Published In
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Document Type
Pre-Print
Publication Date
7-2023
Subjects
Mathematical models, Heating systems, Deep learning, Computational modeling, Parallel processing -- Data models
Abstract
The inversion problem of partial differential equation plays a crucial role in cyber-physical systems applications. This paper presents a novel deep learning optimization approach to constructing a solver of heat equation inversion. To improve the computational efficiency in large-scale industrial applications, data and model parallelisms are incorporated on a platform of multiple GPUs. The advanced Ring-AllReduce architecture is harnessed to achieve an acceleration ratio of 3.46. Then a new multi-GPUs distributed optimization method GradReduce is proposed based on Ring-AllReduce architecture. This method optimizes the original data communication mechanism based on mechanical time and frequency by introducing the gradient transmission scheme solved by linear programming. The experimental results show that the proposed method can achieve an acceleration ratio of 3.84 on a heterogeneous system platform with two CPUs and four GPUs.
Rights
© Copyright the author(s)
Locate the Document
DOI
10.1109/TCAD.2023.3296370
Persistent Identifier
https://archives.pdx.edu/ds/psu/40576
Citation Details
Wang, Z., Yang, L., Lin, H., Zhao, G., Liu, Z., & Song, X. (2023). Distributed Deep Learning Optimization of Heat Equation Inverse Problem Solvers. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.
Description
This article has been accepted for publication in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. This is the author's version which has not been fully edited content may change prior to final publication. Citation information: DOI 10.1109/TCAD.2023.3296370