From dc566a033cca87821d55ff0f68ee8a108eb0e2a3 Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Wed, 22 Aug 2018 21:55:55 -0700 Subject: [PATCH] nir/algebraic: Pull common multiplication out of flrp arguments MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit All Intel platforms had similar results. (Skylake shown) total instructions in shared programs: 15342485 -> 15337495 (-0.03%) instructions in affected programs: 217456 -> 212466 (-2.29%) helped: 1539 HURT: 1 helped stats (abs) min: 1 max: 17 x̄: 3.24 x̃: 3 helped stats (rel) min: 0.22% max: 18.75% x̄: 3.10% x̃: 1.91% HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1 HURT stats (rel) min: 0.56% max: 0.56% x̄: 0.56% x̃: 0.56% 95% mean confidence interval for instructions value: -3.39 -3.09 95% mean confidence interval for instructions %-change: -3.24% -2.96% Instructions are helped. total cycles in shared programs: 355734320 -> 355728237 (<.01%) cycles in affected programs: 1851555 -> 1845472 (-0.33%) helped: 835 HURT: 575 helped stats (abs) min: 1 max: 658 x̄: 40.62 x̃: 14 helped stats (rel) min: <.01% max: 35.69% x̄: 3.78% x̃: 1.81% HURT stats (abs) min: 1 max: 322 x̄: 48.40 x̃: 14 HURT stats (rel) min: 0.04% max: 71.02% x̄: 8.06% x̃: 2.43% 95% mean confidence interval for cycles value: -8.50 -0.13 95% mean confidence interval for cycles %-change: 0.48% 1.62% Inconclusive result (value mean confidence interval and %-change mean confidence interval disagree). Reviewed-by: Matt Turner --- 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 59ba4add43e..53beb4a8546 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -136,6 +136,11 @@ optimizations = [ (('~flrp@32', ('fadd', a, b), ('fadd', a, c), d), ('fadd', ('flrp', b, c, d), a), 'options->lower_flrp32'), (('~flrp@64', ('fadd', a, b), ('fadd', a, c), d), ('fadd', ('flrp', b, c, d), a), 'options->lower_flrp64'), + (('~flrp@32', a, ('fmul(is_used_once)', a, b), c), ('fmul', ('flrp', 1.0, b, c), a), 'options->lower_flrp32'), + (('~flrp@64', a, ('fmul(is_used_once)', a, b), c), ('fmul', ('flrp', 1.0, b, c), a), 'options->lower_flrp64'), + + (('~flrp', ('fmul(is_used_once)', a, b), ('fmul(is_used_once)', a, c), d), ('fmul', ('flrp', b, c, d), a)), + (('~flrp', a, b, ('b2f', 'c@1')), ('bcsel', c, b, a), 'options->lower_flrp32'), (('~flrp', a, 0.0, c), ('fadd', ('fmul', ('fneg', a), c), a)), (('flrp@16', a, b, c), ('fadd', ('fmul', c, ('fsub', b, a)), a), 'options->lower_flrp16'), -- 2.30.2