[Mesa-dev] [PATCH 17/17] nir: Handle FB fetch outputs correctly in nir_lower_io_to_temporaries.

[Francisco Jerez]

This requires emitting a series of copies at the top of the program
from each output variable to the corresponding temporary.  The initial
copy can be skipped for non-framebuffer fetch outputs whose initial
value is undefined, and the final copy needs to be skipped for
read-only outputs (i.e. gl_LastFragData), since it would be illegal to
emit a store output intrinsic for it.
---
 src/compiler/nir/nir_lower_io_to_temporaries.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/src/compiler/nir/nir_lower_io_to_temporaries.c b/src/compiler/nir/nir_lower_io_to_temporaries.c
index 3153a49..c8f94ff 100644
--- a/src/compiler/nir/nir_lower_io_to_temporaries.c
+++ b/src/compiler/nir/nir_lower_io_to_temporaries.c
@@ -49,6 +49,21 @@ emit_copies(nir_cursor cursor, nir_shader *shader, struct exec_list *new_vars,
       nir_variable *newv = exec_node_data(nir_variable, new_node, node);
       nir_variable *temp = exec_node_data(nir_variable, old_node, node);
 
+      /* No need to copy the contents of a non-fb_fetch_output output variable
+       * to the temporary allocated for it, since its initial value is
+       * undefined.
+       */
+      if (temp->data.mode == nir_var_shader_out &&
+          !temp->data.fb_fetch_output)
+         continue;
+
+      /* Can't copy the contents of the temporary back to a read-only
+       * interface variable.  The value of the temporary won't have been
+       * modified by the shader anyway.
+       */
+      if (newv->data.read_only)
+         continue;
+
       nir_intrinsic_instr *copy =
          nir_intrinsic_instr_create(shader, nir_intrinsic_copy_var);
       copy->variables[0] = nir_deref_var_create(copy, newv);
@@ -79,6 +94,10 @@ emit_output_copies_impl(struct lower_io_state *state, nir_function_impl *impl)
          }
       }
    } else if (impl->function == state->entrypoint) {
+      nir_cursor cursor = nir_before_block(nir_start_block(impl));
+      emit_copies(cursor, state->shader, &state->old_outputs,
+                  &state->shader->outputs);
+
       /* For all other shader types, we need to do the copies right before
        * the jumps to the end block.
        */
@@ -121,6 +140,8 @@ create_shadow_temp(struct lower_io_state *state, nir_variable *var)
    const char *mode = (temp->data.mode == nir_var_shader_in) ? "in" : "out";
    temp->name = ralloc_asprintf(var, "%s@%s-temp", mode, nvar->name);
    temp->data.mode = nir_var_global;
+   temp->data.read_only = false;
+   temp->data.fb_fetch_output = false;
    temp->constant_initializer = NULL;
 
    return nvar;
-- 
2.9.0