fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-07 13:38:06 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

radv: Rework guard band calculation.

Browse source 
We want the guardband_x/y to be the largerst scalars such that each
viewport scaled by that amount is still a subrange of [-32767, 32767].

The old code has a couple of issues:
1) It used scissor instead of viewport_scissor, potentially taking into
   account a viewport that is too small and therefore selecting a scale
   that is too large.
2) Merging the viewports isn't ideal, as for example viewports with
   boundaries [0,1] and [1000, 1001] would allow a guardband scale of ~30k,
   while their union [0, 1001] only allows a scale of ~32.

The new code just determines the guardband per viewport and takes the minimum.

Signed-off-by: Bas Nieuwenhuizen <basni@google.com>
Acked-by: Dave Airlie <airlied@redhat.com>
This commit is contained in:
Bas Nieuwenhuizen 2017-04-02 12:32:39 +02:00
parent d64f689f61
commit a4c4efad89
1 changed files with 15 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
src/amd/vulkan/si_cmd_buffer.c
View file

@ -504,22 +504,6 @@ get_viewport_xform(const VkViewport *viewport,
translate[2] = n; translate[2] = n;
} }
static void
get_viewport_xform_scissor(const VkRect2D *scissor,
float scale[2], float translate[2])
{
float x = scissor->offset.x;
float y = scissor->offset.y;
float half_width = 0.5f * scissor->extent.width;
float half_height = 0.5f * scissor->extent.height;
scale[0] = half_width;
translate[0] = half_width + x;
scale[1] = half_height;
translate[1] = half_height + y;
}
void void
si_write_viewport(struct radeon_winsys_cs *cs, int first_vp, si_write_viewport(struct radeon_winsys_cs *cs, int first_vp,
int count, const VkViewport *viewports) int count, const VkViewport *viewports)
@ -579,26 +563,13 @@ static VkRect2D si_intersect_scissor(const VkRect2D *a, const VkRect2D *b) {
return ret; return ret;
} }
static VkRect2D si_union_scissor(const VkRect2D *a, const VkRect2D *b) {
VkRect2D ret;
ret.offset.x = MIN2(a->offset.x, b->offset.x);
ret.offset.y = MIN2(a->offset.y, b->offset.y);
ret.extent.width = MAX2(a->offset.x + a->extent.width,
b->offset.x + b->extent.width) - ret.offset.x;
ret.extent.height = MAX2(a->offset.y + a->extent.height,
b->offset.y + b->extent.height) - ret.offset.y;
return ret;
}
void void
si_write_scissors(struct radeon_winsys_cs *cs, int first, si_write_scissors(struct radeon_winsys_cs *cs, int first,
int count, const VkRect2D *scissors, int count, const VkRect2D *scissors,
const VkViewport *viewports, bool can_use_guardband) const VkViewport *viewports, bool can_use_guardband)
{ {
int i; int i;
VkRect2D merged; float scale[3], translate[3], guardband_x = INFINITY, guardband_y = INFINITY;
float scale[2], translate[2], guardband_x = 1.0, guardband_y = 1.0;
const float max_range = 32767.0f; const float max_range = 32767.0f;
assert(count); assert(count);
@ -607,10 +578,17 @@ si_write_scissors(struct radeon_winsys_cs *cs, int first,
VkRect2D viewport_scissor = si_scissor_from_viewport(viewports + i); VkRect2D viewport_scissor = si_scissor_from_viewport(viewports + i);
VkRect2D scissor = si_intersect_scissor(&scissors[i], &viewport_scissor); VkRect2D scissor = si_intersect_scissor(&scissors[i], &viewport_scissor);
if (i) get_viewport_xform(viewports + i, scale, translate);
merged = si_union_scissor(&merged, &scissor); scale[0] = abs(scale[0]);
else scale[1] = abs(scale[1]);
merged = scissor;
if (scale[0] < 0.5)
scale[0] = 0.5;
if (scale[1] < 0.5)
scale[1] = 0.5;
guardband_x = MIN2(guardband_x, (max_range - abs(translate[0])) / scale[0]);
guardband_y = MIN2(guardband_y, (max_range - abs(translate[1])) / scale[1]);
radeon_emit(cs, S_028250_TL_X(scissor.offset.x) | radeon_emit(cs, S_028250_TL_X(scissor.offset.x) |
S_028250_TL_Y(scissor.offset.y) | S_028250_TL_Y(scissor.offset.y) |
@ -618,12 +596,9 @@ si_write_scissors(struct radeon_winsys_cs *cs, int first,
radeon_emit(cs, S_028254_BR_X(scissor.offset.x + scissor.extent.width) | radeon_emit(cs, S_028254_BR_X(scissor.offset.x + scissor.extent.width) |
S_028254_BR_Y(scissor.offset.y + scissor.extent.height)); S_028254_BR_Y(scissor.offset.y + scissor.extent.height));
} }
if (!can_use_guardband) {
get_viewport_xform_scissor(&merged, scale, translate); guardband_x = 1.0;
guardband_y = 1.0;
if (can_use_guardband) {
guardband_x = (max_range - abs(translate[0])) / scale[0];
guardband_y = (max_range - abs(translate[1])) / scale[1];
} }
radeon_set_context_reg_seq(cs, R_028BE8_PA_CL_GB_VERT_CLIP_ADJ, 4); radeon_set_context_reg_seq(cs, R_028BE8_PA_CL_GB_VERT_CLIP_ADJ, 4);