From cfc0d34802b13a7436f8d0029e9b1370f2bc585e Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Tue, 9 Jan 2018 15:32:47 -0800 Subject: [PATCH] nir: See through an fneg to apply existing optimizations MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Doing the same for the existing feq and fne transformations didn't help anything in shader-db. shader-db results: Broadwell and Skylake (Skylake shown) total instructions in shared programs: 14529463 -> 14526147 (-0.02%) instructions in affected programs: 402420 -> 399104 (-0.82%) helped: 2136 HURT: 131 helped stats (abs) min: 1 max: 10 x̄: 1.61 x̃: 1 helped stats (rel) min: 0.03% max: 16.22% x̄: 3.14% x̃: 1.12% HURT stats (abs) min: 1 max: 2 x̄: 1.01 x̃: 1 HURT stats (rel) min: 0.13% max: 7.69% x̄: 0.75% x̃: 0.57% 95% mean confidence interval for instructions value: -1.51 -1.41 95% mean confidence interval for instructions %-change: -3.06% -2.78% Instructions are helped. total cycles in shared programs: 533146915 -> 533120531 (<.01%) cycles in affected programs: 10356261 -> 10329877 (-0.25%) helped: 1933 HURT: 844 helped stats (abs) min: 1 max: 490 x̄: 29.44 x̃: 16 helped stats (rel) min: <.01% max: 28.57% x̄: 3.43% x̃: 1.88% HURT stats (abs) min: 1 max: 423 x̄: 36.17 x̃: 12 HURT stats (rel) min: <.01% max: 23.75% x̄: 1.90% x̃: 0.59% 95% mean confidence interval for cycles value: -11.78 -7.22 95% mean confidence interval for cycles %-change: -1.98% -1.65% Cycles are helped. Haswell total instructions in shared programs: 9037416 -> 9034106 (-0.04%) instructions in affected programs: 389831 -> 386521 (-0.85%) helped: 2184 HURT: 120 helped stats (abs) min: 1 max: 11 x̄: 1.57 x̃: 1 helped stats (rel) min: 0.03% max: 25.00% x̄: 2.73% x̃: 1.02% HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1 HURT stats (rel) min: 0.19% max: 7.69% x̄: 0.81% x̃: 0.57% 95% mean confidence interval for instructions value: -1.49 -1.39 95% mean confidence interval for instructions %-change: -2.68% -2.41% Instructions are helped. total cycles in shared programs: 84636243 -> 84631628 (<.01%) cycles in affected programs: 4745058 -> 4740443 (-0.10%) helped: 1904 HURT: 960 helped stats (abs) min: 1 max: 466 x̄: 30.21 x̃: 18 helped stats (rel) min: 0.02% max: 36.36% x̄: 3.57% x̃: 2.38% HURT stats (abs) min: 1 max: 1080 x̄: 55.11 x̃: 14 HURT stats (rel) min: 0.02% max: 51.33% x̄: 2.77% x̃: 0.81% 95% mean confidence interval for cycles value: -4.51 1.29 95% mean confidence interval for cycles %-change: -1.64% -1.25% Inconclusive result (value mean confidence interval includes 0). LOST: 1 GAINED: 0 Sandy Bridge and Ivy Bridge (Ivy Bridge shown) total instructions in shared programs: 10018873 -> 10015456 (-0.03%) instructions in affected programs: 512820 -> 509403 (-0.67%) helped: 2268 HURT: 162 helped stats (abs) min: 1 max: 11 x̄: 1.62 x̃: 1 helped stats (rel) min: 0.03% max: 25.00% x̄: 2.47% x̃: 0.88% HURT stats (abs) min: 1 max: 4 x̄: 1.59 x̃: 1 HURT stats (rel) min: 0.09% max: 7.69% x̄: 0.86% x̃: 0.50% 95% mean confidence interval for instructions value: -1.46 -1.35 95% mean confidence interval for instructions %-change: -2.38% -2.12% Instructions are helped. total cycles in shared programs: 87538223 -> 87524771 (-0.02%) cycles in affected programs: 5435520 -> 5422068 (-0.25%) helped: 1916 HURT: 946 helped stats (abs) min: 1 max: 1392 x̄: 29.44 x̃: 18 helped stats (rel) min: <.01% max: 34.51% x̄: 3.34% x̃: 1.97% HURT stats (abs) min: 1 max: 633 x̄: 45.41 x̃: 11 HURT stats (rel) min: 0.02% max: 25.95% x̄: 2.41% x̃: 0.62% 95% mean confidence interval for cycles value: -7.34 -2.06 95% mean confidence interval for cycles %-change: -1.62% -1.26% Cycles are helped. LOST: 1 GAINED: 0 Iron Lake total instructions in shared programs: 7888446 -> 7886959 (-0.02%) instructions in affected programs: 331581 -> 330094 (-0.45%) helped: 1160 HURT: 97 helped stats (abs) min: 1 max: 10 x̄: 1.37 x̃: 1 helped stats (rel) min: 0.02% max: 9.68% x̄: 0.93% x̃: 0.43% HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1 HURT stats (rel) min: 0.17% max: 4.17% x̄: 0.37% x̃: 0.25% 95% mean confidence interval for instructions value: -1.25 -1.12 95% mean confidence interval for instructions %-change: -0.91% -0.75% Instructions are helped. total cycles in shared programs: 178130766 -> 178116996 (<.01%) cycles in affected programs: 12534564 -> 12520794 (-0.11%) helped: 1856 HURT: 187 helped stats (abs) min: 2 max: 202 x̄: 7.78 x̃: 4 helped stats (rel) min: <.01% max: 6.47% x̄: 0.28% x̃: 0.11% HURT stats (abs) min: 2 max: 26 x̄: 3.55 x̃: 2 HURT stats (rel) min: 0.01% max: 2.14% x̄: 0.08% x̃: 0.02% 95% mean confidence interval for cycles value: -7.41 -6.07 95% mean confidence interval for cycles %-change: -0.28% -0.22% Cycles are helped. GM45 total instructions in shared programs: 4858912 -> 4857887 (-0.02%) instructions in affected programs: 237565 -> 236540 (-0.43%) helped: 867 HURT: 57 helped stats (abs) min: 1 max: 10 x̄: 1.25 x̃: 1 helped stats (rel) min: 0.02% max: 9.38% x̄: 0.87% x̃: 0.43% HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1 HURT stats (rel) min: 0.16% max: 3.85% x̄: 0.34% x̃: 0.22% 95% mean confidence interval for instructions value: -1.18 -1.04 95% mean confidence interval for instructions %-change: -0.88% -0.71% Instructions are helped. total cycles in shared programs: 122189118 -> 122180816 (<.01%) cycles in affected programs: 8776418 -> 8768116 (-0.09%) helped: 1213 HURT: 166 helped stats (abs) min: 2 max: 202 x̄: 7.30 x̃: 4 helped stats (rel) min: <.01% max: 6.43% x̄: 0.25% x̃: 0.11% HURT stats (abs) min: 2 max: 26 x̄: 3.35 x̃: 2 HURT stats (rel) min: 0.01% max: 2.14% x̄: 0.06% x̃: 0.02% 95% mean confidence interval for cycles value: -6.78 -5.26 95% mean confidence interval for cycles %-change: -0.24% -0.18% Cycles are helped. Signed-off-by: Ian Romanick Reviewed-by: Samuel Iglesias Gonsálvez Reviewed-by: Elie Tournier --- src/compiler/nir/nir_opt_algebraic.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/src/compiler/nir/nir_opt_algebraic.py b/src/compiler/nir/nir_opt_algebraic.py index ad75228..0ada915 100644 --- a/src/compiler/nir/nir_opt_algebraic.py +++ b/src/compiler/nir/nir_opt_algebraic.py @@ -354,7 +354,8 @@ optimizations = [ # a single non-constant. We could do better eventually. (('~fmul', '#a', ('fmul', b, '#c')), ('fmul', ('fmul', a, c), b)), (('imul', '#a', ('imul', b, '#c')), ('imul', ('imul', a, c), b)), - (('~fadd', '#a', ('fadd', b, '#c')), ('fadd', ('fadd', a, c), b)), + (('~fadd', '#a', ('fadd', b, '#c')), ('fadd', ('fadd', a, c), b)), + (('~fadd', '#a', ('fneg', ('fadd', b, '#c'))), ('fadd', ('fadd', a, ('fneg', c)), ('fneg', b))), (('iadd', '#a', ('iadd', b, '#c')), ('iadd', ('iadd', a, c), b)), # By definition... @@ -569,8 +570,10 @@ before_ffma_optimizations = [ late_optimizations = [ # Most of these optimizations aren't quite safe when you get infinity or # Nan involved but the first one should be fine. - (('flt', ('fadd', a, b), 0.0), ('flt', a, ('fneg', b))), - (('~fge', ('fadd', a, b), 0.0), ('fge', a, ('fneg', b))), + (('flt', ('fadd', a, b), 0.0), ('flt', a, ('fneg', b))), + (('flt', ('fneg', ('fadd', a, b)), 0.0), ('flt', ('fneg', a), b)), + (('~fge', ('fadd', a, b), 0.0), ('fge', a, ('fneg', b))), + (('~fge', ('fneg', ('fadd', a, b)), 0.0), ('fge', ('fneg', a), b)), (('~feq', ('fadd', a, b), 0.0), ('feq', a, ('fneg', b))), (('~fne', ('fadd', a, b), 0.0), ('fne', a, ('fneg', b))), -- 2.7.4