From 68420d8322c2b304a0b15f94b43dec19f082dfae Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Tue, 8 Mar 2016 11:11:00 -0800 Subject: [PATCH] nir: Simplify min and max of b2f MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit v2: Rebase on almost 2 years. Require that one of the arguments to fmin or fmax be used only once. This prevents some regressions. shader-db results: Skylake and Broadwell had similar results. Skylake shown. total instructions in shared programs: 14526021 -> 14525913 (<.01%) instructions in affected programs: 4613 -> 4505 (-2.34%) helped: 31 HURT: 0 helped stats (abs) min: 1 max: 4 x̄: 3.48 x̃: 4 helped stats (rel) min: 0.62% max: 6.67% x̄: 3.31% x̃: 2.42% total cycles in shared programs: 533118710 -> 533118403 (<.01%) cycles in affected programs: 34334 -> 34027 (-0.89%) helped: 24 HURT: 0 helped stats (abs) min: 4 max: 24 x̄: 12.79 x̃: 14 helped stats (rel) min: 0.25% max: 2.40% x̄: 1.08% x̃: 1.03% No changes on GM45, Iron Lake, Sandy Bridge, Ivy Bridge, or Haswell. Signed-off-by: Ian Romanick Reviewed-by: Samuel Iglesias Gonsálvez Reviewed-by: Elie Tournier --- src/compiler/nir/nir_opt_algebraic.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index b141f2414db..c097f128323 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -158,6 +158,11 @@ optimizations = [ # a != 0.0 (('flt', 0.0, ('fabs', a)), ('fne', a, 0.0)), + (('fmax', ('b2f(is_used_once)', a), ('b2f', b)), ('b2f', ('ior', a, b))), + (('fmax', ('fneg(is_used_once)', ('b2f(is_used_once)', a)), ('fneg', ('b2f', b))), ('fneg', ('b2f', ('ior', a, b)))), + (('fmin', ('b2f(is_used_once)', a), ('b2f', b)), ('b2f', ('iand', a, b))), + (('fmin', ('fneg(is_used_once)', ('b2f(is_used_once)', a)), ('fneg', ('b2f', b))), ('fneg', ('b2f', ('iand', a, b)))), + # ignore this opt when the result is used by a bcsel or if so we can make # use of conditional modifiers on supported hardware. (('flt(is_not_used_by_conditional)', ('fadd(is_used_once)', a, ('fneg', b)), 0.0), ('flt', a, b)), -- 2.30.2