Reducing the memory usage of Lattice-Boltzmann schemes with a DWT-based compression

02/20/2023
by   Clément Flint, et al.
0

This paper presents a new solution to address the challenge of increasing memory usage in high-performance computing simulations of Lattice-Bolzmann or Finite-Volume schemes.Our approach utilises a lossy compression scheme based on the Discrete Wavelet Transform (DWT) to achieve high compression ratios while preserving the accuracy of the simulation.Our evaluation on two different FV/LBM schemes demonstrates that the approach can reduce memory usage by several orders of magnitude.

READ FULL TEXT

page 8

page 9

page 13

page 16

page 17

page 18

research
04/13/2023

Thread-safe lattice Boltzmann for high-performance computing on GPUs

We present thread-safe, highly-optimized lattice Boltzmann implementatio...
research
05/25/2017

Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks

Computational Fluid Dynamics (CFD) is a hugely important subject with ap...
research
09/16/2021

SEACOW: Synopsis Embedded Array Compression using Wavelet Transform

Recently, multidimensional data is produced in various domains; because ...
research
01/14/2022

Finite Difference formulation of any lattice Boltzmann scheme

Lattice Boltzmann schemes rely on the enlargement of the size of the tar...
research
10/23/2015

FIESTA 4: optimized Feynman integral calculations with GPU support

This paper presents a new major release of the program FIESTA (Feynman I...
research
03/05/2020

Order-Preserving Key Compression for In-Memory Search Trees

We present the High-speed Order-Preserving Encoder (HOPE) for in-memory ...
research
05/28/2021

High accuracy analysis of adaptive multiresolution-based lattice Boltzmann schemes via the equivalent equations

Multiresolution provides a fundamental tool based on the wavelet theory ...

Please sign up or login with your details

Forgot password? Click here to reset