AI Bibliography
AI Bibliography |
|
 |
 |
 |
|
Su, J.-W., Si, X., Chou, Y.-C., Chang, T.-W., Huang, W.-H., & Tu, Y.-N., et al.. 2020, 15.2 a 28nm 64kb inference-training two-way transpose multibit 6t sram compute-in-memory macro for ai edge chips. Paper presented at 2020 IEEE International Solid-State Circuits Conference-(ISSCC). |
| Resource type: Proceedings Article BibTeX citation key: Su2020 View all bibliographic details  |
Categories: Artificial Intelligence, Computer Science, Data Sciences, Engineering, General, Innovation, Military Science Subcategories: Big data, Cloud computing, Command and control, Edge AI, Internet of things, JADC2 Creators: Chang, Chou, Huang, Liu, Liu, Lu, others, Si, Su, Tu, Wang Publisher: Collection: 2020 IEEE International Solid-State Circuits Conference-(ISSCC) |
| Attachments |
| Abstract |
|
Many Al edge devices require local intelligence to achieve fast computing time (t AC ), high energy efficiency (EF), and privacy. The transfer-learning approach is a popular solution for Al edge chips, wherein data used to re-train the Al in the cloud is used to fine-tune (re-train) a few of the neural layers in edge devices. This enables the dynamic incorporation of data from in-situ environments or private information. Computing-in-memory (CIM) is a promising approach to improve EF for Al edge chips, existing CIM schemes support inference [1]-[5] with forward (FWD) propagation; however, they do not support training, requiring both FWD and backward (BWD) propagation, due to differences in weight-access flow for FWD and BWD propagation. As Fig. 15.2.1 shows, efforts to increase the precision of the input (IN), weight (W), and/or output (OUT) tend to degrade r AC and EF for training operations irrespective of scheme: digital FWD and BWD (DF-DB) or CIM-FWD-digital-BWD (CiMF-DB). This work develops a two-way transpose (TWT) SRAM-CIM macro supporting multibit MAC operations for FWD and BWD propagation with fast r ACand high EF within a compact area. The proposed scheme features (1) A TWT multiply cell (TWT-MC) with a high resistance to process variation; and (2) a small-offset gain-enhancement sense amplifier (SOGE-SA) to tolerate a small read margin. A 28nm 64Kb TWT SRAM-CIM macro was fabricated using a foundry-provided compact 6T-SRAM cell for SRAM-CIM devices supporting both inference and training operations for the first time. This macro also demonstrates the fastest t AC (3.8 - 21ns) and highest EF (7 - 61.1TOPS/w) for MAC operations using 2 - 8b inputs, 4 - 8b weights and 12 - 20b outputs.
|