Uploaded March 2022 | Updated November 2026, 5 hours ago
With a novel "Esoteric-Pull" in-place streaming scheme, combined with FP32/FP16 mixed precision, the memory requirements for the Volume-of-Fluid lattice Boltzmann method is cut down from 181 to 67 Bytes/Node, about 1/3 of vanilla LBM.
This enables colossal resolutions. The simulation in the video is a d = 7 mm diameter terminal velocity (9.55 m/s) raindrop impact (D3Q19 SRT) at 20° inclination, simulated for 1.5 milliseconds. The box is 5d x 5d x 4.25d and the pool height is 2d. Velocity, density and fluid mass are solved at 253 million lattice points (668 x 668 x 568). The simulation requires 16 GB video memory. For reproducibility: The dimensionless numbers for this setup are Re = 63618, We = 8864, Fr = 36.44, Ca = 0.1393, Bo = 6.674.
Raytracing is done at 2560x1440 pixel resolution with 1-10 rays per pixel; 305 frames are generated. There was no more VRAM for a larger frame buffer. Combined simulation and rendering time is 50 minutes, of which simulation time alone is about 5 minutes.
Raindrop simulations: doi.org/10.1186/s43591-021-00018-8
Volume-of-Fluid: doi.org/10.3390/computation10020021
Esoteric-Pull: doi.org/10.3390/computation10060092
FP32/FP16 mixed precision: researchgate.net/publication/362275548_Accuracy_and_performance_of_the_lattice_Boltzmann_method_with_64-bit_32-bit_and_customized_16-bit_number_formats
FluidX3D: doi.org/10.15495/EPub_UBT_00005400
The simulation software used is FluidX3D, an OpenCL implementation of the lattice Boltzmann method. FluidX3D runs at peak hardware efficiency on the worlds fastest data-center GPUs (8799/5232 MLUPs/s on the Nvidia A100/V100 @ D3Q19 SRT FP32), on gaming GPUs and CPUs and it even runs my smartphone.
The rendering is done by FluidX3D as well, now with raytracing. Simulated light rays from the camera traverse the LBM lattice and check for intersections with the triangles that marching-cubes generates on-the-fly from the isovalues. Triangles never leave registers.
The 3D lattice that the LBM provides already is one of the ideal acceleration structures for raytracing. Any ray only has to check for possible intersections with iso-surface triangles contained within the traversed grid cells. This makes it - when the lattice is not too large - even run in real time on non-RTX GPUs.
FluidX3D is now built entirely on my open source OpenCL-Wrapper, reducing the entire code on the C++ side to about half. If you want to get into OpenCL yourself, look no further: github.com/ProjectPhysX/OpenCL-Wrapper
#FluidX3D #OpenCL #Raytracing #GPU #LBM
With a novel "Esoteric-Pull" in-place streaming scheme, combined with FP32/FP16 mixed precision, the memory requirements for the Volume-of-Fluid lattice Boltzmann method is cut down from 181 to 67 Bytes/Node, about 1/3 of vanilla LBM.
This enables colossal resolutions. The simulation in the video is a d = 7 mm diameter terminal velocity (9.55 m/s) raindrop impact (D3Q19 SRT) at 20° inclination, simulated for 1.5 milliseconds. The box is 5d x 5d x 4.25d and the pool height is 2d. Velocity, density and fluid mass are solved at 253 million lattice points (668 x 668 x 568). The simulation requires 16 GB video memory. For reproducibility: The dimensionless numbers for this setup are Re = 63618, We = 8864, Fr = 36.44, Ca = 0.1393, Bo = 6.674.
Raytracing is done at 2560x1440 pixel resolution with 1-10 rays per pixel; 305 frames are generated. There was no more VRAM for a larger frame buffer. Combined simulation and rendering time is 50 minutes, of which simulation time alone is about 5 minutes.
Raindrop simulations: doi.org/10.1186/s43591-021-00018-8
Volume-of-Fluid: doi.org/10.3390/computation10020021
Esoteric-Pull: doi.org/10.3390/computation10060092
FP32/FP16 mixed precision: researchgate.net/publication/362275548_Accuracy_and_performance_of_the_lattice_Boltzmann_method_with_64-bit_32-bit_and_customized_16-bit_number_formats
FluidX3D: doi.org/10.15495/EPub_UBT_00005400
The simulation software used is FluidX3D, an OpenCL implementation of the lattice Boltzmann method. FluidX3D runs at peak hardware efficiency on the worlds fastest data-center GPUs (8799/5232 MLUPs/s on the Nvidia A100/V100 @ D3Q19 SRT FP32), on gaming GPUs and CPUs and it even runs my smartphone.
The rendering is done by FluidX3D as well, now with raytracing. Simulated light rays from the camera traverse the LBM lattice and check for intersections with the triangles that marching-cubes generates on-the-fly from the isovalues. Triangles never leave registers.
The 3D lattice that the LBM provides already is one of the ideal acceleration structures for raytracing. Any ray only has to check for possible intersections with iso-surface triangles contained within the traversed grid cells. This makes it - when the lattice is not too large - even run in real time on non-RTX GPUs.
FluidX3D is now built entirely on my open source OpenCL-Wrapper, reducing the entire code on the C++ side to about half. If you want to get into OpenCL yourself, look no further: github.com/ProjectPhysX/OpenCL-Wrapper
#FluidX3D #OpenCL #Raytracing #GPU #LBM

![PhysX3D [GRAVITY SIMULATION] Stereoscopic 3D Graphics Preview
Ich habe in meine hocheffiziente Java-Grafikausgabe stereoskopisches 3D Rendering integriert. Jeder Frame wird dabei aus zwei leicht unterschiedlichen Kameraperspektiven berechnet, was in Sachen Framerate etwa doppelt so lange dauert, wie das Rendern eines normalen 2D -Frames. Beide Bilder werden nebeneinander auf dem Display ausgegeben. Der Effekt ist wirklich atemberaubend, gerade eben bei so dreidimensionalen Dingen, wie den Umlaufbahnen von Planeten, Monden und Asteroiden. Und weil ich alles selbst programmiert habe, kann ich einstellen, wie weit die Kameras auseinander sind, also wie stark der 3D-Effekt ist, und wie weit die beiden Frames von einander verschoben sind, d.h. wie weit das Bild aus der Displayebene herauskommt oder wie tief es im Display erscheint.
Mehr Informationen auf: http://www.projectphysx.de
Song: Disfigure - Blank [NCS Release] PhysX3D [GRAVITY SIMULATION] Stereoscopic 3D Graphics Preview](https://i.ytimg.com/vi/N9gWOj8UVTU/mqdefault.jpg)




![PhysX3D [GRAVITY SIMULATION] Portraits of the Planets
Es wurde wirklich Zeit, die Rotation von Himmelskörpern in PhysX3D einzubauen. Die dazu notwendigen Daten für die Planeten unseres Sonnensystems zu bekommen stellte sich als Herausforderung heraus. Die Inklination der Rotationsachse und die Rotationsperiode zu finden war leicht, aber um die Rotationsachse korrekt definieren zu können, wird noch einen weiterer Winkel benötigt: die Rektaszension.
Außerdem hat Saturn seine charakteristischen Ringe bekommen.
Mehr Informationen auf: http://www.projectphysx.de
Musik: John Murphy - Sunshine (Adagio in d Minor) PhysX3D [GRAVITY SIMULATION] Portraits of the Planets](https://i.ytimg.com/vi/O1cLkJP2nfk/mqdefault.jpg)



