On 10/1/18 8:23 PM, Marek Olšák wrote:
What improvement do you get from this?
Possibly less HTILE decompressions if small surfaces don't support TC-compatible HTILE. RADV has some restrictions, like mipmaps and MSAA.
I didn't benchmark anything though.
Thanks, Marek On Fri, Sep 28, 2018 at 10:27 AM Samuel Pitoiset <samuel.pitoi...@gmail.com> wrote:Like we disable DCC/CMASK for small color surfaces as well. Serious Sam 2017 creates a 1x1 depth surface and I think it should be faster to decompress compared to the benefit of fast clears. Signed-off-by: Samuel Pitoiset <samuel.pitoi...@gmail.com> --- src/amd/vulkan/radv_image.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/amd/vulkan/radv_image.c b/src/amd/vulkan/radv_image.c index 658ccb65be..64346aa340 100644 --- a/src/amd/vulkan/radv_image.c +++ b/src/amd/vulkan/radv_image.c @@ -923,7 +923,9 @@ radv_image_can_enable_fmask(struct radv_image *image) static inline bool radv_image_can_enable_htile(struct radv_image *image) { - return image->info.levels == 1 && vk_format_is_depth(image->vk_format); + return image->info.levels == 1 && + vk_format_is_depth(image->vk_format) && + image->info.width * image->info.height >= 8 * 8; } VkResult -- 2.19.0 _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
_______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
