fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-08 15:38:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

nak: don't set the divergent flag on uniform sysvals

Browse source 
The list of S2UR allowed sysvals comes from the nvidia NDA docs.

with open shader-db:
Totals:
CodeSize: 14022144 -> 12291088 (-12.35%); split: -12.94%, +0.59%
Number of GPRs: 41467 -> 40560 (-2.19%)
SLM Size: 92344 -> 68824 (-25.47%)
Static cycle count: 5312651 -> 3856674 (-27.41%); split: -27.95%, +0.54%
Spills to memory: 54216 -> 51018 (-5.90%)
Fills from memory: 54216 -> 51018 (-5.90%)
Spills to reg: 7533 -> 7204 (-4.37%); split: -4.42%, +0.05%
Fills from reg: 8406 -> 7987 (-4.98%)
Max warps/SM: 61508 -> 61780 (+0.44%)

Totals from 689 (51.73% of 1332) affected shaders:
CodeSize: 12873552 -> 11142496 (-13.45%); split: -14.09%, +0.64%
Number of GPRs: 26789 -> 25882 (-3.39%)
SLM Size: 89176 -> 65656 (-26.37%)
Static cycle count: 5058667 -> 3602690 (-28.78%); split: -29.35%, +0.57%
Spills to memory: 54216 -> 51018 (-5.90%)
Fills from memory: 54216 -> 51018 (-5.90%)
Spills to reg: 7533 -> 7204 (-4.37%); split: -4.42%, +0.05%
Fills from reg: 8406 -> 7987 (-4.98%)
Max warps/SM: 30908 -> 31180 (+0.88%)

 PERCENTAGE DELTAS                      Shaders  CodeSize Number of GPRs  SLM Size Static cycle count Spills to memory Fills from memory Spills to reg Fills from reg Max warps/SM
 google-meet-clvk/BgBlur                49        +6.46%      -5.10%         .           +6.81%               .                .               .              .          +1.48%
 google-meet-clvk/Relight               81        +5.47%      -4.74%         .           +6.29%               .                .               .              .          +1.23%
 parallel-rdp/small_subgroup            246       -2.88%      -4.10%         .           +0.41%               .                .             -3.65%        -2.39%        +0.73%
 parallel-rdp/small_uber_subgroup       55       -23.04%      -1.32%      -36.28%        -42.86%           -1.61%            -1.61%          -6.88%        -9.55%        +0.68%
 parallel-rdp/subgroup                  327       -2.78%      -2.64%         .           -0.26%               .                .             -3.17%        -2.07%        +0.53%
 parallel-rdp/uber_subgroup             55       -25.59%      -1.32%      -29.98%        -41.29%           -9.04%            -9.04%          -7.06%        -10.08%       +0.68%
 q2rtx/q2rtx-rt-pipeline                42        -0.38%      -0.25%      -49.40%        +0.84%            -97.48%          -97.48%            .              .             .
 sascha-willems/bloom                   12          .            .           .              .                 .                .               .              .             .
 sascha-willems/computecloth            7         +0.20%         .           .           +0.51%               .                .               .              .             .
 sascha-willems/computecullandlod       5         +0.21%         .           .           +0.84%               .                .               .              .             .
 sascha-willems/computeheadless         1        -28.85%         .           .           +27.71%              .                .               .              .             .
 sascha-willems/computenbody            6         +0.73%         .           .           +1.78%               .                .               .              .             .
 sascha-willems/computeparticles        5         +0.53%         .           .           +1.24%               .                .               .              .             .
 sascha-willems/computeraytracing       5         +0.14%         .           .           +0.26%               .                .               .              .             .
 sascha-willems/computeshader           7         +1.29%         .           .           +2.97%               .                .               .              .             .

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36105>
This commit is contained in:
Dave Airlie 2025-07-15 06:39:22 +10:00 • committed by Marge Bot
parent 4726c08f53
commit d5037a34bb
1 changed files with 19 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
src/nouveau/compiler/nak_nir.c
View file

@ -24,9 +24,27 @@ nir_def *
nak_nir_load_sysval(nir_builder *b, enum nak_sv idx,
enum gl_access_qualifier access)
{
bool divergent;
switch (idx) {
case NAK_SV_CTAID_X:
case NAK_SV_CTAID_Y:
case NAK_SV_CTAID_Z:
case NAK_SV_VIRTCFG:
case NAK_SV_PRIM_TYPE:
case NAK_SV_CLOCK_LO:
case NAK_SV_CLOCK_HI:
case NAK_SV_VARIABLE_RATE:
divergent = false;
break;
default:
divergent = true;
break;
}
return nir_load_sysval_nv(b, 32, .base = idx,
.access = access,
.divergent = true);
.divergent = divergent);
}
bool