulation of a real chip. Furthermore, a batch processing mode of the massive calculations that are required to mimic the behavior of ReRAM-crossbar circuits is proposed to fully apply the computational concurrency of the mapping strategy. On CPU/GPGPU, this batch processing mode can improve the simulation speed by up to 5.02x or 34.29x. Within this framework, comprehensive architectural exploration and end-to-end evaluation have been achieved, which provide some insights for systemic optimization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available