A TensorFlow Simulation Framework for Scientific Computing of Fluid Flows on Tensor Processing Units

TL;DR

This paper presents a novel CFD simulation framework built on TensorFlow for fluid flow prediction on TPUs, demonstrating high accuracy and scalable performance for turbulent flow simulations.

Contribution

It introduces a TPU-optimized CFD framework using TensorFlow that efficiently solves Navier-Stokes equations for turbulent flows, with validated accuracy and scalability.

Findings

Achieves good statistical agreement with reference solutions

Demonstrates linear weak scaling and superlinear strong scaling on TPU v3

Validates turbulent flow simulations with canonical cases

Abstract

A computational fluid dynamics (CFD) simulation framework for fluid-flow prediction is developed on the Tensor Processing Unit (TPU) platform. The TPU architecture is featured with accelerated dense matrix multiplication, large high bandwidth memory, and a fast inter-chip interconnect, making it attractive for high-performance scientific computing. The CFD framework solves the variable-density Navier-Stokes equation using a low-Mach approximation, and the governing equations are discretized by a finite-difference method on a collocated structured mesh. It uses the graph-based TensorFlow as the programming paradigm. The accuracy and performance of this framework is studied both numerically and analytically, specifically focusing on effects of TPU-native single precision floating point arithmetic. The algorithm and implementation are validated with canonical 2D and 3D Taylor-Green vortex simulations. To demonstrate the capability for simulating turbulent flows, simulations are conducted for two configurations, namely decaying homogeneous isotropic turbulence and a turbulent planar jet. Both simulations show good statistical agreement with reference solutions. The performance analysis shows a linear weak scaling and a superlinear strong scaling up to a full TPU v3 pod with 2048 cores.