diff options
author | Ian Romanick <[email protected]> | 2018-05-30 18:06:57 -0700 |
---|---|---|
committer | Ian Romanick <[email protected]> | 2018-06-01 10:13:16 -0700 |
commit | 619c51722b7978366f15a03bec6751327f2b4b65 (patch) | |
tree | 59dea0d27ccf4dd43bbe7cb68d49a16b8b3f9ea5 /src/compiler | |
parent | 57fbc2ac5023d281b8134f4da4da821a7ae405f8 (diff) |
nir: Add some missing "optimization undo" patterns
d8d18516b0a and 03fb13f6467 added some patterns to undo conversions like
(('ior', ('flt', a, b), ('flt', a, c)), ('flt', a, ('fmax', b, c)))
If further optimization cause some of the operands to either be the same
or be constants, undoing the transformation can lead to further savings.
I don't know why these patterns were not added in those patches. I did
not check to see which specific patterns actually helped. I just added
all of them for symmetry. This prevents some loop unrolling regressions
Plane Shift caused by Samuel's "nir: implement the GLSL equivalent of if
simplication in nir_opt_if" patch.
Skylake and Broadwell had similar results. (Skylake shown)
total instructions in shared programs: 14369768 -> 14369557 (<.01%)
instructions in affected programs: 44076 -> 43865 (-0.48%)
helped: 141
HURT: 0
helped stats (abs) min: 1 max: 5 x̄: 1.50 x̃: 1
helped stats (rel) min: 0.07% max: 1.52% x̄: 0.66% x̃: 0.60%
95% mean confidence interval for instructions value: -1.67 -1.32
95% mean confidence interval for instructions %-change: -0.72% -0.59%
Instructions are helped.
total cycles in shared programs: 532430629 -> 532425772 (<.01%)
cycles in affected programs: 1170832 -> 1165975 (-0.41%)
helped: 101
HURT: 5
helped stats (abs) min: 1 max: 160 x̄: 48.54 x̃: 32
helped stats (rel) min: <.01% max: 8.49% x̄: 2.76% x̃: 2.03%
HURT stats (abs) min: 2 max: 22 x̄: 9.20 x̃: 4
HURT stats (rel) min: <.01% max: 0.05% x̄: 0.02% x̃: <.01%
95% mean confidence interval for cycles value: -53.64 -38.00
95% mean confidence interval for cycles %-change: -3.06% -2.20%
Cycles are helped.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Samuel Pitoiset <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
Diffstat (limited to 'src/compiler')
-rw-r--r-- | src/compiler/nir/nir_opt_algebraic.py | 20 |
1 files changed, 19 insertions, 1 deletions
diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index ba788f221a3..f153570105b 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -292,6 +292,8 @@ optimizations = [ (('~fge', ('fmax', a, b), a), True), (('~flt', a, ('fmin', b, a)), False), (('~flt', ('fmax', a, b), a), False), + (('~fge', a, ('fmax', b, a)), ('fge', a, b)), + (('~fge', ('fmin', a, b), a), ('fge', b, a)), (('ilt', a, ('imax', b, a)), ('ilt', a, b)), (('ilt', ('imin', a, b), a), ('ilt', b, a)), @@ -301,7 +303,23 @@ optimizations = [ (('ult', ('umin', a, b), a), ('ult', b, a)), (('uge', a, ('umin', b, a)), True), (('uge', ('umax', a, b), a), True), - + (('ilt', a, ('imin', b, a)), False), + (('ilt', ('imax', a, b), a), False), + (('ige', a, ('imax', b, a)), ('ige', a, b)), + (('ige', ('imin', a, b), a), ('ige', b, a)), + (('ult', a, ('umin', b, a)), False), + (('ult', ('umax', a, b), a), False), + (('uge', a, ('umax', b, a)), ('uge', a, b)), + (('uge', ('umin', a, b), a), ('uge', b, a)), + + (('ilt', '#a', ('imax', '#b', c)), ('ior', ('ilt', a, b), ('ilt', a, c))), + (('ilt', ('imin', '#a', b), '#c'), ('ior', ('ilt', a, c), ('ilt', b, c))), + (('ige', '#a', ('imin', '#b', c)), ('ior', ('ige', a, b), ('ige', a, c))), + (('ige', ('imax', '#a', b), '#c'), ('ior', ('ige', a, c), ('ige', b, c))), + (('ult', '#a', ('umax', '#b', c)), ('ior', ('ult', a, b), ('ult', a, c))), + (('ult', ('umin', '#a', b), '#c'), ('ior', ('ult', a, c), ('ult', b, c))), + (('uge', '#a', ('umin', '#b', c)), ('ior', ('uge', a, b), ('uge', a, c))), + (('uge', ('umax', '#a', b), '#c'), ('ior', ('uge', a, c), ('uge', b, c))), (('ilt', '#a', ('imin', '#b', c)), ('iand', ('ilt', a, b), ('ilt', a, c))), (('ilt', ('imax', '#a', b), '#c'), ('iand', ('ilt', a, c), ('ilt', b, c))), (('ige', '#a', ('imax', '#b', c)), ('iand', ('ige', a, b), ('ige', a, c))), |