intel/compiler: Use partial redundancy elimination for compares

Almost all of the hurt shaders are repeated instances of the same shader
in synmark's compilation speed tests.

shader-db results:

All Gen6+ platforms had similar results. (Skylake shown)
total instructions in shared programs: 15256840 -> 15256389 (<.01%)
instructions in affected programs: 54137 -> 53686 (-0.83%)
helped: 288
HURT: 0
helped stats (abs) min: 1 max: 15 x̄: 1.57 x̃: 1
helped stats (rel) min: 0.06% max: 26.67% x̄: 1.99% x̃: 0.74%
95% mean confidence interval for instructions value: -1.76 -1.38
95% mean confidence interval for instructions %-change: -2.47% -1.50%
Instructions are helped.

total cycles in shared programs: 372286583 -> 372283851 (<.01%)
cycles in affected programs: 833829 -> 831097 (-0.33%)
helped: 265
HURT: 16
helped stats (abs) min: 2 max: 74 x̄: 11.81 x̃: 4
helped stats (rel) min: 0.04% max: 9.07% x̄: 0.99% x̃: 0.35%
HURT stats (abs)   min: 2 max: 130 x̄: 24.88 x̃: 8
HURT stats (rel)   min: <.01% max: 12.31% x̄: 1.44% x̃: 0.27%
95% mean confidence interval for cycles value: -12.30 -7.15
95% mean confidence interval for cycles %-change: -1.06% -0.64%
Cycles are helped.

Iron Lake and GM45 had similar results. (GM45 shown)
total instructions in shared programs: 5038653 -> 5038495 (<.01%)
instructions in affected programs: 13939 -> 13781 (-1.13%)
helped: 50
HURT: 1
helped stats (abs) min: 1 max: 15 x̄: 3.18 x̃: 4
helped stats (rel) min: 0.33% max: 13.33% x̄: 2.24% x̃: 1.09%
HURT stats (abs)   min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel)   min: 0.83% max: 0.83% x̄: 0.83% x̃: 0.83%
95% mean confidence interval for instructions value: -3.73 -2.47
95% mean confidence interval for instructions %-change: -3.16% -1.21%
Instructions are helped.

total cycles in shared programs: 128118922 -> 128118228 (<.01%)
cycles in affected programs: 134906 -> 134212 (-0.51%)
helped: 50
HURT: 0
helped stats (abs) min: 2 max: 60 x̄: 13.88 x̃: 18
helped stats (rel) min: 0.06% max: 3.19% x̄: 0.74% x̃: 0.70%
95% mean confidence interval for cycles value: -16.54 -11.22
95% mean confidence interval for cycles %-change: -0.95% -0.53%
Cycles are helped.

Reviewed-by: Kenneth Graunke <[email protected]>

1 files changed, 20 insertions, 0 deletions

diff --git a/src/intel/compiler/brw_nir.c b/src/intel/compiler/brw_nir.c
index 370b66dc57d..238db902b47 100644
--- a/src/intel/compiler/brw_nir.c
+++ b/src/intel/compiler/brw_nir.c
@@ -853,6 +853,26 @@ brw_postprocess_nir(nir_shader *nir, const struct brw_compiler *compiler,
       OPT(brw_nir_opt_peephole_ffma);
    }
 
+   if (OPT(nir_opt_comparison_pre)) {
+      OPT(nir_copy_prop);
+      OPT(nir_opt_dce);
+      OPT(nir_opt_cse);
+
+      /* Do the select peepehole again.  nir_opt_comparison_pre (combined with
+       * the other optimization passes) will have removed at least one
+       * instruction from one of the branches of the if-statement, so now it
+       * might be under the threshold of conversion to bcsel.
+       *
+       * See brw_nir_optimize for the explanation of is_vec4_tessellation.
+       */
+      const bool is_vec4_tessellation = !is_scalar &&
+         (nir->info.stage == MESA_SHADER_TESS_CTRL ||
+          nir->info.stage == MESA_SHADER_TESS_EVAL);
+      OPT(nir_opt_peephole_select, 0, is_vec4_tessellation, false);
+      OPT(nir_opt_peephole_select, 1, is_vec4_tessellation,
+          compiler->devinfo->gen >= 6);
+   }
+
    OPT(nir_opt_algebraic_late);
 
    OPT(nir_lower_to_source_mods, nir_lower_all_source_mods);