Full-Stack Optimization for CAM-Only DNN Inference
De Lima JPC, Khan AA, Carro L, Castrillon J (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Institute of Electrical and Electronics Engineers Inc.
Conference Proceedings Title: Proceedings -Design, Automation and Test in Europe, DATE
Event location: Valencia, ESP
ISBN: 9798350348590
DOI: 10.23919/DATE58400.2024.10546805
Abstract
The accuracy of neural networks has greatly improved across various domains over the past years. Their ever-increasing complexity, however, leads to prohibitively high energy demands and latency in von-Neumann systems. Several computing-in-memory (CIM) systems have recently been proposed to overcome this, but trade-offs involving accuracy, hardware reliability, and scalability for large models remain a challenge. Additionally, for some CIM designs, the activation movement still requires considerable time and energy. This paper explores the combination of algorithmic optimizations for ternary weight neural networks and associative processors (APs) implemented using racetrack memory (RTM). We propose a novel compilation flow to optimize convolutions on APs by reducing their arithmetic intensity. By leveraging the benefits of RTM-based APs, this approach substantially reduces data transfers within the memory while addressing accuracy, energy efficiency, and reliability concerns. Concretely, our solution improves the energy efficiency of ResNet-18 inference on ImageNet by 7.5× compared to crossbar in-memory accelerators while retaining software accuracy.
Involved external institutions
Technische Universität Dresden
Germany (DE)
Universidade Federal do Rio Grande do Sul (UFRGS)
Brazil (BR)
Germany (DE)
Universidade Federal do Rio Grande do Sul (UFRGS)
Brazil (BR)
How to cite
APA:
De Lima, J.P.C., Khan, A.A., Carro, L., & Castrillon, J. (2024). Full-Stack Optimization for CAM-Only DNN Inference. In Proceedings -Design, Automation and Test in Europe, DATE. Valencia, ESP: Institute of Electrical and Electronics Engineers Inc..
MLA:
De Lima, João Paulo C., et al. "Full-Stack Optimization for CAM-Only DNN Inference." Proceedings of the 2024 Design, Automation and Test in Europe Conference and Exhibition, DATE 2024, Valencia, ESP Institute of Electrical and Electronics Engineers Inc., 2024.
BibTeX: Download