Zink Is Moving Closer To OpenGL 3.0 Support Over Vulkan

[phoronix]

Phoronix: Zink Is Moving Closer To OpenGL 3.0 Support Over Vulkan

Zink was one of the Mesa/Gallium3D innovations that saw mainline status in 2019 for offering OpenGL support atop Vulkan hardware drivers. While an interesting approach, so far only the dated OpenGL 2.1 support has been exposed but the Collabora-led effort is closing in on OpenGL 3.0 capabilities...

http://www.phoronix.com/scan.php?page=news_item&px=Zink-Closer-GL-3.0-On-Vulkan

[Britoid]

It'd be cool to see this eventually replace the OpenGL driver in Mesa.

[R41N3R]

Seems like I need to upgrade again to Mesa-git! Great to see Zink progressing, OpenGL 3.0 would be a nice milestone :-)

[log0]

It'd be cool to see this eventually replace the OpenGL driver in Mesa.

Only if you don't mind having (in some cases massively) lower performance. Such layers will never be as fast as a native implementation.

[Britoid]

Only if you don't mind having (in some cases massively) lower performance. Such layers will never be as fast as a native implementation.

I guess it depends in what you consider "native".

Are the existing OpenGL drivers native given they get converted to Gallum first? Vulkan is designed to be as close to hardware as possible without having hardware specific APIs. Once optimized, I expect the overhead of this to be extremely minimal.

[GruenSein]

Only if you don't mind having (in some cases massively) lower performance. Such layers will never be as fast as a native implementation.

Some years down the line when hardware will be much more capable and only legacy apps use OpenGL that might be totally OK and much easier than supporting OpenGL natively. For now, I agree with you, though.

[Veto]

I guess the killer use case is virtualization. If the host exposes a virtual Vulkan hardware to the guest it can implement OpenGL and DirectX on top of that with Zink and DXVK. That would be much more versatile than e.g. the current Virgil approach.

[mdedetrich]

Only if you don't mind having (in some cases massively) lower performance. Such layers will never be as fast as a native implementation.

Vulkan is pretty much as close to native as you can get for GPU's, its almost the equivalent for x86_64/32 for CPU's, the only thing lower would be GPU microcode.

The whole point of Vulkan is it being a lower level driver that is portable amongst GPU's, the whole issue with the current situation is that API's like OpenGL/DirectX are very high level and don't give users that much control (they are also terrible when it comes to multithreading)

[geearf]

Only if you don't mind having (in some cases massively) lower performance. Such layers will never be as fast as a native implementation.

Why would using Vulkan as intermediate API be inherently slower than using Gallium3D? Neither goes directly from OGL to native, and Vulkan is not higher level.

[archsway]

It'd be cool to see this eventually replace the OpenGL driver in Mesa.

This is the OpenGL driver in Mesa, just with 10k lines of code for making Vulkan the backend.