MicroSim: A high-performance phase-field solver based on CPU and GPU implementations

被引:1
|
作者
Dutta, Tanmay [1 ]
Mohan, Dasari [2 ,5 ]
Shenoy, Saurav [3 ]
Attar, Nasir [4 ]
Kalokhe, Abhishek [4 ]
Sagar, Ajay [1 ]
Bhure, Swapnil [1 ]
Pradhan, Swaroop S. [2 ]
Praharaj, Jitendriya [1 ]
Mridha, Subham [1 ]
Kushwaha, Anshika [1 ]
Shah, Vaishali [6 ]
Gururajan, M. P. [5 ]
Shenoi, V. Venkatesh [4 ]
Phanikumar, Gandham [2 ]
Bhattacharyya, Saswata [3 ]
Choudhury, Abhik [1 ]
机构
[1] Indian Inst Sci, Dept Mat Engn, Bangalore 560012, Karnataka, India
[2] IIT Madras, Dept Met & Mat Engn, Chennai 600036, Tamil Nadu, India
[3] IIT Hyderabad, Dept Mat Sci & Met Engn, Hyderabad 502284, Telangana, India
[4] Pune Univ Campus, Ctr Dev Adv Comp, Pune 411007, Maharashtra, India
[5] IIT Bombay Powai, Dept Met Engn & Mat Sci, Mumbai 400076, Maharashtra, India
[6] Savitribai Phule Pune Univ, Dept Sci Comp Modeling & Simulat, Pune 411007, Maharashtra, India
关键词
Phase-field modeling; High-performance computing; CALPHAD; Solidification; Precipitation; OpenCL; CUDA; MPI; MODEL;
D O I
10.1016/j.commatsci.2024.113438
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The phase-field method has become a useful tool for the simulation of classical metallurgical phase transformations as well as other phenomena related to materials science. The thermodynamic consistency that forms the basis of these formulations lends to its strong predictive capabilities and utility. However, a strong impediment to the usage of the method for typical applied problems of industrial and academic relevance is the significant overhead with regard to the code development and know-how required for quantitative model formulations. In this paper, we report the development of an open-source phase-field software stack that contains generic formulations for the simulation of multiphase and multi-component phase transformations. The solvers incorporate thermodynamic coupling that allows the realization of simulations with real alloys in scenarios directly relevant to the materials industry. Further, the solvers utilize parallelization strategies using either multiple CPUs or GPUs to provide cross-platform portability and usability on available supercomputing machines. Finally, the solver stack also contains a graphical user interface to gradually introduce the usage of the software. The user interface also provides a collection of post-processing tools that allow the estimation of useful metrics related to microstructural evolution.
引用
收藏
页数:27
相关论文
共 50 条
  • [1] High performance CPU/GPU multiresolution Poisson solver
    Van Rees, Wim M.
    Rossinelli, Diego
    Hadjidoukas, Panagiotis
    Koumoutsakos, Petros
    PARALLEL COMPUTING: ACCELERATING COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), 2014, 25 : 481 - 490
  • [2] High Performance FFT Based Poisson Solver on a CPU-GPU Heterogeneous Platform
    Wu, Jing
    JaJa, Joseph
    IEEE 27TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2013), 2013, : 115 - 125
  • [3] qLD: High-performance Computation of Linkage Disequilibrium on CPU and GPU
    Theodoris, Charalampos
    Alachiotis, Nikolaos
    Low, Tze Meng
    Pavlidis, Pavlos
    2020 IEEE 20TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE 2020), 2020, : 65 - 72
  • [4] Orchestration of CPU and GPU Consumers for High-Performance Streaming Processing
    Rovnyagin, Mikhail M.
    Gukov, Aleksey D.
    Timofeev, Kirill, V
    Hrapov, Alexander S.
    Mitenkov, Roman A.
    PROCEEDINGS OF THE 2021 IEEE CONFERENCE OF RUSSIAN YOUNG RESEARCHERS IN ELECTRICAL AND ELECTRONIC ENGINEERING (ELCONRUS), 2021, : 623 - 626
  • [5] A high-performance matrix–matrix multiplication methodology for CPU and GPU architectures
    Vasilios Kelefouras
    A. Kritikakou
    Iosif Mporas
    Vasilios Kolonias
    The Journal of Supercomputing, 2016, 72 : 804 - 844
  • [6] High-performance Implementation of Parallel Semi-Implicit Method for Pressure Linked Equations Solver on CPU plus GPU Platform
    Xu, Qianting
    Li, Ruitian
    Xu, Minghai
    INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER, 2022, 182
  • [7] LRnLA Lattice Boltzmann Method: A Performance Comparison of Implementations on GPU and CPU
    Levchenko, Vadim
    Zakirov, Andrey
    Perepelkina, Anastasia
    PARALLEL COMPUTATIONAL TECHNOLOGIES, PCT 2019, 2019, 1063 : 139 - 151
  • [8] A CFD Heterogeneous Parallel Solver Based on Collaborating CPU and GPU
    Lai, Jianqi
    Tian, Zhengyu
    Li, Hua
    Pan, Sha
    3RD INTERNATIONAL CONFERENCE ON MECHANICAL AND AERONAUTICAL ENGINEERING (ICMAE 2017), 2018, 326
  • [9] An investigation of the performance of the colored Gauss-Seidel solver on CPU and GPU
    Yoon J.S.
    Jeon B.J.
    Choi H.G.
    Choi, Hyoung Gwon (hgchoi@seoultech.ac.kr), 1600, Korean Society of Mechanical Engineers (41): : 117 - 124
  • [10] A high-performance matrix-matrix multiplication methodology for CPU and GPU architectures
    Kelefouras, Vasilios
    Kritikakou, A.
    Mporas, Iosif
    Kolonias, Vasilios
    JOURNAL OF SUPERCOMPUTING, 2016, 72 (03): : 804 - 844