Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

Guardat en:
Dades bibliogràfiques
Publicat a:Symmetry vol. 17, no. 9 (2025), p. 1409-1426
Autor principal: Kacmaz Semih
Altres autors: Haas, Roland, Huerta, E A
Publicat:
MDPI AG
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3254649207
003 UK-CbPIL
022 |a 2073-8994 
024 7 |a 10.3390/sym17091409  |2 doi 
035 |a 3254649207 
045 2 |b d20250101  |b d20251231 
084 |a 231635  |2 nlm 
100 1 |a Kacmaz Semih  |u Department of Physics, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA 
245 1 |a Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves <inline-formula>L1</inline-formula> and <inline-formula>L∞</inline-formula> errors of <inline-formula>4.54×10−7</inline-formula> and <inline-formula>3.44×10−6</inline-formula>, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations. 
653 |a Accuracy 
653 |a Relativistic effects 
653 |a Neutrons 
653 |a Neutron stars 
653 |a Artificial neural networks 
653 |a Supercomputers 
653 |a Numerical analysis 
653 |a Hydrodynamics 
653 |a Theory of relativity 
653 |a Machine learning 
653 |a Performance evaluation 
653 |a Numerical methods 
653 |a Data points 
653 |a Simulation 
653 |a Datasets 
653 |a Graphics processing units 
653 |a Equations of state 
653 |a Neural networks 
653 |a Optimization 
653 |a Inference 
653 |a Variables 
653 |a Spacetime 
653 |a Methods 
653 |a Algorithms 
653 |a Fluid mechanics 
653 |a Parameter estimation 
700 1 |a Haas, Roland  |u Department of Physics, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA 
700 1 |a Huerta, E A  |u Department of Physics, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA 
773 0 |t Symmetry  |g vol. 17, no. 9 (2025), p. 1409-1426 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3254649207/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3254649207/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3254649207/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch