oneDNN VS femtovg

If you are talking about non-small matrix multiplication in MKL, is now in opensource as a part of oneDNN. It literally has exactly the same code, as in MKL (you can see this by inspecting constants or doing high-precision benchmarks).

For small matmul there is libxsmm. It may take tremendous efforts make something faster than oneDNN and libxsmm, as jit-based approach of https://github.com/oneapi-src/oneDNN/blob/main/src/gpu/jit/g... is too flexible: if someone finds a better sequence, oneDNN can reuse it without major change of design.

But MKL is not limited to matmul, I understand it...

For completeness, it looks like this question was posted to the oneDNN GitHub repo and the response was to stay tune for updates.

From the release note of oneDNN v2.5:

Intel are trying to support their oneAPI compute framework on Arm and IBM POWER and z/Architecture (s390x) but since they ever released only a single discrete GPU with the Xe architecture it's unclear whether they'll support Xe GPU compute on e.g. ARM https://github.com/oneapi-src/oneDNN

Femtovg (https://github.com/femtovg/femtovg) which uses OpenGL to render

Congrats! I don't want to diminish the accomplishment, but have you seen femtovg? It seems like it's probably well-aligned with your needs.

I'm currently using femtovg for vector graphics in my games, and I would like to get into bevy by porting one of my game prototypes using it to bevy.

I use femtovg It's a simple vector graphics engine having all the important features you probably want from a 2D rendering engine: simple shapes, images, text

https://github.com/femtovg/femtovg/pull/5

Before Power10 was done, IBM actually asked us Raptor users about proposals for useful machine code instructions to add to it. I replied that I’d like to have hardware UTF-8 de-/encoding but they wanted a more detailed proposal and I never got around to write it. I’m not even sure that this would be worthwhile, but I see UTF-8 de-/encoding everywhere in the code I write and would like it to approach memory read/write speeds.

I was very disappointed to learn that they had gone more proprietary with Power10 so I would not have been able to use those instructions anyway. What a pity!

In my actual code, I'm using a library called femtovg that is a Rust port of a C library for 2D rendering. But In the blog post I kept the example simple to keep it relevant for people who might want to use Web Workers + WASM for other things; didn't want to get hung up on femtovg for someone who had never heard of it. As you say, if you all you need to do is basic 2D manipulations of a canvas that are supported by the native API, then you likely don't need WASM.

You guys should also check out the femtovg project, a 2D rendering API that sixty fps relies on.

https://github.com/femtovg/femtovg

It's a decent starting point for trying to build your own toolkit.

I have recently added a wgpu backend but for now it lives in my fork https://github.com/adamnemecek/femtovg

run the demo with `cargo run --example wgpu_demo --release`.

Also join the femtovg discord https://discord.gg/V69VdVu

I'm involved with the femtovg project. We are definitely looking for contributors. Join the discord channel.

It's not a GUI framework but I'm involved with this project called femtovg, it's a Rust nanovg port. I've recently added a wgpu backend. Run the demo with cargo run --example wgpu_demo --release. Some people have been using it for their own UIs, e.g. tuix. I think that you should consider rolling your own GUI toolkit, it's not that bad and you'll appreciate the control.