Rust-CUDA VS wgpu

The Rust-CUDA project just recently started up again [0], I've started digging into it a little bit and am hoping to contribute to it since the summers are a little slower for me.

[0] https://github.com/rust-gpu/rust-cuda

Source code [here](https://github.com/ihawn/RTracer) if anyone is interested in taking a look or giving feedback. As a side question, does anyone have any general advise on getting GPU compute working with rust? I tried [this project](https://github.com/Rust-GPU/Rust-CUDA) but had a bunch of issues (And it doesn't look like an active repo anyways)

You have this https://github.com/Rust-GPU/Rust-CUDA

What I'm trying to do is check out https://github.com/Rust-GPU/Rust-CUDA for a class project.

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...