Lettuce: PyTorch-Based Lattice Boltzmann Framework

Bedrunka, Mario; Wilde, Dominik; Kliemank, Martin; Reith, Dirk; Foysi, Holger; Krämer, Andreas

doi:10.1007/978-3-030-90539-2_3

Cited by 11 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The details of computation speed are reported in Table 1.The computation speeds reached over 900 MLUPs using an NVIDIA A100 with D3Q19 and MRT. The performance was much better than the PyTorch implementation with 150 MLUPs reported in [36]. Other popular LBM codes, e.g., the latest version of OpenLB [32], require over 200 cores CPUs to reach the same speed.…”

Section: Performance Tests On Parallel Platformsmentioning

confidence: 93%

See 1 more Smart Citation

Taichi-LBM3D: A Single-Phase and Multiphase Lattice Boltzmann Solver on Cross-Platform Multicore CPU/GPUs

Yang¹,

Yang

2022

Fluids

View full text Add to dashboard Cite

The success of the lattice Boltzmann method requires efficient parallel programming and computing power. Here, we present a new lattice Boltzmann solver implemented in Taichi programming language, named Taichi-LBM3D. It can be employed on cross-platform shared-memory many-core CPUs or massively parallel GPUs (OpenGL and CUDA). Taichi-LBM3D includes the single- and two-phase porous medium flow simulation with a D3Q19 lattice model, Multi-Relaxation-Time (MRT) collision scheme and sparse data storage. It is open source, intuitive to understand, and easily extensible for scientists and researchers.

show abstract

Section: Performance Tests On Parallel Platformsmentioning

confidence: 93%

“…The researchers could prototype their new algorithm rapidly and/or test their new applications on multicore CPUs or massively parallel GPUs. Interestingly enough, recent efforts were found to use PyTorch [36] to develop LBM models on GPUs, but these were limited to single-phase flow applications.…”

Section: Introductionmentioning

confidence: 99%

Taichi-LBM3D: A Single-Phase and Multiphase Lattice Boltzmann Solver on Cross-Platform Multicore CPU/GPUs

Yang¹,

Yang

2022

Fluids

View full text Add to dashboard Cite

show abstract

“…Consequently, other numerical simulation methods that directly model images of pore space, such as lattice Boltzmann method (LBM) or particle tracking, have increasingly been adopted to study dispersion in fluid flow (Bijeljic et al, 2011;Blunt et al, 2013;Hasan et al, 2020). Direct simulation methods can accurately compute macroscopic parameters of porous media, yet their substantial time and resource demands are significant limitations (Bedrunka et al, 2021;Kamrava, Im, et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

A Physics-Enhanced Neural Network for Estimating Longitudinal Dispersion Coefficient and Average Solute Transport Velocity in Porous Media

Meng,

Jiang,

et al. 2024

Preprint

View full text Add to dashboard Cite

Dispersion coefficients and the average solute transport velocity are pivotal for groundwater solute transport modeling. Accurately and efficiently determining these parameters is challenging due to difficulties in directly correlating them with pore-space structure. To address this issue, we introduced the Physics-enhanced Convolutional Neural Network-Transformer (PhysenCT-Net), an innovative model designed to concurrently estimate the longitudinal dispersion coefficient and average solute transport velocity in three-dimensional porous media. PhysenCT-Net exhibited excellent predictive performance on unseen testing datasets and significantly reduced computational demands. Comprehensive evaluations confirmed its robust generalization across various flow conditions and pore structures. Notably, the longitudinal dispersion coefficient predictions closely align with established empirical relationships involving flow velocity, affirming the model’s physical interpretability and potential to aid in simulating transport phenomena in porous media.

show abstract

“…In areas such as finance or healthcare, they are used to identify anomalies and provide predictions [16]. Scientific simulations may employ surrogate models to speed up computation [1]. The diversity of these application domains and of the algorithms used in each area is leading to a Cambrian explosion [8] of specialized systems that try to accelerate computations while fitting specific domain requirements.…”

Section: Introductionmentioning

confidence: 99%

SODA Synthesizer

Agostini

Limaye

Minutoli

et al. 2022

Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design

View full text Add to dashboard Cite

The SODA Synthesizer is an open-source, modular, end-to-end hardware compiler framework. The SODA frontend, developed in MLIR, performs system-level design, code partitioning, and highlevel optimizations to prepare the specifications for the hardware synthesis. The backend is based on a state-of-the-art high-level synthesis tool and generates the final hardware design. The backend can interface with logic synthesis tools for field programmable gate arrays or with commercial and open-source logic synthesis tools for application-specific integrated circuits. We discuss the opportunities and challenges in integrating with commercial and open-source tools both at the frontend and backend, and highlight the role that an end-to-end compiler framework like SODA can play in an open-source hardware design ecosystem.

show abstract

Lettuce: PyTorch-Based Lattice Boltzmann Framework

Cited by 11 publications

References 35 publications

Taichi-LBM3D: A Single-Phase and Multiphase Lattice Boltzmann Solver on Cross-Platform Multicore CPU/GPUs

Taichi-LBM3D: A Single-Phase and Multiphase Lattice Boltzmann Solver on Cross-Platform Multicore CPU/GPUs

A Physics-Enhanced Neural Network for Estimating Longitudinal Dispersion Coefficient and Average Solute Transport Velocity in Porous Media

SODA Synthesizer

Contact Info

Product

Resources

About