I thought GL_vs_VK wasn't really important to optimize, but heh? Looks
good to me!
Reviewed-by: Samuel Pitoiset
On 01/10/2018 11:14 PM, Dave Airlie wrote:
From: Dave Airlie
If the number of instances hasn't changed and we've already
emitted it, don't emit it again.
If the vertex shader is
Tested-by: Dieter Nützel
Woohoo,
this one shot 'smoketest' for the first time over 1200 fps on my system
(RX580, Xeon X3470, 4/8, ~3 GHz, 24 GB)!
Comming from ~1060-1080 fps.
6154 presents in 5.00069 seconds (FPS: 1230.63)
6183 presents in 5.00108 seconds (FPS: 1236.33)
6173 presents in 5.0
Reviewed-by: Bas Nieuwenhuizen
On Wed, Jan 10, 2018 at 11:14 PM, Dave Airlie wrote:
> From: Dave Airlie
>
> If the number of instances hasn't changed and we've already
> emitted it, don't emit it again.
>
> If the vertex shader is the same and the first_instance, vertex_offset
> haven't changed
From: Dave Airlie
If the number of instances hasn't changed and we've already
emitted it, don't emit it again.
If the vertex shader is the same and the first_instance, vertex_offset
haven't changed don't emit them again.
This increases the fps in GL_vs_VK -t 1 -m -api vk from around 40
to aroun
