nir/algebraic: optimize ishl(iadd(iadd(a, #b), c), #d)

fossil-db (navi31):
Totals from 671 (0.85% of 79377) affected shaders:
MaxWaves: 17048 -> 17052 (+0.02%); split: +0.04%, -0.01%
Instrs: 786643 -> 785459 (-0.15%); split: -0.20%, +0.05%
CodeSize: 4074988 -> 4069304 (-0.14%); split: -0.18%, +0.04%
VGPRs: 43896 -> 43860 (-0.08%); split: -0.11%, +0.03%
SpillSGPRs: 753 -> 748 (-0.66%)
Latency: 8187731 -> 8186707 (-0.01%); split: -0.11%, +0.10%
InvThroughput: 1274564 -> 1274582 (+0.00%); split: -0.11%, +0.11%
VClause: 14292 -> 14183 (-0.76%); split: -0.98%, +0.22%
SClause: 21527 -> 21426 (-0.47%); split: -0.53%, +0.06%
Copies: 59381 -> 59299 (-0.14%); split: -0.67%, +0.53%
PreSGPRs: 29358 -> 29349 (-0.03%)
PreVGPRs: 36595 -> 36368 (-0.62%); split: -0.70%, +0.08%
VALU: 482669 -> 481927 (-0.15%); split: -0.21%, +0.06%
SALU: 70019 -> 70009 (-0.01%); split: -0.06%, +0.05%
VOPD: 142 -> 139 (-2.11%)

fossil-db (navi21):
Totals from 671 (0.85% of 79377) affected shaders:
MaxWaves: 11536 -> 11516 (-0.17%); split: +0.03%, -0.21%
Instrs: 773615 -> 772476 (-0.15%); split: -0.18%, +0.03%
CodeSize: 4092564 -> 4086688 (-0.14%); split: -0.17%, +0.03%
VGPRs: 43424 -> 43448 (+0.06%); split: -0.04%, +0.09%
SpillSGPRs: 565 -> 560 (-0.88%)
Latency: 8650893 -> 8633993 (-0.20%); split: -0.31%, +0.11%
InvThroughput: 1920741 -> 1920368 (-0.02%); split: -0.10%, +0.08%
VClause: 15830 -> 15774 (-0.35%); split: -0.76%, +0.40%
SClause: 21025 -> 21009 (-0.08%); split: -0.11%, +0.03%
Copies: 65425 -> 65460 (+0.05%); split: -0.37%, +0.43%
Branches: 21845 -> 21848 (+0.01%)
PreSGPRs: 29457 -> 29448 (-0.03%)
PreVGPRs: 37296 -> 37066 (-0.62%); split: -0.69%, +0.08%
VALU: 516908 -> 516056 (-0.16%); split: -0.20%, +0.04%
SALU: 91545 -> 91531 (-0.02%); split: -0.05%, +0.03%

fossil-db (vega10):
Totals from 497 (0.79% of 62962) affected shaders:
MaxWaves: 2325 -> 2328 (+0.13%); split: +0.17%, -0.04%
Instrs: 298230 -> 297284 (-0.32%); split: -0.35%, +0.03%
CodeSize: 1535212 -> 1530636 (-0.30%); split: -0.34%, +0.04%
SGPRs: 36464 -> 36480 (+0.04%)
VGPRs: 29412 -> 29396 (-0.05%); split: -0.07%, +0.01%
SpillSGPRs: 164 -> 159 (-3.05%)
Latency: 3957230 -> 3948919 (-0.21%); split: -0.51%, +0.30%
InvThroughput: 1680680 -> 1679105 (-0.09%); split: -0.17%, +0.08%
VClause: 6175 -> 6102 (-1.18%); split: -1.55%, +0.37%
SClause: 9503 -> 9510 (+0.07%); split: -0.15%, +0.22%
Copies: 20992 -> 20892 (-0.48%); split: -0.97%, +0.50%
PreSGPRs: 17803 -> 17795 (-0.04%)
PreVGPRs: 23072 -> 22823 (-1.08%); split: -1.11%, +0.03%
VALU: 225322 -> 224587 (-0.33%); split: -0.36%, +0.04%
SALU: 21029 -> 21011 (-0.09%); split: -0.22%, +0.13%

fossil-db (polaris10):
Totals from 489 (0.79% of 61794) affected shaders:
Instrs: 299330 -> 298308 (-0.34%); split: -0.40%, +0.06%
CodeSize: 1529316 -> 1525440 (-0.25%); split: -0.32%, +0.07%
SpillSGPRs: 159 -> 149 (-6.29%)
Latency: 3924819 -> 3898471 (-0.67%); split: -0.93%, +0.25%
InvThroughput: 1687167 -> 1684956 (-0.13%); split: -0.22%, +0.09%
VClause: 6248 -> 6067 (-2.90%); split: -3.28%, +0.38%
SClause: 9519 -> 9492 (-0.28%); split: -0.72%, +0.44%
Copies: 21673 -> 21637 (-0.17%); split: -0.90%, +0.73%
PreSGPRs: 17611 -> 17603 (-0.05%)
PreVGPRs: 22873 -> 22625 (-1.08%)
VALU: 226805 -> 225928 (-0.39%); split: -0.45%, +0.06%
SALU: 21419 -> 21413 (-0.03%); split: -0.28%, +0.25%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29242>

src/compiler/nir/nir_opt_algebraic.py

@@ -641,6 +641,8 @@ optimizations.extend([
    # 'a<<c' to be CSE'd.  It also helps architectures that have an ISHLADD
    # instruction or a constant offset field for in load / store instructions.
    (('ishl', ('iadd', a, '#b'), '#c'), ('iadd', ('ishl', a, c), ('ishl', b, c))),
+   (('ishl', ('iadd(is_used_once)', ('iadd', a, '#b'), c), '#d'),
+    ('iadd', ('ishl', ('iadd', a, c), d), ('ishl', b, d))),
 
    # (a + #b) * #c => (a * #c) + (#b * #c)
    (('imul', ('iadd(is_used_once)', a, '#b'), '#c'), ('iadd', ('imul', a, c), ('imul', b, c))),