NVIDIA OpenGL vs. Vulkan CPU Core Scaling For Linux Gaming

[phoronix]

Phoronix: NVIDIA OpenGL vs. Vulkan CPU Core Scaling For Linux Gaming

At the end of June I posted some Vulkan vs. OpenGL Linux Game CPU Core Scaling using RADV/RadeonSI with a Polaris graphics card. At that time I also carried out some NVIDIA CPU core scaling results in a Vulkan vs. OpenGL manner, but simply forgot to post those numbers until now...

http://www.phoronix.com/scan.php?page=news_item&px=NVIDIA-Linux-CPU-Scaling

[Azrael5]

now vulkan appears to be superior to opengl apis what I'm curious to know is how both the ones manage the physic engines.

[Jahimself]

Remember that OpenGL is more matured than Vulkan which is only at its early stage. But still the benchmarks tends to show Vulkan performs a lot better when correctly optimised, such in Talos Principle. Thread optimisations should come with time.

[starshipeleven]

opengl appears to be superior to vulkan apis what I'm curious to know is how both the ones manage the physic engines.

Afaik, neither do. Physics engines is computing, not rendering, so it either runs on CUDA or OpenCL or CPU (running like crap).

[microcode]

Those framerate ranges for The Talos Principle are great, very little variance between top and bottom framerate.

[bridgman]

opengl appears to be superior to vulkan apis what I'm curious to know is how both the ones manage the physic engines.

I don't understand your comment - isn't the Vulkan performance always higher than OpenGL in these tests (red line higher than blue line) ?

[humbug]

opengl appears to be superior to vulkan apis

you were just shown a wide selection of games where vulkan outperforms openGL in framerates and then you make this comment.

also Vulkan is more power efficient.

[humbug]

Thread optimisations should come with time.

also the fact that the framerate isn't scaling past x number of cores does not mean the game isn't using more. It often just means that the bottle neck is now elsewhere, E.g. GPU

[Azrael5]

I don't understand your comment - isn't the Vulkan performance always higher than OpenGL in these tests (red line higher than blue line) ?

You are right I've confused the colors.

[bridgman]

No worries, I did the same thing first time I looked. It was only the second time I read the article I started thinking "hey that doesn't make sense..."