fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-09 04:38:03 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

ac/nir/cull: Tweak phi for cull_small_primitive branch.

Browse source 
cull_small_primitive will now allow the caller to pass an
SSA def that it will use to determine if the primitive was
initially rejected.

This allows ACO to remove an s_branch instruction from every
NGG culling shader.

Fossil DB stats on Navi 21:

Totals from 60918 (45.16% of 134906) affected shaders:
CodeSize: 160086644 -> 159355824 (-0.46%); split: -0.46%, +0.00%
Instrs: 30477916 -> 30356092 (-0.40%); split: -0.40%, +0.00%
Latency: 139587915 -> 139611487 (+0.02%); split: -0.00%, +0.02%
InvThroughput: 21184261 -> 21184346 (+0.00%)
Copies: 2762930 -> 2702024 (-2.20%); split: -2.20%, +0.00%
Branches: 1236970 -> 1176052 (-4.92%)

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17919>
This commit is contained in:
Timur Kristóf 2022-08-06 01:21:47 +02:00 • committed by Marge Bot
parent abc4eda846
commit e035c289b5
1 changed files with 4 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
src/amd/common/ac_nir_cull.c
View file

@ -101,17 +101,17 @@ cull_frustrum(nir_builder *b, nir_ssa_def *bbox_min[3], nir_ssa_def *bbox_max[3]
}
static nir_ssa_def *
cull_small_primitive(nir_builder *b, nir_ssa_def *bbox_min[3], nir_ssa_def *bbox_max[3])
cull_small_primitive(nir_builder *b, nir_ssa_def *bbox_min[3], nir_ssa_def *bbox_max[3],
nir_ssa_def *prim_is_small_else)
{
nir_ssa_def *prim_is_small = NULL;
nir_ssa_def *prim_is_small_else = nir_imm_false(b);
nir_if *if_cull_small_prims = nir_push_if(b, nir_load_cull_small_primitives_enabled_amd(b));
{
nir_ssa_def *vp_scale[2] = { nir_load_viewport_x_scale(b), nir_load_viewport_y_scale(b), };
nir_ssa_def *vp_translate[2] = { nir_load_viewport_x_offset(b), nir_load_viewport_y_offset(b), };
nir_ssa_def *small_prim_precision = nir_load_cull_small_prim_precision_amd(b);
prim_is_small = nir_imm_false(b);
prim_is_small = prim_is_small_else;
for (unsigned chan = 0; chan < 2; ++chan) {
/* Convert the position to screen-space coordinates. */
@ -155,8 +155,7 @@ ac_nir_cull_triangle(nir_builder *b,
calc_bbox(b, pos, bbox_min, bbox_max);
nir_ssa_def *prim_outside_view = cull_frustrum(b, bbox_min, bbox_max);
nir_ssa_def *prim_is_small = cull_small_primitive(b, bbox_min, bbox_max);
nir_ssa_def *prim_invisible = nir_ior(b, prim_outside_view, prim_is_small);
nir_ssa_def *prim_invisible = cull_small_primitive(b, bbox_min, bbox_max, prim_outside_view);
accepted = nir_iand(b, nir_inot(b, prim_invisible), nir_inot(b, w_info.any_w_negative));
nir_if *if_still_accepted = nir_push_if(b, accepted);