|
The most egregious, and the one the bug report and failure in the cubemap
demo were about was introduced with intel_mipmap_pitch_align(), where a
"* 2" for the pitch calculation was lost. The base size < 32 case also
failed to align, which may have caused problems with render to texture.
Another bug would have broken 2x2/1x1 base mipmap levels by placing the
data where the hardware wouldn't look for it.
Other bugs remain with the layout of the small mipmap faces (hardware looks
for them in X,Y,Z,-X,-Y,-Z order along the bottom row, but we lay them out
X,-X,Y,-Y,Z,-Z).
|
|
mipmap pitches must account for the device alignment requirements, which
used to be fairly simple; just align to a 4-byte boundary. However, to allow
textures to be drawn to under TTM, they now need to be aligned to a 64-byte
boundary. Placing all of the alignment constraints in a single function
allows this new constraint to be applied uniformly.
There was some pitch constraining code in intel_miptree_create, but that was
modifying the pitch long after the miptree had been layed out, so it only
served to wreck the mipmap and cause rendering errors.
|