On 18.07.2014 12:58, Dieter Nützel wrote:
Am 18.07.2014 05:07, schrieb Michel Dänzer:
On 17.07.2014 19:09, Christian König wrote:
Am 17.07.2014 12:01, schrieb Michel Dänzer:
[PATCH 5/5] drm/radeon: Use VRAM for indirect buffers on >= SI
I'm still not very keen with this change since I still don't understand the reason why it's faster than with GTT. Definitely needs more testing on a wider range of systems.
Sure. If anyone wants to give this patch a spin and see if they can measure any performance difference, good or bad, that would be interesting.
Maybe limit it to APUs for now?
But IIRC, CPU writes to VRAM vs. write-combined GTT are actually an even bigger win with dedicated GPUs than with the Kaveri built-in GPU on my system. I suspect it may depend on the bandwidth available for PCIe vs. system memory though.
Michel,
please, please do NOT change anything on this!;-) You all know that I currently can only run this on my poor Duron 1800 with RV730 (AGP), but...
With this all 'objview' demos (mesa-demos) run at 60 fps (vsync), even with chip set/CPU power management enabled (athcool on).
If I set vblank_mode=0 the slowest GreatLakesBiplaneHP.obj run at ~100 fps (~16 fps before) => 6x speedup. (Even 5 planes run at 30 fps) - Wow!!!
That's great, but note that the disputed change above only has an effect with SI or newer GPUs, i.e. none with yours.
I suspect that speedup is because the app ends up using effectively static vertex/index buffers, which are now in VRAM instead of in GTT due to my Mesa changes.
Overall X/Kwin eXperience is much better. Let me know which benchmarks you need.
I'm not looking for anything in particular, basically anything where you care about performance. E.g. the usual suspects in PTS.
BTW Do anyone know how I can override BIOS GTT settings? I can only set 256 MB max. - BIOS patching?
Your AGP bridge hardware might not support more.
With agpmode=-1 I can run with 1024 MB GTT
What effect does that have on performance? I'm not sure if AGP provides any benefit for GPUs with PCIe GART.