nir/opt_algebaric: convert fadd(a, a) to a * 2.0

On AMD, this is a clear win. 2.0 is a free constant,
the multiplication can be fused into fma, or it can
be done as a free output modifier. Otherwise, fmul
and fadd have the same throughput/latency, with the only
possible downside being potentially power consumption.

For other hardware this might not be as clear,
but we should at least choose one option for NIR because
it allows more CSE.

Foz-DB Navi21:
Totals from 12231 (15.41% of 79395) affected shaders:
MaxWaves: 309068 -> 309032 (-0.01%)
Instrs: 11826395 -> 11790132 (-0.31%); split: -0.31%, +0.00%
CodeSize: 63531496 -> 63512868 (-0.03%); split: -0.03%, +0.00%
VGPRs: 551256 -> 551328 (+0.01%); split: -0.00%, +0.02%
SpillSGPRs: 984 -> 979 (-0.51%)
Latency: 88486492 -> 88394296 (-0.10%); split: -0.11%, +0.01%
InvThroughput: 22360595 -> 22300790 (-0.27%); split: -0.27%, +0.00%
VClause: 226267 -> 226273 (+0.00%); split: -0.01%, +0.01%
SClause: 293820 -> 293783 (-0.01%); split: -0.02%, +0.00%
Copies: 727187 -> 727106 (-0.01%); split: -0.03%, +0.02%
PreSGPRs: 539623 -> 539625 (+0.00%)
PreVGPRs: 440843 -> 440946 (+0.02%); split: -0.00%, +0.03%
VALU: 8324962 -> 8288809 (-0.43%); split: -0.43%, +0.00%
SALU: 1278550 -> 1278538 (-0.00%); split: -0.00%, +0.00%
VMEM: 440600 -> 440599 (-0.00%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32989>

src/compiler/nir/nir_opt_algebraic.py

@@ -242,6 +242,7 @@ optimizations = [
    (('~fadd', ('fneg', a), ('fadd', a, b)), b),
    (('~fadd', a, ('fadd', ('fneg', a), b)), b),
    (('fadd', ('fsat', a), ('fsat', ('fneg', a))), ('fsat', ('fabs', a))),
+   (('fadd', a, a), ('fmul', a, 2.0)),
    (('~fmul', a, 0.0), 0.0),
    # The only effect a*0.0 should have is when 'a' is infinity, -0.0 or NaN
    (('fmul(nsz,nnan)', 'a', 0.0), 0.0),