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

intel/compiler: tileY friendly LID order for CS

Browse Source 
Computer shaders that access tileY resources (textures) benefit
from Y-locality accesses. Easiest way to implement this is walk
local ids in Y-major fashion, instead of X-major fashion. Y-major
local ids will reduce partial writes and increase cache locality
for tileY accesses since tileY resources cachelines progress in
Y direction.

Improves performance on TGL:
  Borderlands3.dxvk-g2  +1.5%

Y-major can introduce a performance drop on CS that use mixture
of buffers and images. This should be fixed in next commit.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10733>
This commit is contained in:
Felix DeGrood
2021-05-19 11:51:20 -07:00
committed by Marge Bot
parent bbd6ce6e9d
commit c23e2a662a
1 changed files with 20 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
src/intel/compiler/brw_nir_lower_cs_intrinsics.c
View File

@@ -111,14 +111,28 @@ lower_cs_intrinsics_convert_block(struct lower_intrinsics_state *state,
nir_ssa_def *id_x, *id_y, *id_z;
switch (state->nir->info.cs.derivative_group) {
case DERIVATIVE_GROUP_NONE:
/* If not using derivatives, just set the local invocation
* index linearly, and calculate local invocation ID from that.
*/
id_x = nir_umod(b, linear, size_x);
id_y = nir_umod(b, nir_udiv(b, linear, size_x), size_y);
if (nir->info.num_images == 0 &&
nir->info.num_textures == 0) {
/* X-major lid order. Optimal for linear accesses only,
* which are usually buffers. X,Y ordering will look like:
* (0,0) (1,0) (2,0) ... (size_x-1,0) (0,1) (1,1) ...
*/
id_x = nir_umod(b, linear, size_x);
id_y = nir_umod(b, nir_udiv(b, linear, size_x), size_y);
local_index = linear;
} else {
/* Y-major lid order. Optimal for tileY accesses only,
* which are usually images. X,Y ordering will look like:
* (0,0) (0,1) (0,2) ... (0,size_y-1) (1,0) (1,1) ...
*/
id_y = nir_umod(b, linear, size_y);
id_x = nir_umod(b, nir_udiv(b, linear, size_y), size_x);
local_index = nir_iadd(b, nir_iadd(b, id_x,
nir_imul(b, id_y, size_x)),
nir_imul(b, id_z, size_xy));
}
id_z = nir_udiv(b, linear, size_xy);
local_id = nir_vec3(b, id_x, id_y, id_z);
local_index = linear;
break;
case DERIVATIVE_GROUP_LINEAR:
/* For linear, just set the local invocation index linearly,