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 <[email protected]>

1 files changed, 25 insertions, 0 deletions

diff --git a/src/amd/vulkan/radv_shader.c b/src/amd/vulkan/radv_shader.c
index 648fb6586f7..7568d59056c 100644
--- a/src/amd/vulkan/radv_shader.c
+++ b/src/amd/vulkan/radv_shader.c
@@ -124,6 +124,10 @@ radv_optimize_nir(struct nir_shader *shader, bool optimize_conservatively,
                   bool allow_copies)
 {
         bool progress;
+        unsigned lower_flrp =
+                (shader->options->lower_flrp16 ? 16 : 0) |
+                (shader->options->lower_flrp32 ? 32 : 0) |
+                (shader->options->lower_flrp64 ? 64 : 0);
 
         do {
                 progress = false;
@@ -164,6 +168,27 @@ radv_optimize_nir(struct nir_shader *shader, bool optimize_conservatively,
                 NIR_PASS(progress, shader, nir_opt_peephole_select, 8, true, true);
                 NIR_PASS(progress, shader, nir_opt_algebraic);
                 NIR_PASS(progress, shader, nir_opt_constant_folding);
+
+                if (lower_flrp != 0) {
+                        bool lower_flrp_progress;
+                        NIR_PASS(lower_flrp_progress,
+                                 shader,
+                                 nir_lower_flrp,
+                                 lower_flrp,
+                                 false /* always_precise */,
+                                 shader->options->lower_ffma);
+                        if (lower_flrp_progress) {
+                                NIR_PASS(progress, shader,
+                                         nir_opt_constant_folding);
+                                progress = true;
+                        }
+
+                        /* Nothing should rematerialize any flrps, so we only
+                         * need to do this lowering once.
+                         */
+                        lower_flrp = 0;
+                }
+
                 NIR_PASS(progress, shader, nir_opt_undef);
                 NIR_PASS(progress, shader, nir_opt_conditional_discard);
                 if (shader->options->max_unroll_iterations) {