ac/nir: Reuse the repacked output positions of culling shaders.
The position outputs are stored into LDS and reloaded after
repacking, therefore the repacked position values can be
reused in the bottom part of the shader.
Fossil DB results on Sienna Cichlid (with NGG culling on):
Totals from 9016 (7.01% of 128647) affected shaders:
VGPRs: 372472 -> 347560 (-6.69%); split: -6.82%, +0.13%
SpillSGPRs: 437 -> 87 (-80.09%)
CodeSize:
32359340 ->
30441692 (-5.93%); split: -5.93%, +0.00%
MaxWaves: 222030 -> 238970 (+7.63%); split: +7.83%, -0.20%
Instrs: 6207833 -> 5834149 (-6.02%); split: -6.02%, +0.00%
Latency:
27626263 ->
27890632 (+0.96%); split: -5.34%, +6.29%
InvThroughput: 4792958 -> 4361336 (-9.01%); split: -9.01%, +0.00%
VClause: 144385 -> 139586 (-3.32%); split: -9.29%, +5.97%
SClause: 141350 -> 129875 (-8.12%); split: -8.57%, +0.45%
Copies: 580017 -> 568916 (-1.91%); split: -3.60%, +1.68%
Branches: 209067 -> 209154 (+0.04%); split: -0.24%, +0.28%
PreSGPRs: 281320 -> 277814 (-1.25%)
PreVGPRs: 290040 -> 273861 (-5.58%)
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10525>