Originally posted by brent
View Post
Announcement
Collapse
No announcement yet.
Airlie Exploring Possibility Of VA-API On Top Of Vulkan Video
Collapse
X
-
I'm often pleased reading these articles because projects like Zink show that it is reasonable to build other higher-level graphics APIs on top of Vulkan, while also properly showing that being a compliant and performant implementation is far from a forgone conclusion. When reading about the initial bring-up of Vulkan Video, I wondered if VA-API could be implemented on top of it, but also had no idea if the models were compatible. Seeing this being tackled so soon is a pleasant surprise.
An interesting consequence of this could be working hardware accelerated video decoding for Firefox on Wayland using the NVIDIA proprietary driver.
- Likes 6
Comment
-
Originally posted by brent View PostI'm often irritated because people tend to assume that everything becomes better, faster and more efficient just because Vulkan is involed. Spoiler: this is, in general, not true. Vulkan has strengths in specific use-cases. In many use cases, Vulkan does not have any or no significant advantages as far as performance and efficiency are considered. Video decode acceleration is one of these use cases. A unified API ecosystem still is advantageous for interoperability, though.
Comment
-
Originally posted by Developer12 View PostThis is blatantly (if not universally) false, given recent results with zink+vulkan running significantly faster than native opengl.
And what about output fidelity? Until Zink is consistently producing the same output as native OpenGL, it's also a bit unfair to compare its performance.
There might be good reasons why Zink could offer better performance, but you'd generally expect that stacking an OpenGL layer atop a Vulkan layer would deliver worse performance.
Comment
Comment