intel/nir: Call nir_lower_io_to_scalar_early

Shader-db results on Kaby Lake:

    total instructions in shared programs: 15166953 -> 15073611 (-0.62%)
    instructions in affected programs: 2390284 -> 2296942 (-3.91%)
    helped: 16469
    HURT: 505

    total loops in shared programs: 4954 -> 4951 (-0.06%)
    loops in affected programs: 3 -> 0
    helped: 3
    HURT: 0

Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/intel/compiler/brw_nir.c b/src/intel/compiler/brw_nir.c
index 29ad68fdb2a47460652ab00935ebd710e0e9063c..31ffbe613ecd3632aa153a630edb8b7583ae410a 100644 (file)
--- a/src/intel/compiler/brw_nir.c
+++ b/src/intel/compiler/brw_nir.c
@@ -713,6 +713,18 @@ brw_nir_link_shaders(const struct brw_compiler *compiler,
    nir_validate_shader(*producer);
    nir_validate_shader(*consumer);
 
+   const bool p_is_scalar =
+      compiler->scalar_stage[(*producer)->info.stage];
+   const bool c_is_scalar =
+      compiler->scalar_stage[(*consumer)->info.stage];
+
+   if (p_is_scalar && c_is_scalar) {
+      NIR_PASS_V(*producer, nir_lower_io_to_scalar_early, nir_var_shader_out);
+      NIR_PASS_V(*consumer, nir_lower_io_to_scalar_early, nir_var_shader_in);
+      *producer = brw_nir_optimize(*producer, compiler, p_is_scalar);
+      *consumer = brw_nir_optimize(*consumer, compiler, c_is_scalar);
+   }
+
    NIR_PASS_V(*producer, nir_remove_dead_variables, nir_var_shader_out);
    NIR_PASS_V(*consumer, nir_remove_dead_variables, nir_var_shader_in);
 
@@ -729,12 +741,7 @@ brw_nir_link_shaders(const struct brw_compiler *compiler,
       NIR_PASS_V(*consumer, nir_lower_indirect_derefs,
                  brw_nir_no_indirect_mask(compiler, (*consumer)->info.stage));
 
-      const bool p_is_scalar =
-         compiler->scalar_stage[(*producer)->info.stage];
       *producer = brw_nir_optimize(*producer, compiler, p_is_scalar);
-
-      const bool c_is_scalar =
-         compiler->scalar_stage[(*consumer)->info.stage];
       *consumer = brw_nir_optimize(*consumer, compiler, c_is_scalar);
    }
 }