OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

radv: move lower_io_arrays_to_elements before lower_io_to_scalar_early

Browse Source 
nir_lower_io_arrays_to_elements lowers arrays or matrices to elements,
which ends up to vectors for matrices, but a bunch of IO optimizations
only work for scalars.

Calling it before lower_io_to_scalar_early allows nir_link_opt_varyings
to remove duplicated inputs and replace constant inputs.

fossils-db (Navi10):
Totals from 294 (0.22% of 136546) affected shaders:
CodeSize: 861356 -> 860224 (-0.13%); split: -0.13%, +0.00%
Instrs: 161972 -> 161832 (-0.09%); split: -0.09%, +0.00%
Cycles: 1185680 -> 1185120 (-0.05%); split: -0.05%, +0.00%
SMEM: 31422 -> 31424 (+0.01%)
Copies: 9065 -> 9068 (+0.03%)

Only Talos and Dark Souls 3 are affected.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7041>
This commit is contained in:
Samuel Pitoiset
2020-10-06 17:54:33 +02:00
committed by Marge Bot
parent b0829c6af7
commit b32a8f83dc
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/amd/vulkan/radv_pipeline.c
View File

@@ -2217,6 +2217,11 @@ radv_link_shaders(struct radv_pipeline *pipeline, nir_shader **shaders,
ordered_shaders[1]->info.has_transform_feedback_varyings)
nir_link_xfb_varyings(ordered_shaders[1], ordered_shaders[0]);
for (int i = 1; i < shader_count; ++i) {
nir_lower_io_arrays_to_elements(ordered_shaders[i],
ordered_shaders[i - 1]);
}
for (int i = 0; i < shader_count; ++i) {
nir_variable_mode mask = 0;
@@ -2259,9 +2264,6 @@ radv_link_shaders(struct radv_pipeline *pipeline, nir_shader **shaders,
}
for (int i = 1; !optimize_conservatively && (i < shader_count); ++i) {
nir_lower_io_arrays_to_elements(ordered_shaders[i],
ordered_shaders[i - 1]);
if (nir_link_opt_varyings(ordered_shaders[i], ordered_shaders[i - 1])) {
nir_opt_constant_folding(ordered_shaders[i - 1]);
nir_opt_algebraic(ordered_shaders[i - 1]);