compustream/src/glfw, branch master Hacky D2Q9 BGK LBM using compute shaders Update lattice multiple times per frame 2019-11-08T22:02:47+00:00 Adrian Kummerlaender 2019-11-08T22:02:47+00:00 d864699c5ddd744ee7376c0d752b6bbb771429a2 Controlled by `--lupf` _Lattice updates per frame_ MLUPS are now calculated and displayed. While performance is still bad compared to a optimized GPU implementation (such as [1] or [2]) this improves the situation. [1]: https://tree.kummerlaender.eu/projects/symlbm_playground/ [2]: https://code.kummerlaender.eu/boltzgen/about/ 
Controlled by `--lupf` _Lattice updates per frame_

MLUPS are now calculated and displayed.

While performance is still bad compared to a optimized GPU implementation (such
as [1] or [2]) this improves the situation.

[1]: https://tree.kummerlaender.eu/projects/symlbm_playground/
[2]: https://code.kummerlaender.eu/boltzgen/about/
Add LUPS reporting and fix glaring oversight 2019-02-25T21:08:58+00:00 Adrian Kummerlaender 2019-02-25T21:08:53+00:00 84666523e9a278ac95ca43dbaa534e8aaaf3ebd2 The GLFW window rendering loop used to dispatch the compute shaders was restricted to 60 FPS. I did not notice this because I never actually measured the computed lattice updates per seconds in addition to trying to push the GPU to its limits. Turns out the lattice sizes I commonly use can be updated 500 times per second comfortably… Now this looks more like the performance gains promised by GPU computation. 
The GLFW window rendering loop used to dispatch the compute shaders was
restricted to 60 FPS. I did not notice this because I never actually
measured the computed lattice updates per seconds in addition to trying
to push the GPU to its limits. Turns out the lattice sizes I commonly
use can be updated 500 times per second comfortably… Now this looks more
like the performance gains promised by GPU computation.
Tidy up wall drawing and geometry initialization 2019-02-22T21:24:30+00:00 Adrian Kummerlaender 2019-02-22T21:24:30+00:00 9779fd7484f7af6d10ae28ca3763c6d938c341e3 






Improvise interactive wall drawing
2019-02-22T20:49:07+00:00

Adrian Kummerlaender

2019-02-22T20:49:07+00:00

f0b536ac93b3a9a49dfff8a7637f09b153a3b955

Internal wall cells need to be disabled to prevent delayed propagation
of the reflected populations.

This is just quickly thrown together - both the visual drawing and the backend's
material handling remain to be improved.





Internal wall cells need to be disabled to prevent delayed propagation
of the reflected populations.

This is just quickly thrown together - both the visual drawing and the backend's
material handling remain to be improved.







Hacky mouse-based fluid interaction
2018-12-18T20:08:20+00:00

Adrian Kummerlaender

2018-12-18T20:08:20+00:00

6f6073be5de8c8598c4af7f38c90c3f83b5bf1bf












Keep track of window size in its wrapper class
2018-12-17T18:31:38+00:00

Adrian Kummerlaender

2018-12-17T18:31:38+00:00

f465b26a8aeac95cf7e0186a86ab1262dc771fb4












Hacky D2Q9 BGK LBM on GPU using GLSL compute shaders
2018-12-15T22:09:32+00:00

Adrian Kummerlaender

2018-12-15T22:09:32+00:00

44f5ac32a68a617f93704d44c4339f7db13b323e

Improvised on top of computicles's scaffolding.

Works in a world where _works_ is defined as "displays stuff on screen that invokes thoughts of fluid movement".





Improvised on top of computicles's scaffolding.

Works in a world where _works_ is defined as "displays stuff on screen that invokes thoughts of fluid movement".