AI Article Synopsis
- In-memory computing helps us understand complicated physical systems better than regular computers, but has problems with noise and errors that can make it less reliable.
- The authors created a new circuit design that turns the analog computing results (like one that uses less precise calculations) into digital results at the end, making it more accurate.
- They tested this new method with a special chip that showed it can solve scientific problems very well while using less power compared to traditional computers.
Article Abstract
In-memory computing represents an effective method for modeling complex physical systems that are typically challenging for conventional computing architectures but has been hindered by issues such as reading noise and writing variability that restrict scalability, accuracy, and precision in high-performance computations. We propose and demonstrate a circuit architecture and programming protocol that converts the analog computing result to digital at the last step and enables low-precision analog devices to perform high-precision computing. We use a weighted sum of multiple devices to represent one number, in which subsequently programmed devices are used to compensate for preceding programming errors. With a memristor system-on-chip, we experimentally demonstrate high-precision solutions for multiple scientific computing tasks while maintaining a substantial power efficiency advantage over conventional digital approaches.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1126/science.adi9405 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!