wgpu VS gfx

People have already mentioned Metal, but if you want cross platform, https://github.com/gfx-rs/wgpu has a vulkan-like API and cross compiles to all the various GPU frameworks. I believe it uses https://github.com/KhronosGroup/MoltenVK to run on Macs. You can also see the metal shader transpilation results for debugging.

This is in reference to [1].

[1] https://github.com/gfx-rs/wgpu/issues/6434

> Did they actually write that somewhere?

wgpu.rs for comments about "general purpose", "modern" is my own interjection, and [1] about the difference in priorities between the WGPU maintainers and (funnily enough) you.

I do believe a cross-platform and modern interface is difficult to square with high performance. I don't think either side is wrong to choose the priorities it has, but someone will be underserved. They probably need far more manpower/talent than they have to improve performance proportionately.

[1] https://github.com/gfx-rs/wgpu/discussions/5525

Sorry, I'll try to be clearer. QRhi docs[1] say "The Qt Rendering Hardware Interface is an abstraction for hardware accelerated graphics APIs, such as, OpenGL, OpenGL ES, Direct3D, Metal, and Vulkan." And PySide6 includes a (python) wrapper for QRhi[2]. Meanwhile, pygfx builds on wgpu-py[3] which builds on wgpu[4] which is a "is a cross-platform, safe, pure-rust graphics API. It runs natively on Vulkan, Metal, D3D12, and OpenGL".

So, from the standpoint of someone using PySide6, QRhi and pygfx seem to be alternative paths to the exact same underlying graphics APIs.

Thus my question: How do they compare? How should I make an informed comparison between them?

[1] https://doc.qt.io/qt-6/qrhi.html

[2] https://doc.qt.io/qtforpython-6/PySide6/QtWidgets/QRhiWidget...

[3] https://github.com/pygfx/wgpu-py/

[4] https://github.com/gfx-rs/wgpu

Everything will be using compute shaders for the foreseeable future. [WGPU](https://wgpu.rs/) abstracts that to work with WebGPU on browsers, DirectX/Vulkan on Windows, Metal on Mac, and Vulkan on Linux and Android. There may be opportunities to explore vendor-specific options like CUDA in the far future to leverage a further increase in performance, but compute shaders are portable and nearly as good.

Instead of building their GPU support atop CUDA/NVIDIA [0], I’m wondering why they didn’t instead go with WebGPU [1] via something like wgpu [2]. Using wgpu, they could offer cross-platform compatibility across several graphics API’s, covering a wide range of hardware including NVIDIA GeForce and Quadro, AMD Radeon, Intel Iris and Arc, ARM Mali, and Apple’s integrated GPU’s.

They note the following [0]:

> The GPU module is under active development. APIs and semantics might change between Codon releases.

The thing is, based on the current syntax and semantics I see, it’ll almost certainly need to change to support non-NVIDIA devices, so I think it might be a better idea to just go with WebGPU compute pipelines sooner rather than later.

Just my two pennies…

[0]: https://docs.exaloop.io/codon/advanced/gpu

[1]: https://www.w3.org/TR/webgpu

[2]: https://wgpu.rs

wgpu supports WebGPU: https://github.com/gfx-rs/wgpu :

> While WebGPU does not support any shading language other than WGSL, we will automatically convert your non-WGSL shaders if you're running on WebGPU.

https://github.com/gfx-rs/wgpu?tab=readme-ov-file#tracking-t...

For users of old school crate _gfx_ v0.18 I have PRs that will fix this issue without any additional changes (https://github.com/gfx-rs/gfx/pull/3791) though I suppose there aren't too many such users nowadays...

The gfx-backend-* READMEs each have a graphic explanation that is very useful. As others have said, the best way to handle this is with a flipped viewport, but I've never seen a satisfactory explanation as to why this doesn't mess with front/back faces and culling.

From https://github.com/gfx-rs/gfx

https://github.com/gfx-rs/gfx#hardware-abstraction-layer

Searching through the source code for wgpu and its dependencies, the error is coming from the gfx-rs DirectX 11 backend. I am guessing this is because of a limitation of DirectX 11. The easiest thing to do would probably be to try switching to the DirectX 12 or Vulkan backends.

Looks like they are using https://github.com/ggez/ggez which in turn uses https://github.com/gfx-rs/gfx for low-level drawing to the screen

There is also gfx-rs, which should be easier to use than opengl.

https://crates.io/crates/tiny-skia

You can put things together pretty easily with these libs. And they also let you skip the gpu boilerplate (I should note that tiny-skia works only in the CPU).

Lastly, you have shader programming (OpenGL, Vulkan, etc.). If you're writing "production code" you'll have to do some setting up of the GPU, and the actual graphics code will be in a separate shader language. Shader languages are similar to C but with restrictions that allow for a high level of parallism, making it extremely fast. If you want to get started with this I'd recommend playing around on a site like shadertoy[1] where you can start writing shaders right away. I haven't done much of this myself but as far as Rust goes I've seen a lot of references to the gfx crate:

https://crates.io/crates/gfx

I hope this helps

[1] https://www.shadertoy.com/