nir: Lower flrp with Boolean interpolator to bcsel

On Intel platforms that don't set lower_flrp, using bcsel instead of
flrp seems to be a small amount worse.  On those platforms, the use of
flrp, bcsel, and multiply of b2f is still an active area of research.
In review, Matt suggested this is because bcsel turns into CMP+SEL, and
because of the flag register we can't schedule instructions well.

shader-db results:

G4X / Ironlake
total instructions in shared programs: 4016538 -> 4012279 (-0.11%)
instructions in affected programs: 161556 -> 157297 (-2.64%)
helped: 1077
HURT: 1

total cycles in shared programs: 84328296 -> 84315862 (-0.01%)
cycles in affected programs: 4174570 -> 4162136 (-0.30%)
helped: 926
HURT: 53

Unsurprisingly, no changes on later platforms.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py
index 39be85f639e8372f64c238217dd8f160463661ca..8a44a7a0a661384af157679980a69a4476d45ae0 100644 (file)
--- a/src/compiler/nir/nir_opt_algebraic.py
+++ b/src/compiler/nir/nir_opt_algebraic.py
@@ -83,10 +83,13 @@ optimizations = [
    (('flrp', a, b, 1.0), b),
    (('flrp', a, a, b), a),
    (('flrp', 0.0, a, b), ('fmul', a, b)),
+   (('flrp', a, b, ('b2f', c)), ('bcsel', c, b, a), 'options->lower_flrp'),
    (('flrp', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp'),
    (('ffract', a), ('fsub', a, ('ffloor', a)), 'options->lower_ffract'),
-   (('fadd', ('fmul', a, ('fadd', 1.0, ('fneg', c))), ('fmul', b, c)), ('flrp', a, b, c), '!options->lower_flrp'),
-   (('fadd', a, ('fmul', c, ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp'),
+   (('fadd', ('fmul', a, ('fadd', 1.0, ('fneg', ('b2f', c)))), ('fmul', b, ('b2f', c))), ('bcsel', c, b, a), 'options->lower_flrp'),
+   (('fadd', ('fmul', a, ('fadd', 1.0, ('fneg',         c ))), ('fmul', b,         c )), ('flrp', a, b, c), '!options->lower_flrp'),
+   (('fadd', a, ('fmul', ('b2f', c), ('fadd', b, ('fneg', a)))), ('bcsel', c, b, a), 'options->lower_flrp'),
+   (('fadd', a, ('fmul',         c , ('fadd', b, ('fneg', a)))), ('flrp', a, b, c), '!options->lower_flrp'),
    (('ffma', a, b, c), ('fadd', ('fmul', a, b), c), 'options->lower_ffma'),
    (('fadd', ('fmul', a, b), c), ('ffma', a, b, c), '!options->lower_ffma'),
    # Comparison simplifications