Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators
ACM Transactions on Design Automation of Electronic Systems · 31.01.2024 · 29 (1) · 1-24
DOI: 10.1145/3631523 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 18.12.2023. Verfasst von Wanqian Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Key Research Program of Frontier Sciences, CAS.
Abstract (Originalsprache)
The resistive random-access memory (ReRAM) has widely been used to accelerate convolutional neural networks (CNNs) thanks to its analog in-memory computing capability. ReRAM crossbars not only store layers’ weights, but also perform in-situ matrix-vector multiplications which are core operations of CNNs. To boost the performance of ReRAM-based CNN accelerators, crossbars can be duplicated to explore more intra-layer parallelism. The crossbar allocation scheme can significantly influence both the computing throughput and bandwidth requirements of ReRAM-based CNN accelerators. Under the resource constraints (i.e., crossbars and memory bandwidths), how to find the optimal number of crossbars for each layer to maximize the inference performance for an entire CNN is an unsolved problem. In this work, we find the optimal crossbar allocation scheme by mathematically modeling the problem as a constrained optimization problem and solving it with a dynamic programming based solver. Experiments demonstrate that our model for CNN inference time is almost precise, and the proposed framework can obtain solutions with near-optimal inference time. We also emphasize that communication (i.e., data access) is an important factor and must also be considered when determining the optimal crossbar allocation scheme.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Key Research Program of Frontier Sciences, CAS
- Strategic Priority Research Program of CAS
- Innovation Funding of ICT, CAS
Zitieren
APA
Li, W., Han, Y., & Chen, X. (2024). Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators. ACM Transactions on Design Automation of Electronic Systems, 29(1), 1-24. https://doi.org/10.1145/3631523
Vancouver
Li W, Han Y, Chen X. Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators. ACM Transactions on Design Automation of Electronic Systems. 2024;29(1):1-24. doi:10.1145/3631523
BibTeX
@article{Li2024,
author = {Li, Wanqian and Han, Yinhe and Chen, Xiaoming},
title = {Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators},
journal = {ACM Transactions on Design Automation of Electronic Systems},
year = {2024},
volume = {29},
number = {1},
pages = {1--24},
doi = {10.1145/3631523}
}
EUVIMED