Am 17.07.2014 12:01, schrieb Michel D?nzer: > In order to try and improve X(Shm)PutImage performance with glamor, I > implemented support for write-combined CPU mappings of BOs in GTT. > > This did provide a nice speedup, but to my surprise, using VRAM instead > of write-combined GTT turned out to be even faster in general on my > Kaveri machine, both for the internal GPU and for discrete GPUs. > > However, I've kept the changes from GTT to VRAM separated, in case this > turns out to be a loss on other setups. > > Kernel patches: > > [PATCH 1/5] drm/radeon: Remove radeon_gart_restore() > [PATCH 2/5] drm/radeon: Pass GART page flags to > [PATCH 3/5] drm/radeon: Allow write-combined CPU mappings of BOs in > [PATCH 4/5] drm/radeon: Use write-combined CPU mappings of rings and
Those four are Reviewed-by: Christian K?nig <christian.koenig at amd.com> > [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. Maybe limit it to APUs for now? Regards, Christian. > > Mesa patches: > > [PATCH 1/5] winsys/radeon: Use separate caching buffer managers for > [PATCH 2/5] r600g/radeonsi: Use write-combined CPU mappings of some > [PATCH 3/5] r600g/radeonsi: Prefer VRAM for CPU -> GPU streaming > [PATCH 4/5] r600g,radeonsi: Use write-combined persistent GTT > [PATCH 5/5] r600g,radeonsi: Prefer VRAM for persistent mappings > _______________________________________________ > dri-devel mailing list > dri-devel at lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/dri-devel
