Abstract
Leveraging the ReRAM crossbar-based In-Memory-Computing (IMC) to accelerate single task DNN inference has been widely studied. However, using the ReRAM crossbar for continual learning has not been explored yet. In this work, we propose XST, a novel crossbar column-wise sparse training framework for continual learning. XST significantly reduces the training cost and saves inference energy. More importantly, it is friendly to existing crossbar-based convolution engine with almost no hardware overhead. Compared with the state-of-the-art CPG method, the experiments show that XST's accuracy achieves 4.95 % higher accuracy. Furthermore, XST demonstrates 5.59 × training speedup and 1.5 × inference energy-saving.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 |
| Editors | Cristiana Bolchini, Ingrid Verbauwhede, Ioana Vatajelu |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 48-51 |
| Number of pages | 4 |
| ISBN (Electronic) | 9783981926361 |
| DOIs | |
| State | Published - 2022 |
| Externally published | Yes |
| Event | 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 - Virtual, Online, Belgium Duration: Mar 14 2022 → Mar 23 2022 |
Publication series
| Name | Proceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 |
|---|
Conference
| Conference | 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 |
|---|---|
| Country/Territory | Belgium |
| City | Virtual, Online |
| Period | 3/14/22 → 3/23/22 |
Bibliographical note
Publisher Copyright:© 2022 EDAA.
Keywords
- Continual Learning
- In-Memory-Computing
- Sparse Learning
