Jack12xl
Ahh thanks for the detailed reply ! The truth is, after I saw your explanation, it seems I misunderstood the `@ti.data_oriented`. In the first place I simply regard it as...
Guess we should remove all the ti.f32 ?
It turns out the `solvePDE` takes too much time
BiMocq velocity during doubleAdvect didn't apply ...
- [ ] numerical benchmark camparisons for different Projection methods
- [x] Add cache read
- [x] Abstract emitter
- [x] Support different grid size with same screen size
- [x] abstract renderer
Make it a real smoke simulator: - [x] Add temperature and advect - [x] Add bouyancy force