nir: Use the flrp lowering pass instead of nir_opt_algebraic

I tried to be very careful while updating all the various drivers, but I
don't have any of that hardware for testing. :(

i965 is the only platform that sets always_precise = true, and it is
only set true for fragment shaders.  Gen4 and Gen5 both set lower_flrp32
only for vertex shaders.  For fragment shaders, nir_op_flrp is lowered
during code generation as a(1-c)+bc.  On all other platforms 64-bit
nir_op_flrp and on Gen11 32-bit nir_op_flrp are lowered using the old
nir_opt_algebraic method.

No changes on any other Intel platforms.

v2: Add panfrost changes.

Iron Lake and GM45 had similar results. (Iron Lake shown)
total cycles in shared programs: 188647754 -> 188647748 (<.01%)
cycles in affected programs: 5096 -> 5090 (-0.12%)
helped: 3
HURT: 0
helped stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
helped stats (rel) min: 0.12% max: 0.12% x̄: 0.12% x̃: 0.12%

Reviewed-by: Matt Turner <mattst88@gmail.com>

src/intel/compiler/brw_nir.c

@@ -538,6 +538,11 @@ brw_nir_optimize(nir_shader *nir, const struct brw_compiler *compiler,
       brw_nir_no_indirect_mask(compiler, nir->info.stage);
 
    bool progress;
+   unsigned lower_flrp =
+      (nir->options->lower_flrp16 ? 16 : 0) |
+      (nir->options->lower_flrp32 ? 32 : 0) |
+      (nir->options->lower_flrp64 ? 64 : 0);
+
    do {
       progress = false;
       OPT(nir_split_array_vars, nir_var_function_temp);
@@ -598,6 +603,24 @@ brw_nir_optimize(nir_shader *nir, const struct brw_compiler *compiler,
       OPT(nir_opt_idiv_const, 32);
       OPT(nir_opt_algebraic);
       OPT(nir_opt_constant_folding);
+
+      if (lower_flrp != 0) {
+         /* To match the old behavior, set always_precise only for scalar
+          * shader stages.
+          */
+         if (OPT(nir_lower_flrp,
+                 lower_flrp,
+                 is_scalar /* always_precise */,
+                 compiler->devinfo->gen >= 6)) {
+            OPT(nir_opt_constant_folding);
+         }
+
+         /* Nothing should rematerialize any flrps, so we only need to do this
+          * lowering once.
+          */
+         lower_flrp = 0;
+      }
+
       OPT(nir_opt_dead_cf);
       if (OPT(nir_opt_trivial_continues)) {
          /* If nir_opt_trivial_continues makes progress, then we need to clean