Abstract
Bias-scalable analog computing is attractive for implementing machine learning (ML) processors with distinct power-performance specifications. For instance, ML implementations for server workloads are focused on higher computational throughput for faster training, whereas ML implementations for edge devices are focused on energy-efficient inference. In this paper, we demonstrate the implementation of bias-scalable approximate analog computing circuits using the generalization of the margin-propagation principle called shape-based analog computing (S-AC). The resulting S-AC core integrates several near-memory compute elements, which include: (a) non-linear activation functions; (b) inner-product compute circuits; and (c) a mixed-signal compressive memory, all of which can be scaled for performance or power while preserving its functionality. Using measured results from prototypes fabricated in a 180nm CMOS process, we demonstrate that the performance of computing modules remains robust to transistor biasing and variations in temperature. In this paper, we also demonstrate the effect of bias-scalability and computational accuracy on a simple ML regression task.
| Original language | English |
|---|---|
| Pages (from-to) | 312-322 |
| Number of pages | 11 |
| Journal | IEEE Journal on Emerging and Selected Topics in Circuits and Systems |
| Volume | 13 |
| Issue number | 1 |
| DOIs | |
| State | Published - Mar 1 2023 |
Keywords
- Analog approximate computing
- ReLU
- analog multiplier
- generalized margin-propagation
- machine learning
- memory DAC
- shape-based analog computing
Fingerprint
Dive into the research topics of 'Bias-Scalable Near-Memory CMOS Analog Processor for Machine Learning'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver