FluidX3D [FLUID SIMULATION] 65536 Particles in Real Time @ProjectPhysX

Uploaded May 2018 | Updated September 2026, 1 week ago

FluidX3D is a GPU-accelerated real time 3D fluid simulation based on the lattice Boltzmann method.

I've added some upgrades, namely the one-step-pull algorithm (OS-Pull) for a combined streaming-and-collide step which cuts VRAM access in half.
Particles are also calculated on the GPU. They don't impact performance much (less than 1%), since 65536 is a small number compared to 256x128x128 LBM nodes. Furthermore, if only the particle positions have to be sent over PCI-e to the CPU for graphics instead of the entire velocity field, it doubles the calculation steps per second, because then the GPU does not have to wait idle until the slow data transfer is done.

For more information about FluidX3D and my other projects, visit
projectphysx.de

Music: CMA - You're Not Alone

FluidX3D [FLUID SIMULATION] 65536 Particles in Real Time

FluidX3D [FLUID SIMULATION] Rocket Nozzle Simulation

Lightning fast CFD free and accessible for everyone - 2 years of FluidX3D on GitHub

The raindrop again but with 8 billion (!) cells in 512GB GPU memory

PhysX3D [GRAVITY SIMULATION] Ulysses slingshot on November 4th 2098

$Combined scientific CFD simulation and interactive raytracing with OpenCL (IWOCL & SYCLcon 2022) This is my IWOCL & SYCLcon 2022 technical talk. Extended Abstract: https://www.researchgate.net/publication/360501260_Combined_scientific_CFD_simulation_and_interactive_raytracing_with_OpenCL Slides: https://www.iwocl.org/wp-content/uploads/06-presentation-iwocl-syclcon-2022-lehmann.pdf 0:00 Intro & Demos 4:16 Basic Idea 6:54 Lattice Boltzmann CFD 8:35 Benchmarks & Efficiency 11:33 Application 12:37 Graphics with OpenCL 23:06 Conclusions 24:16 More Demos!! 26:09 Outro One of the main uses for OpenCL is compute applications where rendering is done externally. However separating simulation and rendering has many disadvantages, especially the slowdown caused by copying data from device to host, and needing to store raw data on the hard drive. A much faster approach is to implement both simulation and rendering in OpenCL. The rendering kernels have direct read-only access to the raw simulation data in ultra-fast GPU memory. This eliminates almost all PCIe data transfer, allowing for interactive visualization in real time while the simulation is running. Although OpenCL does not have existing functionality for graphical rendering, being a general compute language, it allows for implementing an entire graphics engine. On top, specific low-level optimizations make this OpenCL graphics engine outperform any existing rendering solution for this scenario, enabling fluid raytracing in real time on even non-RTX GPUs. This is demonstrated with the software FluidX3D [1]. First I introduce the lattice Boltzmann method for simulating physically accurate fluid flow and discuss optimizations: Being a memory-bound algorithm, coalesced memory access is key. This is achieved through AoS data layout and the one-step-pull LBM streaming scheme. One-step-pull leverages that misaligned read penalty is much smaller than misaligned write penalty on most GPUs. Roofline analysis shows that with these optimizations, the LBM runs at 100% efficiency on the fastest GPUs [2]. For free surface flows, the LBM is extended with an efficient Volume-of-Fluid (VoF) implementation [3]. This allows covering new grounds in science: FluidX3D has been used to simulate more than 1600 raindrop impacts to evaluate how microplastics transition from the ocean surface into the atmosphere [4]. Rasterization on the GPU is parallelized not over pixels but lines/triangles instead. Each line/triangle is transformed from 3D to 2D screen coordinates and then rasterized onto the frame (integer array) with Bresenham [5] and z-buffer. The raytracing graphics are based on a combination of fast ray-grid traversal and marching-cubes, leveraging that the computational grid from the LBM already is an ideal acceleration structure for raytracing. The idea is simple: Through each pixel on screen, shoot a reverse light ray out of the camera and see where it intersects with a surface in the scene. Then (recursively) calculate reflected/refracted rays and mix colors. If a ray doesnt intersect anything, its color is determined by the skybox. With mesh surfaces consisting of triangles, computation time quickly becomes a problem, as all triangles have to be tested for intersection. To overcome this, an acceleration structure is required. While games often use a bounding volume hierarchy, the LBM already provides an ideal alternative acceleration structure: the simulation grid. The corresponding algorithm is called ray-grid traversal: When a ray shoots through the 3D grid, intersections with the surface only have to be checked for at each traversed grid cell rather than the entire grid. Triangles are generated on-the-fly with marching-cubes and ray-triangle intersections are checked with Möller-Trumbore. If an intersection has been found, the normals are calculated on the 8 grid points spanning the cell, and are trilinearly interpolated to the intersection. The interpolated surface normal makes the raytraced surface appear smooth. On the GPU, the ray(s) for each pixel are computed in parallel. It is important how to align the OpenCL workgroups: best performance is achieved for 8x8 pixel tiles; this is about 50% faster than 64x1 tiles, because all rays of the workgroup are more likely to traverse the same grid cells, improving memory broadcasting. For marching-cubes, the algorithm by Paul Bourke [6] is implemented in OpenCL. Table size is reduced to 1/8. The Möller-Trumbore algorithm [7] is implemented branchless. This raytracing implementation is fast enough to run in real time for even the largest lattice dimensions that fit into GPU memory. This is demonstrated on the most realistic simulation of an impacting raindrop ever done [8]. [1] https://doi.org/10.15495/EPub_UBT_00005400 [2] https://arxiv.org/abs/2112.08926 [3] https://doi.org/10.3390/computation10020021 [4] https://doi.org/10.1186/s43591-021-00018-8 [5] https://doi.org/10.1147/sj.41.0025 [6] http://paulbourke.net/geometry/polygonise/ [7] https://doi.org/10.1080/10867651.1997.10487468 [8] https://youtu.be/1g_zFsvScME$

Visualizing 144 TeraByte of CFD data for fun

hw-smi - a minimal, cross-compatible CPU/GPU telemetry monitor

PhysX3D [GRAVITY SIMULATION] Extreme Performance

Dr. Moritz Lehmann |

FluidX3D [FLUID SIMULATION] 65536 Particles in Real Time