# ProjectPhysX/FluidX3D

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.

Repository: https://github.com/ProjectPhysX/FluidX3D
Canonical: https://ross.abutalabs.com/products/fluidx3d
Homepage: https://youtube.com/@ProjectPhysX
Language: C++
License: NOASSERTION
License Family: other
Topics: cfd, computational-fluid-dynamics, gpu, gpu-computing, lbm, opencl, high-performance-computing, hpc, simulation, fluid-simulation, fluid-solver, raytracing, interactive-visualization, physics, gpgpu, fluid-dynamics, lattice-boltzmann, benchmark, science, scientific-computing
Last push: 2026-08-23T09:02:44+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 72, longevity 100
- inputs: {"age_days": 1490, "days_push": 10, "days_rel": 111, "gap_med": 69.0, "n_releases_24m": 9}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5250, forks 472 (observed 2026-08-28T04:09:13.670801+00:00)

## What it is
FluidX3D is a high-performance lattice Boltzmann method computational fluid dynamics (CFD) application written in C++/OpenCL. It runs on all GPUs and CPUs with exceptional speed and memory efficiency, and includes interactive visualization and benchmarking capabilities.

## Use cases
- simulate fluid flow around objects on GPU
- run CFD simulations without expensive licenses
- benchmark GPU and CPU floating-point and memory performance
- visualize fluid dynamics interactively in 3D
- compute forces and torques on bodies in a flow
- run multi-GPU CFD simulations on a single machine
- voxelize STL meshes into simulation grids

## When to choose
- you need fast, memory-efficient lattice Boltzmann CFD on any GPU vendor via OpenCL
- you want free-for-non-commercial-use fluid simulation with interactive visualization
- you want to stress-test or benchmark GPUs/CPUs with a real scientific workload
- you need cross-vendor multi-GPU scaling on one node

## When to avoid
- you need commercial-use CFD without licensing restrictions (license is non-commercial only)
- you need general-purpose CFD with meshes, turbulence models, or heat/solver features beyond LBM
- you need a library to embed in your own code rather than a standalone application
- your environment lacks OpenCL support

## Facets
- artifact type: application
- maturity: active
- function: simulation, graphics, gpu-computing, benchmarking, data-visualization
- domain: simulation, graphics, gpu-computing, performance
- platform: cross-platform, windows, cpp
- tags: cfd, lattice-boltzmann, opencl, fluid-dynamics, hpc, fluid-simulation, gpgpu, multi-gpu, voxelization, raytracing, physics, scientific-computing, linux, macos, gpu

## Member repositories
- ProjectPhysX/FluidX3D (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:13.670801+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:59:33.948397+00:00, confidence not recorded.
  - readme: https://github.com/ProjectPhysX/FluidX3D (fetched 2026-08-28T04:09:13.670801+00:00, sha b1986f87dead)
  - homepage: https://youtube.com/@ProjectPhysX (fetched 2026-08-29T08:54:34.193578+00:00, sha 6635947985e2)
- Data as of 2026-08-30T08:39:29.467469+00:00.